System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving project information input by a user; means for analyzing the received project information to extract keywords and attributes; means for selecting appropriate candidates from a font database based on the extracted keywords and attributes; means for presenting the selected candidates to the user in a ranking format; means for receiving feedback regarding fonts selected by the user; and means for refining a recommendation algorithm based on the received 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] In today's global business environment, creative projects targeting different cultural regions are on the rise, but selecting fonts appropriate for each region and culture is not an easy task and requires specialized knowledge. This issue can lead to ineffective communication with the target audience if the font is not selected properly, or to misunderstandings and negative impressions caused by using a culturally incompatible font. Therefore, there is a need for a tool that can automatically recommend fonts appropriate for different regions and cultures and support cross-cultural design projects. [Means for solving the problem]

[0005] This invention provides a system that analyzes project information entered by a user and extracts specific keywords and attributes. This allows appropriate font candidates to be selected from a database and presented to the user in a ranked format. It also includes a means for receiving user feedback and improving the recommendation algorithm based on that feedback. This system automatically recommends fonts optimal for different regions and cultures, effectively supporting users' creative projects. In particular, machine learning is used to continuously improve the accuracy of the algorithm, enhancing its ability to respond to user needs.

[0006] "Project information" refers to information such as target region, cultural background, and emotional tone that a user inputs when proceeding with a creative project.

[0007] "Keywords" are attributes extracted from project information to express the culture and emotional tone specific to a region.

[0008] An "attribute" is an element within the project information that indicates a particular characteristic or feature and is used to select a font.

[0009] A "font database" is a storage device that stores information about various fonts and is used to select fonts.

[0010] "Feedback" refers to information such as the user's evaluation and opinion of the selected font, and the reason for the selection.

[0011] A "recommendation algorithm" is a set of calculations or procedures for automatically selecting the most suitable font based on the user's project information and feedback.

[0012] A "machine learning model" is a technology that allows the system to continuously learn based on feedback data and improve the accuracy of the recommendation algorithm. [Brief explanation of the drawings]

[0013] [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

[0014] 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.

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

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

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

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0028] 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.

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

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] The present invention provides an AI-based system that recommends appropriate fonts based on user input project information. The system selects fonts appropriate for a specific region or culture and continuously improves the recommendation accuracy based on user feedback.

[0035] System configuration

[0036] The system mainly includes the following elements:

[0037] 1. User interface (terminal): An interface for users to input project information and display font recommendation results.

[0038] 2. Server: Analyzes project information, recommends fonts, and collects and analyzes feedback.

[0039] 3. Font database: A database that stores information about various fonts and is used by the recommendation algorithm.

[0040] Program processing explanation

[0041] 1. User information input phase

[0042] Device: The user uses the device to input project information, such as "Target region: Japan" and "Emotional tone: Modern and trustworthy."

[0043] Terminal: The entered information is converted into an appropriate format and sent to the server.

[0044] 2. Data Receipt and Analysis Phase

[0045] Server: The server receives the project information sent from the terminal.

[0046] Server: Analyzes the received data and extracts keywords and attributes related to the project's purpose, cultural background, and emotional tone. For example, it analyzes keywords such as "Japan," "modern," and "trustworthy."

[0047] 3. Candidate selection phase from font database

[0048] Server: The server accesses the font database and generates a list of suitable fonts based on the extracted keywords and attributes.

[0049] Server: An AI algorithm is applied to the generated font list to evaluate the characteristics of each font and create a ranking.

[0050] 4. Recommended font display phase

[0051] Server: Sends a list of fonts in ranking format to the device.

[0052] Terminal: The terminal displays the received font list on the user interface, for example presenting candidates such as "Font A," "Font B," and "Font C."

[0053] 5. User selection and feedback gathering phase

[0054] User: The user selects the most suitable font from the displayed font list.

[0055] User: After completing the selection, the user may enter a reason for their selection or feedback. For example, they may send feedback such as "I found font A to be the easiest to read."

[0056] 6. Feedback Receiving and Analysis Phase

[0057] Server: The server receives the selection information and feedback sent by the user.

[0058] Server: Analyzes the received feedback and extracts the characteristics of the selected font and the reasons for its selection.

[0059] 7. Algorithm improvement phase using machine learning

[0060] Server: The server uses the analysis results to perform machine learning to improve the font recommendation algorithm.

[0061] Server: Adds new data to the learning model to improve the algorithm's accuracy for the next recommendation.

[0062] Specific examples

[0063] Example 1: Website design for the Japanese market

[0064] 1. User information input phase

[0065] Device: User inputs "E-commerce site design for the Japanese market", "Target region: Japan", "Emotional tone: modern and trustworthy".

[0066] 2. Data Receipt and Analysis Phase

[0067] Server: The server extracts keywords such as "Japan," "modern," and "trustworthy."

[0068] 3. Candidate selection phase from font database

[0069] Server: The server generates candidates such as "Font A," "Font B," and "Font C" from the font database and creates a ranking.

[0070] 4. Recommended font display phase

[0071] Terminal: The terminal displays "Font A", "Font B", and "Font C" to the user.

[0072] 5. User selection and feedback gathering phase

[0073] User: The user selects "Font A" and types, "I found it to be more readable than the other fonts."

[0074] 6. Feedback Receiving and Analysis Phase

[0075] Server: The server analyzes that "Font A was chosen because it is highly readable."

[0076] 7. Algorithm improvement phase using machine learning

[0077] Server: The server uses this feedback to improve its algorithm to prioritize "readability" the next time it recommends a font.

[0078] In this manner, the present invention can efficiently recommend fonts that are appropriate for different cultures and regions, and support creative projects.

[0079] The processing flow will be explained below.

[0080] Step 1:

[0081] User: Enters project information via a terminal. For example, the user enters information such as "Target region: Japan" and "Emotional tone: Modern and trustworthy" into an input form.

[0082] Step 2:

[0083] Terminal: Converts the entered project information into the appropriate format and sends it to the server.

[0084] Step 3:

[0085] Server: Receives the project information sent, temporarily stores the received information, and prepares it for analysis.

[0086] Step 4:

[0087] Server: Analyzes the received project information and extracts keywords and attributes such as target region and emotional tone. For example, it identifies keywords such as "Japan," "modern," and "trustworthy."

[0088] Step 5:

[0089] Server: Based on the extracted keywords and attributes, the server accesses a font database to find suitable font candidates. The database contains metadata about each font's cultural background and usage.

[0090] Step 6:

[0091] Server: Based on the search results, an AI algorithm is used to evaluate each font and generate a ranked list of candidate fonts.

[0092] Step 7:

[0093] Server: Sends the generated list of font candidates to the device. The list includes the font names and their respective evaluation scores.

[0094] Step 8:

[0095] Terminal: The received font candidate list is displayed on the user interface. For example, candidates such as "Font A," "Font B," and "Font C" are presented.

[0096] Step 9:

[0097] User: Select the best font from the list of fonts presented. After selecting, the user can also provide feedback and justify their choice.

[0098] Step 10:

[0099] Terminal: Sends the user's selection information and feedback to the server. The feedback may include specific reasons for the selection, such as "I felt that font A was the easiest to read."

[0100] Step 11:

[0101] Server: Receives the selection information and feedback sent. Analyzes the received feedback and extracts the characteristics of the selected font and the reasons for its selection.

[0102] Step 12:

[0103] Server: Using the analysis results, we perform machine learning to improve the font recommendation algorithm. We add new data to the learning model to make the algorithm more accurate for the next font recommendation.

[0104] Step 13:

[0105] Server: Improved algorithms will be applied to the system, allowing it to more accurately recommend the best fonts the next time a user enters project information.

[0106] Example 1

[0107] 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."

[0108] Conventional font recommendation systems have the problem of being unable to fully analyze user input information, resulting in low recommendation accuracy. Furthermore, the lack of a process for utilizing user feedback to improve the recommendation algorithm limits the system's learning ability. This makes it difficult to recommend fonts that are appropriate for different cultures and regions.

[0109] 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.

[0110] In this invention, the server includes means for receiving project information entered by a user, means for analyzing the received project information and extracting keywords and attributes, means for selecting appropriate candidates from a database based on the extracted keywords and attributes, means for presenting the selected candidates to the user in a ranked format, means for receiving feedback on elements selected by the user, means for improving a recommendation algorithm based on the received feedback, means for parsing the extracted keywords and attributes and analyzing them using natural language processing technology, and means for generating a candidate list using a machine learning model, evaluating the characteristics of each candidate, and performing scoring and ranking. This enables the server to accurately recommend the font best suited to the user's project.

[0111] "User" refers to an individual or organization that utilizes the System to input project information and receive font recommendations.

[0112] "Project Information" refers to information entered into the system by a user regarding target geography, emotional tone, design objectives, etc.

[0113] "Analysis" refers to the process of extracting specific keywords and attributes from received project information and using natural language processing or other data processing techniques to make sense of that information.

[0114] "Keywords and attributes" refers to characteristic words and phrases extracted from project information, such as target region, emotional tone, and design purpose.

[0115] The "database" refers to a storage system that stores various fonts and information about them, and is a collection of data used by the recommendation algorithm.

[0116] "Candidate List" refers to a collection of fonts selected from a database that are best suited to the project information.

[0117] "Ranking format" refers to providing multiple candidate fonts in a prioritized list format based on their evaluation scores.

[0118] "Feedback" refers to information such as impressions, opinions, and ratings regarding the font selected by the user.

[0119] "Recommendation algorithm" refers to a computational method or program for selecting the most appropriate font based on project information and user feedback.

[0120] "Natural language processing technology" refers to algorithms and methods that allow computers to understand, analyze, and generate human language.

[0121] A "machine learning model" refers to an algorithm or system that can learn from large amounts of data and perform predictions or classifications for certain tasks.

[0122] The present invention is an AI-based system that recommends appropriate fonts based on project information entered by the user. The system selects fonts appropriate for a specific region or culture and continuously improves the recommendation accuracy based on user feedback. The following describes specific embodiments of the present invention.

[0123] System configuration

[0124] The system mainly includes the following elements:

[0125] 1. User interface (terminal): This is the interface where the user inputs project information and displays font recommendation results.

[0126] 2. Server: Analyzes project information, recommends fonts, and collects and analyzes feedback.

[0127] 3. Database: A database containing information about various fonts, which is used in the recommendation algorithm.

[0128] Program processing overview

[0129] The system operates in the following steps:

[0130] 1. Enter your user information

[0131] The user uses the device to input project information, such as "Target region: Japan" and "Emotional tone: Modern and trustworthy." The device collects this information and sends it to the server as JSON-formatted data.

[0132] 2. Receipt and Analysis

[0133] The server receives the HTTP request and parses the JSON data sent from the device. It then analyzes the received data and extracts keywords and attributes such as the project's purpose, cultural background, and emotional tone. This analysis is performed using natural language processing (NLP) techniques.

[0134] 3. Selecting candidates from the font database

[0135] The server executes a database query to generate a list of suitable font candidates based on the extracted keywords and attributes, and then applies a machine learning model to the list to evaluate the characteristics of each font and perform scoring and ranking.

[0136] 4. Display recommended fonts

[0137] The server sends the ranked font list to the terminal and displays it on the user interface, for example, presenting information such as "Font A," "Font B," and "Font C."

[0138] 5. Feedback Collection

[0139] The user selects the desired font from the displayed font list. After selecting, the reason for the selection and feedback are entered through the terminal, which is converted into JSON format and sent to the server.

[0140] 6. Feedback Analysis

[0141] The server receives the feedback data and stores it in a database. It analyzes the received feedback and quantifies and structures the characteristics of the selected font and the reasons for its selection. This analysis also uses natural language processing technology.

[0142] 7. Algorithm Improvement

[0143] The server uses the analysis results to retrain the machine learning model and improve the font recommendation algorithm, thereby improving the accuracy of the algorithm for the next recommendation.

[0144] Specific examples

[0145] Example 1: Website design for the Japanese market

[0146] Enter your user information:

[0147] The user enters into the interface: "E-commerce site design for the Japanese market," "Target region: Japan," and "Emotional tone: modern and trustworthy."

[0148] Receiving and analyzing data:

[0149] The server extracts keywords such as "Japan," "modern," and "trustworthy."

[0150] Candidate selection from font database:

[0151] The server generates candidates such as "Font A," "Font B," and "Font C" from the database and creates a ranking.

[0152] Show recommended fonts:

[0153] The terminal will display "Font A," "Font B," and "Font C" to the user.

[0154] User Choices and Feedback Collection:

[0155] The user selects "Font A" and enters feedback that "I felt it was easier to read than the other fonts."

[0156] Receiving and analyzing feedback:

[0157] The server analyzes that "Font A was chosen because it is highly readable."

[0158] Machine learning algorithm improvement:

[0159] The server uses this feedback to improve its algorithm to prioritize "readability" the next time it recommends a font.

[0160] In this manner, the present invention can efficiently recommend fonts that are appropriate for different cultures and regions, and support creative projects.

[0161] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0162] Step 1:

[0163] Entering user information

[0164] User: The user uses the terminal interface to input project information, for example, "Target region: Japan" and "Emotional tone: Modern and trustworthy."

[0165] Input: Project information (target region, emotional tone, design objectives, etc.)

[0166] Terminal: The terminal collects input information and stores it in JSON format.

[0167] (Application example 1)

[0168] 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."

[0169] Content distribution services face the challenge of making it difficult for users to easily find the optimal font that matches a specific region, culture, or emotional tone. Additionally, when designing content while taking legibility and cultural compatibility into consideration, selecting the appropriate font from the vast number of available fonts can be time-consuming.

[0170] 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.

[0171] In this invention, the server includes means for receiving project information entered by a user, means for analyzing the received project information and extracting keywords and attributes, means for selecting appropriate candidates from a font database based on the extracted keywords and attributes, means for presenting the selected candidates to the user in a ranked format, means for automatically applying a font selected by the user in a content distribution service based on legibility and cultural suitability, means for receiving feedback regarding the font selected by the user, and means for improving a recommendation algorithm based on the received feedback. This allows users to quickly find fonts suitable for the purpose of their project and enables content design with improved legibility and cultural suitability.

[0172] "Project information" refers to specific requirements and goals, such as target area, emotional tone, and purpose, entered by the user.

[0173] "Keywords and attributes" refer to features such as specific local area names, cultural backgrounds, and emotional tones extracted from project information.

[0174] A "font database" is a database that stores information about various fonts and is a source of information for selecting appropriate fonts based on specific keywords or attributes.

[0175] The "ranking format" refers to a format in which the results evaluated by a recommendation algorithm are ranked and presented to the user.

[0176] "Viewability" refers to the degree to which a user can easily read content.

[0177] "Cultural suitability" refers to the degree to which a font is suitable for a particular region or cultural context.

[0178] "Feedback" refers to the ratings and opinions that users provide about their selected fonts.

[0179] "Recommendation algorithm" refers to a computational method for selecting the best font based on input project information and feedback.

[0180] "Machine learning model" refers to a computer model that has a learning process to improve the accuracy of its recommendation algorithm based on collected data.

[0181] MODE FOR CARRYING OUT THE INVENTION

[0182] This invention is an AI-based system that recommends appropriate fonts based on project information entered by the user. The system selects fonts that are appropriate for a specific region or culture, and continuously improves the recommendation accuracy based on user feedback.

[0183] System configuration

[0184] The system mainly includes the following elements:

[0185] 1. User interface (terminal): An interface for users to input project information and view font recommendation results.

[0186] 2. Server: Analyzes project information, recommends fonts, and collects and analyzes feedback.

[0187] 3. Font Database: A database that stores information about various fonts and is used by the recommendation algorithm.

[0188] Program processing explanation

[0189] 1. User information input phase:

[0190] The user uses a terminal to input project information, such as "Target region: Japan" and "Emotional tone: Modern and trustworthy." They also input "Blog article design" as a situation for the content distribution service.

[0191] 2. Data reception and analysis phase:

[0192] The server receives project information sent from the device, analyzes the received data, and extracts keywords and attributes related to the project's purpose, cultural background, and emotional tone.

[0193] 3. Font database candidate selection phase:

[0194] The server accesses the font database and generates a list of suitable fonts based on the extracted keywords and attributes. An AI algorithm is then applied to the generated font list to evaluate the characteristics of each font and create a ranking.

[0195] 4. Recommended font display phase:

[0196] The server sends a list of fonts in a ranking format to the terminal, which then displays the received font list on the user interface.

[0197] 5. Font auto-application phase:

[0198] The font selected by the user in the content distribution service is automatically applied based on visibility and cultural compatibility, so that the font selected by the user is automatically reflected in accordance with the content design.

[0199] 6. User selection and feedback gathering phase:

[0200] The user selects the most suitable font from the displayed font list, and after completing the selection, inputs the reason for the selection and feedback.

[0201] 7. Feedback receiving and analysis phase:

[0202] The server receives the selection information and feedback sent by the user, analyzes the received feedback, and extracts the characteristics of the selected font and the reasons for its selection.

[0203] 8. Algorithm improvement phase using machine learning:

[0204] The server uses the analysis results to perform machine learning to improve the font recommendation algorithm, adding new data to the learning model and improving the algorithm's accuracy for the next recommendation.

[0205] Specific examples

[0206] A user who wants to design a blog post for the Japanese market enters "Target region: Japan," "Emotional tone: Modern and trustworthy," and "Content type: Blog post design." In this case, the server extracts keywords such as "Japan," "modern," and "trustworthy," and recommends appropriate fonts. The recommended fonts are then automatically applied to the content design.

[0207] Prompt Sentence Examples

[0208] "I'd like to design a blog post for the Japanese market. The target region is Japan, and the emotional tone should be modern and trustworthy. I'd like you to recommend which font would be best for this."

[0209] In this way, the present invention can efficiently recommend fonts that are appropriate for different cultures and regions, supporting creative projects, and continuously improve its accuracy based on user feedback.

[0210] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0211] Step 1:

[0212] The user enters project information using a device, such as "Target region: Japan," "Emotional tone: Modern and trustworthy," and "Content type: Blog article design." This input information is saved as project information.

[0213] Step 2:

[0214] The device converts the input project information into an appropriate format and sends it to the server. The input information is converted into a data structure such as JSON or XML and sent to the server via the network.

[0215] Step 3:

[0216] The server analyzes the received project information. Specifically, it uses natural language processing technology to extract keywords and attributes such as "target region" and "emotional tone." As a result of this analysis, keywords such as "Japan," "modern," and "trustworthy" are obtained.

[0217] Step 4:

[0218] The server accesses the font database and generates a list of suitable font candidates based on the extracted keywords and attributes. The font information is retrieved from the font database, and each font is evaluated using an AI algorithm.

[0219] Step 5:

[0220] The server generates a list of fonts and sends it to the terminal in a ranked format. The fonts are ranked based on the evaluation results, and the list is sent to the terminal.

[0221] Step 6:

[0222] The terminal displays the received font list on the user interface. For example, candidates such as "Font A," "Font B," and "Font C" are presented to the user.

[0223] Step 7:

[0224] In a content distribution service, the font selected by the user is automatically applied based on visibility and cultural suitability. The font selected by the user is automatically reflected in the content design.

[0225] Step 8:

[0226] The user enters feedback about the selected font. For example, the user enters and submits an evaluation such as "I found Font A to be the easiest to read."

[0227] Step 9:

[0228] The server analyzes the received feedback and extracts the characteristics of the selected font and the reasons for its selection.

[0229] Step 10:

[0230] The server uses machine learning models to refine the recommendation algorithm. Based on the collected feedback, it runs a learning process to improve the algorithm's accuracy, which will improve the accuracy of the next font recommendation.

[0231] 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.

[0232] This invention provides an AI-based system that inputs project information from users, analyzes the user's emotional state based on that information using an emotion engine, and recommends appropriate fonts. Furthermore, by improving the recommendation algorithm based on user feedback, the accuracy of the recommendation is continuously improved.

[0233] System configuration

[0234] The system mainly includes the following elements:

[0235] 1. User interface (terminal): An interface for users to input project information and display font recommendation results.

[0236] 2. Server: Analyzes project information, recognizes emotional states through an emotion engine, recommends fonts, and collects and analyzes feedback.

[0237] 3. Font database: A database that stores information about various fonts and is used by the recommendation algorithm.

[0238] 4. Emotion engine: An engine that analyzes the user's emotional state from their input and reactions and reflects this in font selection.

[0239] Program processing explanation

[0240] The program processing of this system will be specifically explained below.

[0241] 1. User information input phase

[0242] Device: The user uses the device to enter project information, such as "Target region: Japan" and "Emotional tone: Modern and trustworthy," into an input form.

[0243] Terminal: The entered project information is converted into an appropriate format and sent to the server.

[0244] 2. Data Receipt and Analysis Phase

[0245] Server: The server receives project information sent from the device, temporarily stores the received information, and prepares it for analysis.

[0246] Server: Analyzes the received project information and extracts keywords and attributes such as target region and emotional tone. For example, it identifies keywords such as "Japan," "modern," and "trustworthy."

[0247] 3. Emotional state analysis phase

[0248] Server: Activates the emotion engine and analyzes the user's emotional state based on the project information and their reactions to the project. For example, the server identifies emotional states such as "relief" or "vigor" based on the user's input and past selection history.

[0249] 4. Candidate selection phase from font database

[0250] Server: Based on the emotional state provided by the emotion engine and the extracted keywords and attributes, the server accesses the font database and searches for suitable font candidates.

[0251] Server: Based on the search results, an AI algorithm is used to evaluate each font and generate a ranked list of candidate fonts.

[0252] 5. Recommended font display phase

[0253] Server: Sends the generated list of font candidates to the device. The list includes the font names and their respective evaluation scores.

[0254] Terminal: The terminal displays the received font list on the user interface. For example, candidates such as "Font A," "Font B," and "Font C" are presented.

[0255] 6. User selection and feedback gathering phase

[0256] User: Select the best font from the list of fonts presented. After selecting, the user can also provide feedback and justify their choice.

[0257] Terminal: Sends the user's selection information and feedback to the server. The feedback may include specific reasons for the selection, such as "I felt that font A was the easiest to read."

[0258] 7. Feedback Receiving and Analysis Phase

[0259] Server: Receives the selection information and feedback sent. Analyzes the received feedback and extracts the characteristics of the selected font and the reasons for its selection.

[0260] 8. Algorithm improvement phase using machine learning

[0261] Server: Using the analysis results, we perform machine learning to improve the font recommendation algorithm. We add new data to the learning model to make the algorithm more accurate for the next font recommendation.

[0262] Specific examples

[0263] Example 1: Website design for the Japanese market

[0264] 1. User information input phase

[0265] Device: User inputs "E-commerce site design for the Japanese market", "Target region: Japan", "Emotional tone: modern and trustworthy".

[0266] 2. Data Receipt and Analysis Phase

[0267] Server: The server extracts keywords such as "Japan," "modern," and "trustworthy."

[0268] 3. Emotional state analysis phase

[0269] Server: Using the emotion engine, determine whether the user has a "sense of security" based on their input and past selection history.

[0270] 4. Candidate selection phase from font database

[0271] Server: The server generates candidates such as "Font A," "Font B," and "Font C" from the font database and creates a ranking.

[0272] 5. Recommended font display phase

[0273] Terminal: The terminal displays "Font A", "Font B", and "Font C" to the user.

[0274] 6. User selection and feedback gathering phase

[0275] User: The user selects "Font A" and types, "I found it to be more readable than the other fonts."

[0276] 7. Feedback Receiving and Analysis Phase

[0277] Server: The server analyzes that "Font A was chosen because it is highly readable."

[0278] 8. Algorithm improvement phase using machine learning

[0279] Server: The server uses this feedback to improve its algorithm to prioritize "readability" the next time it recommends a font.

[0280] In this manner, the present invention can take into account the user's emotional state and efficiently recommend fonts that are appropriate for different cultures and regions, supporting creative projects.

[0281] The processing flow will be explained below.

[0282] Step 1:

[0283] User: Enters project information using a device. For example, enters "Target region: Japan" and "Emotional tone: Modern and trustworthy" into an input form.

[0284] Step 2:

[0285] Terminal: Converts the entered project information into the appropriate format and sends it to the server.

[0286] Step 3:

[0287] Server: Receives the project information sent, temporarily stores the received information, and prepares it for analysis.

[0288] Step 4:

[0289] Server: Analyzes the received project information and extracts keywords and attributes such as target region and emotional tone. For example, it identifies keywords such as "Japan," "modern," and "trustworthy."

[0290] Step 5:

[0291] Server: Activates the emotion engine and analyzes the user's emotional state based on the project information and their reactions to the project. For example, it identifies emotional states such as "relief" and "vigor."

[0292] Step 6:

[0293] Server: Searches for suitable font candidates from the font database based on the extracted keywords and attributes and the emotional state analyzed by the emotion engine.

[0294] Step 7:

[0295] Server: Based on the search results, an AI algorithm is used to evaluate each font and generate a ranked list of candidate fonts.

[0296] Step 8:

[0297] Server: Sends the generated list of font candidates to the device. The list includes the font names and their respective evaluation scores.

[0298] Step 9:

[0299] Terminal: The received font candidate list is displayed on the user interface. For example, candidates such as "Font A," "Font B," and "Font C" are presented.

[0300] Step 10:

[0301] User: Selects the best font from a list of fonts presented, and when selected, optionally provides feedback and justification for the selection.

[0302] Step 11:

[0303] Terminal: Sends the user's selection information and feedback to the server. The feedback may include specific reasons for the selection, such as "I felt that font A was the easiest to read."

[0304] Step 12:

[0305] Server: Receives the selection information and feedback sent. Analyzes the received feedback and extracts the characteristics of the selected font and the reasons for its selection.

[0306] Step 13:

[0307] Server: Using the analysis results, we perform machine learning to improve the font recommendation algorithm. We add new data to the learning model to make the algorithm more accurate for the next font recommendation.

[0308] Step 14:

[0309] Server: Improved algorithms will be applied to the system, allowing it to more accurately recommend the best fonts the next time a user enters project information.

[0310] Example 2

[0311] 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."

[0312] Conventional font recommendation systems have difficulty recommending appropriate fonts because they do not sufficiently consider the user's emotional state or past selection history. Furthermore, they lack a mechanism for utilizing user feedback to improve the accuracy of the algorithm, making it difficult to continuously improve recommendation accuracy.

[0313] 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.

[0314] In this invention, the server includes means for receiving project information entered by a user, means for analyzing the received project information to extract keywords and attributes, means for selecting appropriate candidates from a database based on the extracted keywords and attributes, means for analyzing the user's emotional state based on the user's project information and past selection history using an emotion engine, means for presenting the selected candidates to the user in a ranked format, means for receiving feedback regarding the candidates selected by the user, means for improving a recommendation algorithm based on the received feedback, means for displaying the generated candidate list on a user interface, and means for applying a machine learning model using the received feedback. This enables appropriate font recommendations that take the user's emotional state into consideration and allows the recommendation algorithm to be continuously improved by utilizing user feedback.

[0315] "Project information" refers to information related to a task or project entered by a user.

[0316] "Keywords" are important words or phrases extracted from project information.

[0317] "Attributes" refer to characteristics or properties associated with keywords.

[0318] A "database" is a data store that stores information about various candidates (eg, fonts).

[0319] An "emotion engine" is a device or software that analyzes a user's emotional state based on their project information and past selection history.

[0320] The "ranking format" is a format in which the selected candidates are sorted based on their evaluation scores or rankings.

[0321] "Feedback" refers to the opinions and ratings provided by a user regarding a selected candidate.

[0322] A "recommendation algorithm" is a calculation method or procedure for recommending suitable candidates to a user.

[0323] A "machine learning model" is a model for improving and optimizing algorithms based on data.

[0324] "User interface" refers to the interface, such as input and output devices and screen displays, through which a user interacts with a system.

[0325] This invention provides an AI-based system that inputs project information, analyzes the user's emotional state using an emotion engine based on that information, and recommends appropriate fonts. Furthermore, by improving the recommendation algorithm based on user feedback, recommendation accuracy can be continuously improved.

[0326] System configuration

[0327] The system mainly includes the following elements:

[0328] 1. User interface (terminal): An interface for users to input project information and display font recommendation results.

[0329] 2. Server: This is the device that analyzes project information, recognizes emotional states using the emotion engine, recommends fonts, and collects and analyzes feedback.

[0330] 3. Font database: A database that stores information about various fonts and is used by the recommendation algorithm.

[0331] 4. Emotion engine: This engine analyzes the user's emotional state from their input and reactions and reflects this in font selection.

[0332] Program processing explanation

[0333] 1. User information input phase

[0334] Device: The user uses the device to enter project information, such as "Target region: Japan" and "Emotional tone: Modern and trustworthy," into an input form.

[0335] Terminal: The entered project information is converted into an appropriate format and sent to the server.

[0336] 2. Data Receipt and Analysis Phase

[0337] Server: The server receives the project information sent from the terminal and temporarily stores the received data in memory or a database.

[0338] Server: Analyzes project information using natural language processing algorithms to extract keywords and attributes such as target region and emotional tone. For example, identify keywords such as "Japan," "modern," and "trustworthy."

[0339] 3. Emotional state analysis phase

[0340] Server: Launches an emotion engine (e.g., a general commercial emotion analysis engine) and analyzes the user's emotional state based on the user's project information and past selection history. For example, it analyzes emotions such as "relief" and "liveliness."

[0341] Server: Temporarily stores the analysis results and uses them in the next phase.

[0342] 4. Candidate selection phase from font database

[0343] Server: Accesses the font database based on the emotional state provided by the emotion engine and the extracted keywords and attributes.

[0344] Server: Runs a database query to find suitable font candidates, such as "Font A" that gives a "comfortable feeling" and "Font B" that has a modern design.

[0345] Server: Evaluates each font using an AI algorithm (e.g., random forest) and generates a ranked list of candidate fonts.

[0346] 5. Recommended font display phase

[0347] Server: Sends the generated list of font candidates to the terminal, including the font names and their respective evaluation scores.

[0348] Terminal: The terminal displays the received font list on the user interface. For example, candidates such as "Font A," "Font B," and "Font C" are presented.

[0349] 6. User selection and feedback gathering phase

[0350] User: Select the most suitable font from the presented font list. For example, select "Font A".

[0351] User: After completing the selection, enter the reason for the selection and feedback. For example, enter a specific reason such as "I felt that font A was the easiest to read."

[0352] Terminal: Sends user selection information and feedback to the server.

[0353] 7. Feedback Receiving and Analysis Phase

[0354] Server: Receives the submitted selection information and feedback and stores it in memory or a database for analysis.

[0355] Server: The feedback is analyzed using natural language processing algorithms to extract the characteristics of the selected font and the reasons for its selection.

[0356] 8. Algorithm improvement phase using machine learning

[0357] Server: Uses the analysis results to perform machine learning to improve the font recommendation algorithm, for example, by adding new data to the learning model and retraining the algorithm's parameters.

[0358] Server: Check that the algorithm has improved and prepare the new model for the next font recommendation.

[0359] Specific examples

[0360] Example 1: Website design for the Japanese market

[0361] 1. User information input phase

[0362] Device: User inputs "E-commerce site design for the Japanese market", "Target region: Japan", "Emotional tone: modern and trustworthy".

[0363] Terminal: The terminal sends the input information to the server.

[0364] 2. Data Receipt and Analysis Phase

[0365] Server: The server extracts keywords such as "Japan," "modern," and "trustworthy" and temporarily stores them.

[0366] 3. Emotional state analysis phase

[0367] Server: Using the emotion engine, determine whether the user has a sense of security based on their input and past selection history.

[0368] 4. Candidate selection phase from font database

[0369] Server: The server generates candidates such as "Font A," "Font B," and "Font C" from the font database and creates a ranking.

[0370] 5. Recommended font display phase

[0371] Terminal: The terminal displays "Font A", "Font B", and "Font C" to the user.

[0372] 6. User selection and feedback gathering phase

[0373] User: The user selects "Font A" and types, "I found it to be more readable than the other fonts."

[0374] Terminal: Sends user selection information and feedback to the server.

[0375] 7. Feedback Receiving and Analysis Phase

[0376] Server: The server analyzes that "Font A was chosen because it is highly readable."

[0377] 8. Algorithm improvement phase using machine learning

[0378] Server: The server uses this feedback to improve its algorithm to prioritize "readability" the next time it recommends a font.

[0379] Example input to a generative AI model

[0380] I'd like to design a modern and trustworthy e-commerce website for the Japanese market. The target geography is Japan, and the emotional tone should ideally be modern and trustworthy. Please recommend a suitable font.

[0381] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0382] Step 1:

[0383] Entering user information

[0384] User: Enters project information into the input form provided on the device.

[0385] Specific actions: For example, enter information such as "Target region: Japan" and "Emotional tone: Modern and trustworthy."

[0386] Input: Project information entered by the user.

[0387] Output: Information entered into the terminal is converted into a data format for transmission from the terminal to the server.

[0388] Step 2:

[0389] Receiving data

[0390] Server: Receives project information sent from the device.

[0391] Specific operation: Temporarily store received data in memory or a database.

[0392] Input: Project information sent from the device.

[0393] Output: The received data converted into a parsable data format.

[0394] Step 3:

[0395] Project Information Analysis

[0396] Server: Analyzes project information using natural language processing algorithms.

[0397] What it does: Uses a natural language processing library (e.g., spaCy) to extract keywords and attributes such as "target region: Japan" and "emotional tone: modern and trustworthy."

[0398] Input: Received project information.

[0399] Output: Extracted keywords and attributes (e.g., "Japan," "modern," "trustworthy").

[0400] Step 4:

[0401] Emotional state analysis

[0402] Server: Launches the emotion engine and analyzes the user's emotional state based on project information and past selection history.

[0403] Specific behavior: Analyze emotions such as "relief" and "liveliness" using a commercial sentiment analysis engine (e.g., IBM Watson NLU).

[0404] Input: Parsed keywords and attributes, and the user's past selection history.

[0405] Output: Emotional state as a result of the analysis (e.g., "Relaxed," "Energetic").

[0406] Step 5:

[0407] Search for font suggestions

[0408] Server: Accesses the font database based on the emotional state provided by the emotion engine and the extracted keywords and attributes.

[0409] What it does: Runs a database query to find, for example, "Font A" that gives a "comfortable feeling" and "Font B" that has a modern design.

[0410] Input: Emotional state, extracted keywords and attributes.

[0411] Output: A list of searched font candidates.

[0412] Step 6:

[0413] Rating and ranking of font candidates

[0414] Server: Based on the search results, an AI algorithm is used to evaluate each font and generate a ranked list of font candidates.

[0415] What it does: It uses a random forest algorithm to calculate the font's rating score and then creates a ranking based on the rating score.

[0416] Input: Font candidate list.

[0417] Output: A ranked list of fonts with rating scores.

[0418] Step 7:

[0419] Displaying font recommendation results

[0420] Server: Sends the generated font candidate list to the terminal.

[0421] Specific behavior: Sends data to the device including font names and their respective rating scores.

[0422] Input: Ranked font list.

[0423] Output: Font candidate list sent to the terminal.

[0424] Step 8:

[0425] User selection and feedback input

[0426] User: Select the best font from the list of fonts presented and provide feedback and reasons for their choice.

[0427] Specific action: For example, the user selects "Font A" and enters "I felt it had higher readability than other fonts."

[0428] Input: User font selection and feedback.

[0429] Output: Selection information and feedback are sent from the device to the server.

[0430] Step 9:

[0431] Receiving and analyzing feedback

[0432] Server: Receives the submitted selection information and feedback and temporarily stores it for analysis.

[0433] What it does: It uses natural language processing algorithms to analyze the feedback and extract the characteristics of the selected font and the reasons for its selection.

[0434] Input: User selection information and feedback.

[0435] Output: Extracted selection reasons and font features.

[0436] Step 10:

[0437] Algorithm Improvements

[0438] Server: Uses the analysis results to perform machine learning to improve the font recommendation algorithm.

[0439] What it does: Adds new data to the learning model and retrains the algorithm's parameters.

[0440] Input: Feedback analysis results.

[0441] Output: An improved recommendation algorithm.

[0442] (Application example 2)

[0443] 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."

[0444] Current advertising design creation systems have difficulty recommending fonts that take into account the user's emotional state when selecting an appropriate font based on project information. Another problem is that font selection takes time, making it difficult to achieve an effective design. With conventional technologies, users often select fonts based on intuition or experience, which can result in suboptimal optimization of the advertisement's visual and emotional impact.

[0445] 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.

[0446] In this invention, the server includes: means for receiving project information input by a user; means for analyzing the received project information and extracting keywords and attributes; means for selecting appropriate candidates from a font database based on the extracted keywords and attributes; means for presenting the selected candidates to the user in a ranked format; means for receiving feedback on the font selected by the user; means for improving a recommendation algorithm based on the received feedback; means for including a smartphone application that inputs advertising design project information and recommends optimal fonts; and means for reflecting the user's emotional state in font selection using an emotion analysis engine that analyzes the user's emotional state. This makes it possible to recommend optimal fonts in real time taking into account the user's emotional state, thereby maximizing the visual and emotional impact of advertisements.

[0447] "Project Information" is detailed information a user provides about an advertising design or other design project, including target market, emotional tone, design objectives, and the like.

[0448] A "font database" is a database that stores information about various fonts, including data such as font names, styles, and uses.

[0449] The "ranking format" is a format in which multiple candidates are ranked based on specific criteria and presented, allowing the user to easily make the optimal selection.

[0450] "Feedback" is information such as opinions, ratings, and reasons for a particular font selection that a user provides, and is used to improve the recommendation algorithm next time.

[0451] An "emotion analysis engine" is an engine that analyzes a user's emotional state from their input information and reactions, and supports specific actions and choices based on the results.

[0452] A "smartphone application" is software that runs on a smartphone and allows users to input project information and receive recommendations for optimal fonts.

[0453] "Recommendation algorithm improvement" is the process of improving the accuracy and efficiency of the algorithm based on feedback received from users.

[0454] "Advertising design" is the process of creating the visual representation of an advertising campaign, selecting elements such as fonts, colors, and images to create the optimal advertisement.

[0455] "Emotional state" refers to the psychological or emotional state analyzed based on the user's input and reactions, and includes emotions such as a sense of security and trust.

[0456] MODE FOR CARRYING OUT THE INVENTION

[0457] This invention provides a system that allows users to input project information, such as advertising design, and then uses an emotion analysis engine to analyze the user's emotional state based on that information and recommend appropriate fonts. Furthermore, the recommendation algorithm is improved based on user feedback, continuously improving recommendation accuracy. This system mainly consists of the following components:

[0458] System Components

[0459] 1. User Interface (Smartphone Application): This is an interface where users can input project information for advertising design and view font recommendations. Users input project information such as target market, emotional tone, and design objectives.

[0460] 2. Server: Receives and analyzes project information, uses an emotion analysis engine to recognize the user's emotional state, recommends fonts, collects and analyzes feedback, and accesses the font database to select the appropriate font.

[0461] 3. Font Database: A database that stores information about various fonts, including font names, styles, and uses. The server uses a recommendation algorithm to select an appropriate font from the database.

[0462] 4. Sentiment Analysis Engine: This engine analyzes the user's emotional state from their input information and reactions, and can use non-specific emotion analysis engines such as IBM Watson Tone Analyzer. This engine identifies the user's emotional state from project information and past selection history and reflects this in the font selection.

[0463] System Operation

[0464] The server first receives advertising design project information entered by the user through a smartphone application, including the target market (e.g., Japan), emotional tone (e.g., modern and trustworthy), and design purpose (e.g., display advertising).

[0465] The server then analyzes the received project information and extracts keywords and attributes such as target market, emotional tone, and design purpose. It uses a sentiment analysis engine to analyze the user's emotional state (e.g., sense of security) and selects an appropriate font from a font database based on the results.

[0466] The selected fonts are presented to the user in a ranked format, and the user selects the most suitable font from the recommended fonts. After completing the selection, the user enters the reason for their selection and feedback, which is then sent to the server. For example, the user could provide feedback such as, "I felt that font A was easier to read than the other fonts."

[0467] The server analyzes the received feedback and extracts the characteristics of the selected font and the reasons for its selection. This is then used to apply a machine learning model to improve the accuracy of the recommendation algorithm. This adds new data to the learning model, improving the algorithm's accuracy for the next font recommendation.

[0468] Specific examples

[0469] For example, if a user inputs the project information "Target region: Japan," "Emotional tone: Modern and trustworthy," and "Ad type: Display ads," the system will extract keywords such as "Japan," "modern," and "trustworthy," and use the sentiment analysis engine to identify the emotional state as "reassuring." As a result, it will recommend fonts such as "Font A," "Font B," and "Font C," and continuously refine the algorithm based on user selection and feedback.

[0470] An example of a prompt is as follows:

[0471] "Please recommend a font that would be ideal for advertising designs that have a modern and trustworthy feel."

[0472] "The target region is Japan, and readability is important."

[0473] In this manner, the invention takes into account the user's emotional state and can efficiently recommend optimal fonts suited to different cultures and regions, thereby supporting creative design creation.

[0474] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0475] Step 1:

[0476] Users operate a smartphone application to input project information for advertising design, including the target market (e.g., "Japan"), emotional tone (e.g., "modern and trustworthy"), and design purpose (e.g., "display advertising"). This data is converted into an appropriate format by the application and sent to the server.

[0477] Inputs: Target market, emotional tone, design objectives

[0478] Output: Data converted into the appropriate format

[0479] Specific operation: A form is displayed on the smartphone screen, the user enters project information, the input is converted to JSON format and sent to the server.

[0480] Step 2:

[0481] The server receives project information sent from the smartphone application, temporarily stores the received information, and prepares it for the next analysis.

[0482] Input: Data converted into the appropriate format

[0483] Output: Temporarily saved project information

[0484] Specific operation: The server receives an HTTP request and temporarily stores the received data in a database.

[0485] Step 3:

[0486] The server analyzes the received project information and extracts keywords and attributes such as target market, emotional tone, design objectives, etc. Specifically, it uses text analysis algorithms to identify keywords.

[0487] Input: Temporarily saved project information

[0488] Output: Extracted keywords and attributes

[0489] What it does: The server uses a natural language processing library (e.g., NLTK or spaCy) to parse the project information text and extract important keywords.

[0490] Step 4:

[0491] The server runs an emotion analysis engine, such as IBM Watson Tone Analyzer, to analyze the user's emotional state based on their input and past selection history.

[0492] Input: Extracted keywords and attributes

[0493] Output: User's emotional state

[0494] Specific operation: Project information is sent to the emotion analysis engine, and the engine returns the emotional state as the analysis result.

[0495] Step 5:

[0496] The server accesses the font database and searches for suitable font candidates based on the emotional state provided by the emotion analysis engine and the extracted keywords and attributes. The searched fonts are then evaluated and a candidate list is generated in a ranked format.

[0497] Input: User's emotional state, extracted keywords and attributes

[0498] Output: Ranked list of font candidates

[0499] Specific operation: Runs an SQL query against the font database to extract fonts that match the search criteria, assigns a score to each font, and generates a ranking.

[0500] Step 6:

[0501] The server sends the generated font candidate list to the smartphone application, which displays the received font list on its user interface.

[0502] Input: A ranked list of font candidates

[0503] Output: A list of font candidates displayed in the user interface

[0504] Specific operation: The server sends an HTTP response, the application receives the response and displays the fonts on the screen in list format.

[0505] Step 7:

[0506] The user selects the most suitable font from the presented font list and inputs the reason for their selection and feedback, which is then sent to the server via the smartphone application.

[0507] Input: User font selection and feedback

[0508] Output: Feedback data converted into the appropriate format

[0509] Specific behavior: The user selects a font from a list in the application, fills out an input form explaining the reason for selecting it, and submits it to the server.

[0510] Step 8:

[0511] The server receives and analyzes the selection information and feedback, extracting the characteristics of the selected font and the reasons for its selection.

[0512] Input: Feedback data converted into the appropriate format

[0513] Output: The characteristics of the selected font and the reason for its selection

[0514] What it does: The server stores the feedback data in a database and uses text analysis algorithms to extract important features and reasons.

[0515] Step 9:

[0516] The server uses the analysis results to perform machine learning to improve the recommendation algorithm, adding new data to the learning model and improving the algorithm for the next font recommendation.

[0517] Input: The characteristics of the selected font and the reason for its selection

[0518] Output: Improved recommendation algorithm

[0519] What it does: Uses machine learning libraries (e.g., scikit-learn and TensorFlow) to train models based on feedback data and improve recommendation algorithms.

[0520] 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.

[0521] 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.

[0522] 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.

[0523] [Second embodiment]

[0524] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0525] 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.

[0526] 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).

[0527] 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.

[0528] 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.

[0529] 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).

[0530] 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.

[0531] 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.

[0532] 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.

[0533] 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.

[0534] 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.

[0535] 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."

[0536] The present invention provides an AI-based system that recommends appropriate fonts based on user input project information. The system selects fonts appropriate for a specific region or culture and continuously improves the recommendation accuracy based on user feedback.

[0537] System configuration

[0538] The system mainly includes the following elements:

[0539] 1. User interface (terminal): An interface for users to input project information and display font recommendation results.

[0540] 2. Server: Analyzes project information, recommends fonts, and collects and analyzes feedback.

[0541] 3. Font database: A database that stores information about various fonts and is used by the recommendation algorithm.

[0542] Program processing explanation

[0543] 1. User information input phase

[0544] Device: The user uses the device to input project information, such as "Target region: Japan" and "Emotional tone: Modern and trustworthy."

[0545] Terminal: The entered information is converted into an appropriate format and sent to the server.

[0546] 2. Data Receipt and Analysis Phase

[0547] Server: The server receives the project information sent from the terminal.

[0548] Server: Analyzes the received data and extracts keywords and attributes related to the project's purpose, cultural background, and emotional tone. For example, it analyzes keywords such as "Japan," "modern," and "trustworthy."

[0549] 3. Candidate selection phase from font database

[0550] Server: The server accesses the font database and generates a list of suitable fonts based on the extracted keywords and attributes.

[0551] Server: An AI algorithm is applied to the generated font list to evaluate the characteristics of each font and create a ranking.

[0552] 4. Recommended font display phase

[0553] Server: Sends a list of fonts in ranking format to the device.

[0554] Terminal: The terminal displays the received font list on the user interface, for example presenting candidates such as "Font A," "Font B," and "Font C."

[0555] 5. User selection and feedback gathering phase

[0556] User: The user selects the most suitable font from the displayed font list.

[0557] User: After completing the selection, the user may enter a reason for their selection or feedback. For example, they may send feedback such as "I found font A to be the easiest to read."

[0558] 6. Feedback Receiving and Analysis Phase

[0559] Server: The server receives the selection information and feedback sent by the user.

[0560] Server: Analyzes the received feedback and extracts the characteristics of the selected font and the reasons for its selection.

[0561] 7. Algorithm improvement phase using machine learning

[0562] Server: The server uses the analysis results to perform machine learning to improve the font recommendation algorithm.

[0563] Server: Adds new data to the learning model to improve the algorithm's accuracy for the next recommendation.

[0564] Specific examples

[0565] Example 1: Website design for the Japanese market

[0566] 1. User information input phase

[0567] Device: User inputs "E-commerce site design for the Japanese market", "Target region: Japan", "Emotional tone: modern and trustworthy".

[0568] 2. Data Receipt and Analysis Phase

[0569] Server: The server extracts keywords such as "Japan," "modern," and "trustworthy."

[0570] 3. Candidate selection phase from font database

[0571] Server: The server generates candidates such as "Font A," "Font B," and "Font C" from the font database and creates a ranking.

[0572] 4. Recommended font display phase

[0573] Terminal: The terminal displays "Font A", "Font B", and "Font C" to the user.

[0574] 5. User selection and feedback gathering phase

[0575] User: The user selects "Font A" and types, "I found it to be more readable than the other fonts."

[0576] 6. Feedback Receiving and Analysis Phase

[0577] Server: The server analyzes that "Font A was chosen because it is highly readable."

[0578] 7. Algorithm improvement phase using machine learning

[0579] Server: The server uses this feedback to improve its algorithm to prioritize "readability" the next time it recommends a font.

[0580] In this manner, the present invention can efficiently recommend fonts that are appropriate for different cultures and regions, and support creative projects.

[0581] The processing flow will be explained below.

[0582] Step 1:

[0583] User: Enters project information via a terminal. For example, the user enters information such as "Target region: Japan" and "Emotional tone: Modern and trustworthy" into an input form.

[0584] Step 2:

[0585] Terminal: Converts the entered project information into the appropriate format and sends it to the server.

[0586] Step 3:

[0587] Server: Receives the project information sent, temporarily stores the received information, and prepares it for analysis.

[0588] Step 4:

[0589] Server: Analyzes the received project information and extracts keywords and attributes such as target region and emotional tone. For example, it identifies keywords such as "Japan," "modern," and "trustworthy."

[0590] Step 5:

[0591] Server: Based on the extracted keywords and attributes, the server accesses a font database to find suitable font candidates. The database contains metadata about each font's cultural background and usage.

[0592] Step 6:

[0593] Server: Based on the search results, an AI algorithm is used to evaluate each font and generate a ranked list of candidate fonts.

[0594] Step 7:

[0595] Server: Sends the generated list of font candidates to the device. The list includes the font names and their respective evaluation scores.

[0596] Step 8:

[0597] Terminal: The received font candidate list is displayed on the user interface. For example, candidates such as "Font A," "Font B," and "Font C" are presented.

[0598] Step 9:

[0599] User: Select the best font from the list of fonts presented. After selecting, the user can also provide feedback and justify their choice.

[0600] Step 10:

[0601] Terminal: Sends the user's selection information and feedback to the server. The feedback may include specific reasons for the selection, such as "I felt that font A was the easiest to read."

[0602] Step 11:

[0603] Server: Receives the selection information and feedback sent. Analyzes the received feedback and extracts the characteristics of the selected font and the reasons for its selection.

[0604] Step 12:

[0605] Server: Using the analysis results, we perform machine learning to improve the font recommendation algorithm. We add new data to the learning model to make the algorithm more accurate for the next font recommendation.

[0606] Step 13:

[0607] Server: Improved algorithms will be applied to the system, allowing it to more accurately recommend the best fonts the next time a user enters project information.

[0608] Example 1

[0609] 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."

[0610] Conventional font recommendation systems have the problem of being unable to fully analyze user input information, resulting in low recommendation accuracy. Furthermore, the lack of a process for utilizing user feedback to improve the recommendation algorithm limits the system's learning ability. This makes it difficult to recommend fonts that are appropriate for different cultures and regions.

[0611] 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.

[0612] In this invention, the server includes means for receiving project information entered by a user, means for analyzing the received project information and extracting keywords and attributes, means for selecting appropriate candidates from a database based on the extracted keywords and attributes, means for presenting the selected candidates to the user in a ranked format, means for receiving feedback on elements selected by the user, means for improving a recommendation algorithm based on the received feedback, means for parsing the extracted keywords and attributes and analyzing them using natural language processing technology, and means for generating a candidate list using a machine learning model, evaluating the characteristics of each candidate, and performing scoring and ranking. This enables the server to accurately recommend the font best suited to the user's project.

[0613] "User" refers to an individual or organization that utilizes the System to input project information and receive font recommendations.

[0614] "Project Information" refers to information entered into the system by a user regarding target geography, emotional tone, design objectives, etc.

[0615] "Analysis" refers to the process of extracting specific keywords and attributes from received project information and using natural language processing or other data processing techniques to make sense of that information.

[0616] "Keywords and attributes" refers to characteristic words and phrases extracted from project information, such as target region, emotional tone, and design purpose.

[0617] The "database" refers to a storage system that stores various fonts and information about them, and is a collection of data used by the recommendation algorithm.

[0618] "Candidate List" refers to a collection of fonts selected from a database that are best suited to the project information.

[0619] "Ranking format" refers to providing multiple candidate fonts in a prioritized list format based on their evaluation scores.

[0620] "Feedback" refers to information such as impressions, opinions, and ratings regarding the font selected by the user.

[0621] "Recommendation algorithm" refers to a computational method or program for selecting the most appropriate font based on project information and user feedback.

[0622] "Natural language processing technology" refers to algorithms and methods that allow computers to understand, analyze, and generate human language.

[0623] A "machine learning model" refers to an algorithm or system that can learn from large amounts of data and perform predictions or classifications for certain tasks.

[0624] The present invention is an AI-based system that recommends appropriate fonts based on project information entered by the user. The system selects fonts appropriate for a specific region or culture and continuously improves the recommendation accuracy based on user feedback. The following describes specific embodiments of the present invention.

[0625] System configuration

[0626] The system mainly includes the following elements:

[0627] 1. User interface (terminal): This is the interface where the user inputs project information and displays font recommendation results.

[0628] 2. Server: Analyzes project information, recommends fonts, and collects and analyzes feedback.

[0629] 3. Database: A database containing information about various fonts, which is used in the recommendation algorithm.

[0630] Program processing overview

[0631] The system operates in the following steps:

[0632] 1. Enter your user information

[0633] The user uses the device to input project information, such as "Target region: Japan" and "Emotional tone: Modern and trustworthy." The device collects this information and sends it to the server as JSON-formatted data.

[0634] 2. Receipt and Analysis

[0635] The server receives the HTTP request and parses the JSON data sent from the device. It then analyzes the received data and extracts keywords and attributes such as the project's purpose, cultural background, and emotional tone. This analysis is performed using natural language processing (NLP) techniques.

[0636] 3. Selecting candidates from the font database

[0637] The server executes a database query to generate a list of suitable font candidates based on the extracted keywords and attributes, and then applies a machine learning model to the list to evaluate the characteristics of each font and perform scoring and ranking.

[0638] 4. Display recommended fonts

[0639] The server sends the ranked font list to the terminal and displays it on the user interface, for example, presenting information such as "Font A," "Font B," and "Font C."

[0640] 5. Feedback Collection

[0641] The user selects the desired font from the displayed font list. After selecting, the reason for the selection and feedback are entered through the terminal, which is converted into JSON format and sent to the server.

[0642] 6. Feedback Analysis

[0643] The server receives the feedback data and stores it in a database. It analyzes the received feedback and quantifies and structures the characteristics of the selected font and the reasons for its selection. This analysis also uses natural language processing technology.

[0644] 7. Algorithm Improvement

[0645] The server uses the analysis results to retrain the machine learning model and improve the font recommendation algorithm, thereby improving the accuracy of the algorithm for the next recommendation.

[0646] Specific examples

[0647] Example 1: Website design for the Japanese market

[0648] Enter your user information:

[0649] The user enters into the interface: "E-commerce site design for the Japanese market," "Target region: Japan," and "Emotional tone: modern and trustworthy."

[0650] Receiving and analyzing data:

[0651] The server extracts keywords such as "Japan," "modern," and "trustworthy."

[0652] Candidate selection from font database:

[0653] The server generates candidates such as "Font A," "Font B," and "Font C" from the database and creates a ranking.

[0654] Show recommended fonts:

[0655] The terminal will display "Font A," "Font B," and "Font C" to the user.

[0656] User Choices and Feedback Collection:

[0657] The user selects "Font A" and enters feedback that "I felt it was easier to read than the other fonts."

[0658] Receiving and analyzing feedback:

[0659] The server analyzes that "Font A was chosen because it is highly readable."

[0660] Machine learning algorithm improvement:

[0661] The server uses this feedback to improve its algorithm to prioritize "readability" the next time it recommends a font.

[0662] In this manner, the present invention can efficiently recommend fonts that are appropriate for different cultures and regions, and support creative projects.

[0663] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0664] Step 1:

[0665] Entering user information

[0666] User: The user uses the terminal interface to input project information, for example, "Target region: Japan" and "Emotional tone: Modern and trustworthy."

[0667] Input: Project information (target region, emotional tone, design objectives, etc.)

[0668] Terminal: The terminal collects input information and stores it in JSON format.

[0669] (Application example 1)

[0670] 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."

[0671] Content distribution services face the challenge of making it difficult for users to easily find the optimal font that matches a specific region, culture, or emotional tone. Additionally, when designing content while taking legibility and cultural compatibility into consideration, selecting the appropriate font from the vast number of available fonts can be time-consuming.

[0672] 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.

[0673] In this invention, the server includes means for receiving project information entered by a user, means for analyzing the received project information and extracting keywords and attributes, means for selecting appropriate candidates from a font database based on the extracted keywords and attributes, means for presenting the selected candidates to the user in a ranked format, means for automatically applying a font selected by the user in a content distribution service based on legibility and cultural suitability, means for receiving feedback regarding the font selected by the user, and means for improving a recommendation algorithm based on the received feedback. This allows users to quickly find fonts suitable for the purpose of their project and enables content design with improved legibility and cultural suitability.

[0674] "Project information" refers to specific requirements and goals, such as target area, emotional tone, and purpose, entered by the user.

[0675] "Keywords and attributes" refer to features such as specific local area names, cultural backgrounds, and emotional tones extracted from project information.

[0676] A "font database" is a database that stores information about various fonts and is a source of information for selecting appropriate fonts based on specific keywords or attributes.

[0677] The "ranking format" refers to a format in which the results evaluated by a recommendation algorithm are ranked and presented to the user.

[0678] "Viewability" refers to the degree to which a user can easily read content.

[0679] "Cultural suitability" refers to the degree to which a font is suitable for a particular region or cultural context.

[0680] "Feedback" refers to the ratings and opinions that users provide about their selected fonts.

[0681] "Recommendation algorithm" refers to a computational method for selecting the best font based on input project information and feedback.

[0682] "Machine learning model" refers to a computer model that has a learning process to improve the accuracy of its recommendation algorithm based on collected data.

[0683] MODE FOR CARRYING OUT THE INVENTION

[0684] This invention is an AI-based system that recommends appropriate fonts based on project information entered by the user. The system selects fonts that are appropriate for a specific region or culture, and continuously improves the recommendation accuracy based on user feedback.

[0685] System configuration

[0686] The system mainly includes the following elements:

[0687] 1. User interface (terminal): An interface for users to input project information and view font recommendation results.

[0688] 2. Server: Analyzes project information, recommends fonts, and collects and analyzes feedback.

[0689] 3. Font Database: A database that stores information about various fonts and is used by the recommendation algorithm.

[0690] Program processing explanation

[0691] 1. User information input phase:

[0692] The user uses a terminal to input project information, such as "Target region: Japan" and "Emotional tone: Modern and trustworthy." They also input "Blog article design" as a situation for the content distribution service.

[0693] 2. Data reception and analysis phase:

[0694] The server receives project information sent from the device, analyzes the received data, and extracts keywords and attributes related to the project's purpose, cultural background, and emotional tone.

[0695] 3. Font database candidate selection phase:

[0696] The server accesses the font database and generates a list of suitable fonts based on the extracted keywords and attributes. An AI algorithm is then applied to the generated font list to evaluate the characteristics of each font and create a ranking.

[0697] 4. Recommended font display phase:

[0698] The server sends a list of fonts in a ranking format to the terminal, which then displays the received font list on the user interface.

[0699] 5. Font auto-application phase:

[0700] The font selected by the user in the content distribution service is automatically applied based on visibility and cultural compatibility, so that the font selected by the user is automatically reflected in accordance with the content design.

[0701] 6. User selection and feedback gathering phase:

[0702] The user selects the most suitable font from the displayed font list, and after completing the selection, inputs the reason for the selection and feedback.

[0703] 7. Feedback receiving and analysis phase:

[0704] The server receives the selection information and feedback sent by the user, analyzes the received feedback, and extracts the characteristics of the selected font and the reasons for its selection.

[0705] 8. Algorithm improvement phase using machine learning:

[0706] The server uses the analysis results to perform machine learning to improve the font recommendation algorithm, adding new data to the learning model and improving the algorithm's accuracy for the next recommendation.

[0707] Specific examples

[0708] A user who wants to design a blog post for the Japanese market enters "Target region: Japan," "Emotional tone: Modern and trustworthy," and "Content type: Blog post design." In this case, the server extracts keywords such as "Japan," "modern," and "trustworthy," and recommends appropriate fonts. The recommended fonts are then automatically applied to the content design.

[0709] Prompt Sentence Examples

[0710] "I'd like to design a blog post for the Japanese market. The target region is Japan, and the emotional tone should be modern and trustworthy. I'd like you to recommend which font would be best for this."

[0711] In this way, the present invention can efficiently recommend fonts that are appropriate for different cultures and regions, supporting creative projects, and continuously improve its accuracy based on user feedback.

[0712] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0713] Step 1:

[0714] The user enters project information using a device, such as "Target region: Japan," "Emotional tone: Modern and trustworthy," and "Content type: Blog article design." This input information is saved as project information.

[0715] Step 2:

[0716] The device converts the input project information into an appropriate format and sends it to the server. The input information is converted into a data structure such as JSON or XML and sent to the server via the network.

[0717] Step 3:

[0718] The server analyzes the received project information. Specifically, it uses natural language processing technology to extract keywords and attributes such as "target region" and "emotional tone." As a result of this analysis, keywords such as "Japan," "modern," and "trustworthy" are obtained.

[0719] Step 4:

[0720] The server accesses the font database and generates a list of suitable font candidates based on the extracted keywords and attributes. The font information is retrieved from the font database, and each font is evaluated using an AI algorithm.

[0721] Step 5:

[0722] The server generates a list of fonts and sends it to the terminal in a ranked format. The fonts are ranked based on the evaluation results, and the list is sent to the terminal.

[0723] Step 6:

[0724] The terminal displays the received font list on the user interface. For example, candidates such as "Font A," "Font B," and "Font C" are presented to the user.

[0725] Step 7:

[0726] In a content distribution service, the font selected by the user is automatically applied based on visibility and cultural suitability. The font selected by the user is automatically reflected in the content design.

[0727] Step 8:

[0728] The user enters feedback about the selected font. For example, the user enters and submits an evaluation such as "I found Font A to be the easiest to read."

[0729] Step 9:

[0730] The server analyzes the received feedback and extracts the characteristics of the selected font and the reasons for its selection.

[0731] Step 10:

[0732] The server uses machine learning models to refine the recommendation algorithm. Based on the collected feedback, it runs a learning process to improve the algorithm's accuracy, which will improve the accuracy of the next font recommendation.

[0733] 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.

[0734] This invention provides an AI-based system that inputs project information from users, analyzes the user's emotional state based on that information using an emotion engine, and recommends appropriate fonts. Furthermore, by improving the recommendation algorithm based on user feedback, the accuracy of the recommendation is continuously improved.

[0735] System configuration

[0736] The system mainly includes the following elements:

[0737] 1. User interface (terminal): An interface for users to input project information and display font recommendation results.

[0738] 2. Server: Analyzes project information, recognizes emotional states through an emotion engine, recommends fonts, and collects and analyzes feedback.

[0739] 3. Font database: A database that stores information about various fonts and is used by the recommendation algorithm.

[0740] 4. Emotion engine: An engine that analyzes the user's emotional state from their input and reactions and reflects this in font selection.

[0741] Program processing explanation

[0742] The program processing of this system will be specifically explained below.

[0743] 1. User information input phase

[0744] Device: The user uses the device to enter project information, such as "Target region: Japan" and "Emotional tone: Modern and trustworthy," into an input form.

[0745] Terminal: The entered project information is converted into an appropriate format and sent to the server.

[0746] 2. Data Receipt and Analysis Phase

[0747] Server: The server receives project information sent from the device, temporarily stores the received information, and prepares it for analysis.

[0748] Server: Analyzes the received project information and extracts keywords and attributes such as target region and emotional tone. For example, it identifies keywords such as "Japan," "modern," and "trustworthy."

[0749] 3. Emotional state analysis phase

[0750] Server: Activates the emotion engine and analyzes the user's emotional state based on the project information and their reactions to the project. For example, the server identifies emotional states such as "relief" or "vigor" based on the user's input and past selection history.

[0751] 4. Candidate selection phase from font database

[0752] Server: Based on the emotional state provided by the emotion engine and the extracted keywords and attributes, the server accesses the font database and searches for suitable font candidates.

[0753] Server: Based on the search results, an AI algorithm is used to evaluate each font and generate a ranked list of candidate fonts.

[0754] 5. Recommended font display phase

[0755] Server: Sends the generated list of font candidates to the device. The list includes the font names and their respective evaluation scores.

[0756] Terminal: The terminal displays the received font list on the user interface. For example, candidates such as "Font A," "Font B," and "Font C" are presented.

[0757] 6. User selection and feedback gathering phase

[0758] User: Select the best font from the list of fonts presented. After selecting, the user can also provide feedback and justify their choice.

[0759] Terminal: Sends the user's selection information and feedback to the server. The feedback may include specific reasons for the selection, such as "I felt that font A was the easiest to read."

[0760] 7. Feedback Receiving and Analysis Phase

[0761] Server: Receives the selection information and feedback sent. Analyzes the received feedback and extracts the characteristics of the selected font and the reasons for its selection.

[0762] 8. Algorithm improvement phase using machine learning

[0763] Server: Using the analysis results, we perform machine learning to improve the font recommendation algorithm. We add new data to the learning model to make the algorithm more accurate for the next font recommendation.

[0764] Specific examples

[0765] Example 1: Website design for the Japanese market

[0766] 1. User information input phase

[0767] Device: User inputs "E-commerce site design for the Japanese market", "Target region: Japan", "Emotional tone: modern and trustworthy".

[0768] 2. Data Receipt and Analysis Phase

[0769] Server: The server extracts keywords such as "Japan," "modern," and "trustworthy."

[0770] 3. Emotional state analysis phase

[0771] Server: Using the emotion engine, determine whether the user has a "sense of security" based on their input and past selection history.

[0772] 4. Candidate selection phase from font database

[0773] Server: The server generates candidates such as "Font A," "Font B," and "Font C" from the font database and creates a ranking.

[0774] 5. Recommended font display phase

[0775] Terminal: The terminal displays "Font A", "Font B", and "Font C" to the user.

[0776] 6. User selection and feedback gathering phase

[0777] User: The user selects "Font A" and types, "I found it to be more readable than the other fonts."

[0778] 7. Feedback Receiving and Analysis Phase

[0779] Server: The server analyzes that "Font A was chosen because it is highly readable."

[0780] 8. Algorithm improvement phase using machine learning

[0781] Server: The server uses this feedback to improve its algorithm to prioritize "readability" the next time it recommends a font.

[0782] In this manner, the present invention can take into account the user's emotional state and efficiently recommend fonts that are appropriate for different cultures and regions, supporting creative projects.

[0783] The processing flow will be explained below.

[0784] Step 1:

[0785] User: Enters project information using a device. For example, enters "Target region: Japan" and "Emotional tone: Modern and trustworthy" into an input form.

[0786] Step 2:

[0787] Terminal: Converts the entered project information into the appropriate format and sends it to the server.

[0788] Step 3:

[0789] Server: Receives the project information sent, temporarily stores the received information, and prepares it for analysis.

[0790] Step 4:

[0791] Server: Analyzes the received project information and extracts keywords and attributes such as target region and emotional tone. For example, it identifies keywords such as "Japan," "modern," and "trustworthy."

[0792] Step 5:

[0793] Server: Activates the emotion engine and analyzes the user's emotional state based on the project information and their reactions to the project. For example, it identifies emotional states such as "relief" and "vigor."

[0794] Step 6:

[0795] Server: Searches for suitable font candidates from the font database based on the extracted keywords and attributes and the emotional state analyzed by the emotion engine.

[0796] Step 7:

[0797] Server: Based on the search results, an AI algorithm is used to evaluate each font and generate a ranked list of candidate fonts.

[0798] Step 8:

[0799] Server: Sends the generated list of font candidates to the device. The list includes the font names and their respective evaluation scores.

[0800] Step 9:

[0801] Terminal: The received font candidate list is displayed on the user interface. For example, candidates such as "Font A," "Font B," and "Font C" are presented.

[0802] Step 10:

[0803] User: Selects the best font from a list of fonts presented, and when selected, optionally provides feedback and justification for the selection.

[0804] Step 11:

[0805] Terminal: Sends the user's selection information and feedback to the server. The feedback may include specific reasons for the selection, such as "I felt that font A was the easiest to read."

[0806] Step 12:

[0807] Server: Receives the selection information and feedback sent. Analyzes the received feedback and extracts the characteristics of the selected font and the reasons for its selection.

[0808] Step 13:

[0809] Server: Using the analysis results, we perform machine learning to improve the font recommendation algorithm. We add new data to the learning model to make the algorithm more accurate for the next font recommendation.

[0810] Step 14:

[0811] Server: Improved algorithms will be applied to the system, allowing it to more accurately recommend the best fonts the next time a user enters project information.

[0812] Example 2

[0813] 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."

[0814] Conventional font recommendation systems have difficulty recommending appropriate fonts because they do not sufficiently consider the user's emotional state or past selection history. Furthermore, they lack a mechanism for utilizing user feedback to improve the accuracy of the algorithm, making it difficult to continuously improve recommendation accuracy.

[0815] 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.

[0816] In this invention, the server includes means for receiving project information entered by a user, means for analyzing the received project information to extract keywords and attributes, means for selecting appropriate candidates from a database based on the extracted keywords and attributes, means for analyzing the user's emotional state based on the user's project information and past selection history using an emotion engine, means for presenting the selected candidates to the user in a ranked format, means for receiving feedback regarding the candidates selected by the user, means for improving a recommendation algorithm based on the received feedback, means for displaying the generated candidate list on a user interface, and means for applying a machine learning model using the received feedback. This enables appropriate font recommendations that take the user's emotional state into consideration and allows the recommendation algorithm to be continuously improved by utilizing user feedback.

[0817] "Project information" refers to information related to a task or project entered by a user.

[0818] "Keywords" are important words or phrases extracted from project information.

[0819] "Attributes" refer to characteristics or properties associated with keywords.

[0820] A "database" is a data store that stores information about various candidates (eg, fonts).

[0821] An "emotion engine" is a device or software that analyzes a user's emotional state based on their project information and past selection history.

[0822] The "ranking format" is a format in which the selected candidates are sorted based on their evaluation scores or rankings.

[0823] "Feedback" refers to the opinions and ratings provided by a user regarding a selected candidate.

[0824] A "recommendation algorithm" is a calculation method or procedure for recommending suitable candidates to a user.

[0825] A "machine learning model" is a model for improving and optimizing algorithms based on data.

[0826] "User interface" refers to the interface, such as input and output devices and screen displays, through which a user interacts with a system.

[0827] This invention provides an AI-based system that inputs project information, analyzes the user's emotional state using an emotion engine based on that information, and recommends appropriate fonts. Furthermore, by improving the recommendation algorithm based on user feedback, recommendation accuracy can be continuously improved.

[0828] System configuration

[0829] The system mainly includes the following elements:

[0830] 1. User interface (terminal): An interface for users to input project information and display font recommendation results.

[0831] 2. Server: This is the device that analyzes project information, recognizes emotional states using the emotion engine, recommends fonts, and collects and analyzes feedback.

[0832] 3. Font database: A database that stores information about various fonts and is used by the recommendation algorithm.

[0833] 4. Emotion engine: This engine analyzes the user's emotional state from their input and reactions and reflects this in font selection.

[0834] Program processing explanation

[0835] 1. User information input phase

[0836] Device: The user uses the device to enter project information, such as "Target region: Japan" and "Emotional tone: Modern and trustworthy," into an input form.

[0837] Terminal: The entered project information is converted into an appropriate format and sent to the server.

[0838] 2. Data Receipt and Analysis Phase

[0839] Server: The server receives the project information sent from the terminal and temporarily stores the received data in memory or a database.

[0840] Server: Analyzes project information using natural language processing algorithms to extract keywords and attributes such as target region and emotional tone. For example, identify keywords such as "Japan," "modern," and "trustworthy."

[0841] 3. Emotional state analysis phase

[0842] Server: Launches an emotion engine (e.g., a general commercial emotion analysis engine) and analyzes the user's emotional state based on the user's project information and past selection history. For example, it analyzes emotions such as "relief" and "liveliness."

[0843] Server: Temporarily stores the analysis results and uses them in the next phase.

[0844] 4. Candidate selection phase from font database

[0845] Server: Accesses the font database based on the emotional state provided by the emotion engine and the extracted keywords and attributes.

[0846] Server: Runs a database query to find suitable font candidates, such as "Font A" that gives a "comfortable feeling" and "Font B" that has a modern design.

[0847] Server: Evaluates each font using an AI algorithm (e.g., random forest) and generates a ranked list of candidate fonts.

[0848] 5. Recommended font display phase

[0849] Server: Sends the generated list of font candidates to the terminal, including the font names and their respective evaluation scores.

[0850] Terminal: The terminal displays the received font list on the user interface. For example, candidates such as "Font A," "Font B," and "Font C" are presented.

[0851] 6. User selection and feedback gathering phase

[0852] User: Select the most suitable font from the presented font list. For example, select "Font A".

[0853] User: After completing the selection, enter the reason for the selection and feedback. For example, enter a specific reason such as "I felt that font A was the easiest to read."

[0854] Terminal: Sends user selection information and feedback to the server.

[0855] 7. Feedback Receiving and Analysis Phase

[0856] Server: Receives the submitted selection information and feedback and stores it in memory or a database for analysis.

[0857] Server: The feedback is analyzed using natural language processing algorithms to extract the characteristics of the selected font and the reasons for its selection.

[0858] 8. Algorithm improvement phase using machine learning

[0859] Server: Uses the analysis results to perform machine learning to improve the font recommendation algorithm, for example, by adding new data to the learning model and retraining the algorithm's parameters.

[0860] Server: Check that the algorithm has improved and prepare the new model for the next font recommendation.

[0861] Specific examples

[0862] Example 1: Website design for the Japanese market

[0863] 1. User information input phase

[0864] Device: User inputs "E-commerce site design for the Japanese market", "Target region: Japan", "Emotional tone: modern and trustworthy".

[0865] Terminal: The terminal sends the input information to the server.

[0866] 2. Data Receipt and Analysis Phase

[0867] Server: The server extracts keywords such as "Japan," "modern," and "trustworthy" and temporarily stores them.

[0868] 3. Emotional state analysis phase

[0869] Server: Using the emotion engine, determine whether the user has a sense of security based on their input and past selection history.

[0870] 4. Candidate selection phase from font database

[0871] Server: The server generates candidates such as "Font A," "Font B," and "Font C" from the font database and creates a ranking.

[0872] 5. Recommended font display phase

[0873] Terminal: The terminal displays "Font A", "Font B", and "Font C" to the user.

[0874] 6. User selection and feedback gathering phase

[0875] User: The user selects "Font A" and types, "I found it to be more readable than the other fonts."

[0876] Terminal: Sends user selection information and feedback to the server.

[0877] 7. Feedback Receiving and Analysis Phase

[0878] Server: The server analyzes that "Font A was chosen because it is highly readable."

[0879] 8. Algorithm improvement phase using machine learning

[0880] Server: The server uses this feedback to improve its algorithm to prioritize "readability" the next time it recommends a font.

[0881] Example input to a generative AI model

[0882] I'd like to design a modern and trustworthy e-commerce website for the Japanese market. The target geography is Japan, and the emotional tone should ideally be modern and trustworthy. Please recommend a suitable font.

[0883] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0884] Step 1:

[0885] Entering user information

[0886] User: Enters project information into the input form provided on the device.

[0887] Specific actions: For example, enter information such as "Target region: Japan" and "Emotional tone: Modern and trustworthy."

[0888] Input: Project information entered by the user.

[0889] Output: Information entered into the terminal is converted into a data format for transmission from the terminal to the server.

[0890] Step 2:

[0891] Receiving data

[0892] Server: Receives project information sent from the device.

[0893] Specific operation: Temporarily store received data in memory or a database.

[0894] Input: Project information sent from the device.

[0895] Output: The received data converted into a parsable data format.

[0896] Step 3:

[0897] Project Information Analysis

[0898] Server: Analyzes project information using natural language processing algorithms.

[0899] What it does: Uses a natural language processing library (e.g., spaCy) to extract keywords and attributes such as "target region: Japan" and "emotional tone: modern and trustworthy."

[0900] Input: Received project information.

[0901] Output: Extracted keywords and attributes (e.g., "Japan," "modern," "trustworthy").

[0902] Step 4:

[0903] Emotional state analysis

[0904] Server: Launches the emotion engine and analyzes the user's emotional state based on project information and past selection history.

[0905] Specific behavior: Analyze emotions such as "relief" and "liveliness" using a commercial sentiment analysis engine (e.g., IBM Watson NLU).

[0906] Input: Parsed keywords and attributes, and the user's past selection history.

[0907] Output: Emotional state as a result of the analysis (e.g., "Relaxed," "Energetic").

[0908] Step 5:

[0909] Search for font suggestions

[0910] Server: Accesses the font database based on the emotional state provided by the emotion engine and the extracted keywords and attributes.

[0911] What it does: Runs a database query to find, for example, "Font A" that gives a "comfortable feeling" and "Font B" that has a modern design.

[0912] Input: Emotional state, extracted keywords and attributes.

[0913] Output: A list of searched font candidates.

[0914] Step 6:

[0915] Rating and ranking of font candidates

[0916] Server: Based on the search results, an AI algorithm is used to evaluate each font and generate a ranked list of font candidates.

[0917] What it does: It uses a random forest algorithm to calculate the font's rating score and then creates a ranking based on the rating score.

[0918] Input: Font candidate list.

[0919] Output: A ranked list of fonts with rating scores.

[0920] Step 7:

[0921] Displaying font recommendation results

[0922] Server: Sends the generated font candidate list to the terminal.

[0923] Specific behavior: Sends data to the device including font names and their respective rating scores.

[0924] Input: Ranked font list.

[0925] Output: Font candidate list sent to the terminal.

[0926] Step 8:

[0927] User selection and feedback input

[0928] User: Select the best font from the list of fonts presented and provide feedback and reasons for their choice.

[0929] Specific action: For example, the user selects "Font A" and enters "I felt it had higher readability than other fonts."

[0930] Input: User font selection and feedback.

[0931] Output: Selection information and feedback are sent from the device to the server.

[0932] Step 9:

[0933] Receiving and analyzing feedback

[0934] Server: Receives the submitted selection information and feedback and temporarily stores it for analysis.

[0935] What it does: It uses natural language processing algorithms to analyze the feedback and extract the characteristics of the selected font and the reasons for its selection.

[0936] Input: User selection information and feedback.

[0937] Output: Extracted selection reasons and font features.

[0938] Step 10:

[0939] Algorithm Improvements

[0940] Server: Uses the analysis results to perform machine learning to improve the font recommendation algorithm.

[0941] What it does: Adds new data to the learning model and retrains the algorithm's parameters.

[0942] Input: Feedback analysis results.

[0943] Output: An improved recommendation algorithm.

[0944] (Application example 2)

[0945] 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."

[0946] Current advertising design creation systems have difficulty recommending fonts that take into account the user's emotional state when selecting an appropriate font based on project information. Another problem is that font selection takes time, making it difficult to achieve an effective design. With conventional technologies, users often select fonts based on intuition or experience, which can result in suboptimal optimization of the advertisement's visual and emotional impact.

[0947] 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.

[0948] In this invention, the server includes: means for receiving project information input by a user; means for analyzing the received project information and extracting keywords and attributes; means for selecting appropriate candidates from a font database based on the extracted keywords and attributes; means for presenting the selected candidates to the user in a ranked format; means for receiving feedback on the font selected by the user; means for improving a recommendation algorithm based on the received feedback; means for including a smartphone application that inputs advertising design project information and recommends optimal fonts; and means for reflecting the user's emotional state in font selection using an emotion analysis engine that analyzes the user's emotional state. This makes it possible to recommend optimal fonts in real time taking into account the user's emotional state, thereby maximizing the visual and emotional impact of advertisements.

[0949] "Project Information" is detailed information a user provides about an advertising design or other design project, including target market, emotional tone, design objectives, and the like.

[0950] A "font database" is a database that stores information about various fonts, including data such as font names, styles, and uses.

[0951] The "ranking format" is a format in which multiple candidates are ranked based on specific criteria and presented, allowing the user to easily make the optimal selection.

[0952] "Feedback" is information such as opinions, ratings, and reasons for a particular font selection that a user provides, and is used to improve the recommendation algorithm next time.

[0953] An "emotion analysis engine" is an engine that analyzes a user's emotional state from their input information and reactions, and supports specific actions and choices based on the results.

[0954] A "smartphone application" is software that runs on a smartphone and allows users to input project information and receive recommendations for optimal fonts.

[0955] "Recommendation algorithm improvement" is the process of improving the accuracy and efficiency of the algorithm based on feedback received from users.

[0956] "Advertising design" is the process of creating the visual representation of an advertising campaign, selecting elements such as fonts, colors, and images to create the optimal advertisement.

[0957] "Emotional state" refers to the psychological or emotional state analyzed based on the user's input and reactions, and includes emotions such as a sense of security and trust.

[0958] MODE FOR CARRYING OUT THE INVENTION

[0959] This invention provides a system that allows users to input project information, such as advertising design, and then uses an emotion analysis engine to analyze the user's emotional state based on that information and recommend appropriate fonts. Furthermore, the recommendation algorithm is improved based on user feedback, continuously improving recommendation accuracy. This system mainly consists of the following components:

[0960] System Components

[0961] 1. User Interface (Smartphone Application): This is an interface where users can input project information for advertising design and view font recommendations. Users input project information such as target market, emotional tone, and design objectives.

[0962] 2. Server: Receives and analyzes project information, uses an emotion analysis engine to recognize the user's emotional state, recommends fonts, collects and analyzes feedback, and accesses the font database to select the appropriate font.

[0963] 3. Font Database: A database that stores information about various fonts, including font names, styles, and uses. The server uses a recommendation algorithm to select an appropriate font from the database.

[0964] 4. Sentiment Analysis Engine: This engine analyzes the user's emotional state from their input information and reactions, and can use non-specific emotion analysis engines such as IBM Watson Tone Analyzer. This engine identifies the user's emotional state from project information and past selection history and reflects this in the font selection.

[0965] System Operation

[0966] The server first receives advertising design project information entered by the user through a smartphone application, including the target market (e.g., Japan), emotional tone (e.g., modern and trustworthy), and design purpose (e.g., display advertising).

[0967] The server then analyzes the received project information and extracts keywords and attributes such as target market, emotional tone, and design purpose. It uses a sentiment analysis engine to analyze the user's emotional state (e.g., sense of security) and selects an appropriate font from a font database based on the results.

[0968] The selected fonts are presented to the user in a ranked format, and the user selects the most suitable font from the recommended fonts. After completing the selection, the user enters the reason for their selection and feedback, which is then sent to the server. For example, the user could provide feedback such as, "I felt that font A was easier to read than the other fonts."

[0969] The server analyzes the received feedback and extracts the characteristics of the selected font and the reasons for its selection. This is then used to apply a machine learning model to improve the accuracy of the recommendation algorithm. This adds new data to the learning model, improving the algorithm's accuracy for the next font recommendation.

[0970] Specific examples

[0971] For example, if a user inputs the project information "Target region: Japan," "Emotional tone: Modern and trustworthy," and "Ad type: Display ads," the system will extract keywords such as "Japan," "modern," and "trustworthy," and use the sentiment analysis engine to identify the emotional state as "reassuring." As a result, it will recommend fonts such as "Font A," "Font B," and "Font C," and continuously refine the algorithm based on user selection and feedback.

[0972] An example of a prompt is as follows:

[0973] "Please recommend a font that would be ideal for advertising designs that have a modern and trustworthy feel."

[0974] "The target region is Japan, and readability is important."

[0975] In this manner, the invention takes into account the user's emotional state and can efficiently recommend optimal fonts suited to different cultures and regions, thereby supporting creative design creation.

[0976] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0977] Step 1:

[0978] Users operate a smartphone application to input project information for advertising design, including the target market (e.g., "Japan"), emotional tone (e.g., "modern and trustworthy"), and design purpose (e.g., "display advertising"). This data is converted into an appropriate format by the application and sent to the server.

[0979] Inputs: Target market, emotional tone, design objectives

[0980] Output: Data converted into the appropriate format

[0981] Specific operation: A form is displayed on the smartphone screen, the user enters project information, the input is converted to JSON format and sent to the server.

[0982] Step 2:

[0983] The server receives project information sent from the smartphone application, temporarily stores the received information, and prepares it for the next analysis.

[0984] Input: Data converted into the appropriate format

[0985] Output: Temporarily saved project information

[0986] Specific operation: The server receives an HTTP request and temporarily stores the received data in a database.

[0987] Step 3:

[0988] The server analyzes the received project information and extracts keywords and attributes such as target market, emotional tone, design objectives, etc. Specifically, it uses text analysis algorithms to identify keywords.

[0989] Input: Temporarily saved project information

[0990] Output: Extracted keywords and attributes

[0991] What it does: The server uses a natural language processing library (e.g., NLTK or spaCy) to parse the project information text and extract important keywords.

[0992] Step 4:

[0993] The server runs an emotion analysis engine, such as IBM Watson Tone Analyzer, to analyze the user's emotional state based on their input and past selection history.

[0994] Input: Extracted keywords and attributes

[0995] Output: User's emotional state

[0996] Specific operation: Project information is sent to the emotion analysis engine, and the engine returns the emotional state as the analysis result.

[0997] Step 5:

[0998] The server accesses the font database and searches for suitable font candidates based on the emotional state provided by the emotion analysis engine and the extracted keywords and attributes. The searched fonts are then evaluated and a candidate list is generated in a ranked format.

[0999] Input: User's emotional state, extracted keywords and attributes

[1000] Output: Ranked list of font candidates

[1001] Specific operation: Runs an SQL query against the font database to extract fonts that match the search criteria, assigns a score to each font, and generates a ranking.

[1002] Step 6:

[1003] The server sends the generated font candidate list to the smartphone application, which displays the received font list on its user interface.

[1004] Input: A ranked list of font candidates

[1005] Output: A list of font candidates displayed in the user interface

[1006] Specific operation: The server sends an HTTP response, the application receives the response and displays the fonts on the screen in list format.

[1007] Step 7:

[1008] The user selects the most suitable font from the presented font list and inputs the reason for their selection and feedback, which is then sent to the server via the smartphone application.

[1009] Input: User font selection and feedback

[1010] Output: Feedback data converted into the appropriate format

[1011] Specific behavior: The user selects a font from a list in the application, fills out an input form explaining the reason for selecting it, and submits it to the server.

[1012] Step 8:

[1013] The server receives and analyzes the selection information and feedback, extracting the characteristics of the selected font and the reasons for its selection.

[1014] Input: Feedback data converted into the appropriate format

[1015] Output: The characteristics of the selected font and the reason for its selection

[1016] What it does: The server stores the feedback data in a database and uses text analysis algorithms to extract important features and reasons.

[1017] Step 9:

[1018] The server uses the analysis results to perform machine learning to improve the recommendation algorithm, adding new data to the learning model and improving the algorithm for the next font recommendation.

[1019] Input: The characteristics of the selected font and the reason for its selection

[1020] Output: Improved recommendation algorithm

[1021] What it does: Uses machine learning libraries (e.g., scikit-learn and TensorFlow) to train models based on feedback data and improve recommendation algorithms.

[1022] 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.

[1023] 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.

[1024] 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.

[1025] [Third embodiment]

[1026] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1027] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1028] 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).

[1029] 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.

[1030] 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.

[1031] 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).

[1032] 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.

[1033] 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.

[1034] 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.

[1035] 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.

[1036] 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.

[1037] 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."

[1038] The present invention provides an AI-based system that recommends appropriate fonts based on user input project information. The system selects fonts appropriate for a specific region or culture and continuously improves the recommendation accuracy based on user feedback.

[1039] System configuration

[1040] The system mainly includes the following elements:

[1041] 1. User interface (terminal): An interface for users to input project information and display font recommendation results.

[1042] 2. Server: Analyzes project information, recommends fonts, and collects and analyzes feedback.

[1043] 3. Font database: A database that stores information about various fonts and is used by the recommendation algorithm.

[1044] Program processing explanation

[1045] 1. User information input phase

[1046] Device: The user uses the device to input project information, such as "Target region: Japan" and "Emotional tone: Modern and trustworthy."

[1047] Terminal: The entered information is converted into an appropriate format and sent to the server.

[1048] 2. Data Receipt and Analysis Phase

[1049] Server: The server receives the project information sent from the terminal.

[1050] Server: Analyzes the received data and extracts keywords and attributes related to the project's purpose, cultural background, and emotional tone. For example, it analyzes keywords such as "Japan," "modern," and "trustworthy."

[1051] 3. Candidate selection phase from font database

[1052] Server: The server accesses the font database and generates a list of suitable fonts based on the extracted keywords and attributes.

[1053] Server: An AI algorithm is applied to the generated font list to evaluate the characteristics of each font and create a ranking.

[1054] 4. Recommended font display phase

[1055] Server: Sends a list of fonts in ranking format to the device.

[1056] Terminal: The terminal displays the received font list on the user interface, for example presenting candidates such as "Font A," "Font B," and "Font C."

[1057] 5. User selection and feedback gathering phase

[1058] User: The user selects the most suitable font from the displayed font list.

[1059] User: After completing the selection, the user may enter a reason for their selection or feedback. For example, they may send feedback such as "I found font A to be the easiest to read."

[1060] 6. Feedback Receiving and Analysis Phase

[1061] Server: The server receives the selection information and feedback sent by the user.

[1062] Server: Analyzes the received feedback and extracts the characteristics of the selected font and the reasons for its selection.

[1063] 7. Algorithm improvement phase using machine learning

[1064] Server: The server uses the analysis results to perform machine learning to improve the font recommendation algorithm.

[1065] Server: Adds new data to the learning model to improve the algorithm's accuracy for the next recommendation.

[1066] Specific examples

[1067] Example 1: Website design for the Japanese market

[1068] 1. User information input phase

[1069] Device: User inputs "E-commerce site design for the Japanese market", "Target region: Japan", "Emotional tone: modern and trustworthy".

[1070] 2. Data Receipt and Analysis Phase

[1071] Server: The server extracts keywords such as "Japan," "modern," and "trustworthy."

[1072] 3. Candidate selection phase from font database

[1073] Server: The server generates candidates such as "Font A," "Font B," and "Font C" from the font database and creates a ranking.

[1074] 4. Recommended font display phase

[1075] Terminal: The terminal displays "Font A", "Font B", and "Font C" to the user.

[1076] 5. User selection and feedback gathering phase

[1077] User: The user selects "Font A" and types, "I found it to be more readable than the other fonts."

[1078] 6. Feedback Receiving and Analysis Phase

[1079] Server: The server analyzes that "Font A was chosen because it is highly readable."

[1080] 7. Algorithm improvement phase using machine learning

[1081] Server: The server uses this feedback to improve its algorithm to prioritize "readability" the next time it recommends a font.

[1082] In this manner, the present invention can efficiently recommend fonts that are appropriate for different cultures and regions, and support creative projects.

[1083] The processing flow will be explained below.

[1084] Step 1:

[1085] User: Enters project information via a terminal. For example, the user enters information such as "Target region: Japan" and "Emotional tone: Modern and trustworthy" into an input form.

[1086] Step 2:

[1087] Terminal: Converts the entered project information into the appropriate format and sends it to the server.

[1088] Step 3:

[1089] Server: Receives the project information sent, temporarily stores the received information, and prepares it for analysis.

[1090] Step 4:

[1091] Server: Analyzes the received project information and extracts keywords and attributes such as target region and emotional tone. For example, it identifies keywords such as "Japan," "modern," and "trustworthy."

[1092] Step 5:

[1093] Server: Based on the extracted keywords and attributes, the server accesses a font database to find suitable font candidates. The database contains metadata about each font's cultural background and usage.

[1094] Step 6:

[1095] Server: Based on the search results, an AI algorithm is used to evaluate each font and generate a ranked list of candidate fonts.

[1096] Step 7:

[1097] Server: Sends the generated list of font candidates to the device. The list includes the font names and their respective evaluation scores.

[1098] Step 8:

[1099] Terminal: The received font candidate list is displayed on the user interface. For example, candidates such as "Font A," "Font B," and "Font C" are presented.

[1100] Step 9:

[1101] User: Select the best font from the list of fonts presented. After selecting, the user can also provide feedback and justify their choice.

[1102] Step 10:

[1103] Terminal: Sends the user's selection information and feedback to the server. The feedback may include specific reasons for the selection, such as "I felt that font A was the easiest to read."

[1104] Step 11:

[1105] Server: Receives the selection information and feedback sent. Analyzes the received feedback and extracts the characteristics of the selected font and the reasons for its selection.

[1106] Step 12:

[1107] Server: Using the analysis results, we perform machine learning to improve the font recommendation algorithm. We add new data to the learning model to make the algorithm more accurate for the next font recommendation.

[1108] Step 13:

[1109] Server: Improved algorithms will be applied to the system, allowing it to more accurately recommend the best fonts the next time a user enters project information.

[1110] Example 1

[1111] 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."

[1112] Conventional font recommendation systems have the problem of being unable to fully analyze user input information, resulting in low recommendation accuracy. Furthermore, the lack of a process for utilizing user feedback to improve the recommendation algorithm limits the system's learning ability. This makes it difficult to recommend fonts that are appropriate for different cultures and regions.

[1113] 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.

[1114] In this invention, the server includes means for receiving project information entered by a user, means for analyzing the received project information and extracting keywords and attributes, means for selecting appropriate candidates from a database based on the extracted keywords and attributes, means for presenting the selected candidates to the user in a ranked format, means for receiving feedback on elements selected by the user, means for improving a recommendation algorithm based on the received feedback, means for parsing the extracted keywords and attributes and analyzing them using natural language processing technology, and means for generating a candidate list using a machine learning model, evaluating the characteristics of each candidate, and performing scoring and ranking. This enables the server to accurately recommend the font best suited to the user's project.

[1115] "User" refers to an individual or organization that utilizes the System to input project information and receive font recommendations.

[1116] "Project Information" refers to information entered into the system by a user regarding target geography, emotional tone, design objectives, etc.

[1117] "Analysis" refers to the process of extracting specific keywords and attributes from received project information and using natural language processing or other data processing techniques to make sense of that information.

[1118] "Keywords and attributes" refers to characteristic words and phrases extracted from project information, such as target region, emotional tone, and design purpose.

[1119] The "database" refers to a storage system that stores various fonts and information about them, and is a collection of data used by the recommendation algorithm.

[1120] "Candidate List" refers to a collection of fonts selected from a database that are best suited to the project information.

[1121] "Ranking format" refers to providing multiple candidate fonts in a prioritized list format based on their evaluation scores.

[1122] "Feedback" refers to information such as impressions, opinions, and ratings regarding the font selected by the user.

[1123] "Recommendation algorithm" refers to a computational method or program for selecting the most appropriate font based on project information and user feedback.

[1124] "Natural language processing technology" refers to algorithms and methods that allow computers to understand, analyze, and generate human language.

[1125] A "machine learning model" refers to an algorithm or system that can learn from large amounts of data and perform predictions or classifications for certain tasks.

[1126] The present invention is an AI-based system that recommends appropriate fonts based on project information entered by the user. The system selects fonts appropriate for a specific region or culture and continuously improves the recommendation accuracy based on user feedback. The following describes specific embodiments of the present invention.

[1127] System configuration

[1128] The system mainly includes the following elements:

[1129] 1. User interface (terminal): This is the interface where the user inputs project information and displays font recommendation results.

[1130] 2. Server: Analyzes project information, recommends fonts, and collects and analyzes feedback.

[1131] 3. Database: A database containing information about various fonts, which is used in the recommendation algorithm.

[1132] Program processing overview

[1133] The system operates in the following steps:

[1134] 1. Enter your user information

[1135] The user uses the device to input project information, such as "Target region: Japan" and "Emotional tone: Modern and trustworthy." The device collects this information and sends it to the server as JSON-formatted data.

[1136] 2. Receipt and Analysis

[1137] The server receives the HTTP request and parses the JSON data sent from the device. It then analyzes the received data and extracts keywords and attributes such as the project's purpose, cultural background, and emotional tone. This analysis is performed using natural language processing (NLP) techniques.

[1138] 3. Selecting candidates from the font database

[1139] The server executes a database query to generate a list of suitable font candidates based on the extracted keywords and attributes, and then applies a machine learning model to the list to evaluate the characteristics of each font and perform scoring and ranking.

[1140] 4. Display recommended fonts

[1141] The server sends the ranked font list to the terminal and displays it on the user interface, for example, presenting information such as "Font A," "Font B," and "Font C."

[1142] 5. Feedback Collection

[1143] The user selects the desired font from the displayed font list. After selecting, the reason for the selection and feedback are entered through the terminal, which is converted into JSON format and sent to the server.

[1144] 6. Feedback Analysis

[1145] The server receives the feedback data and stores it in a database. It analyzes the received feedback and quantifies and structures the characteristics of the selected font and the reasons for its selection. This analysis also uses natural language processing technology.

[1146] 7. Algorithm Improvement

[1147] The server uses the analysis results to retrain the machine learning model and improve the font recommendation algorithm, thereby improving the accuracy of the algorithm for the next recommendation.

[1148] Specific examples

[1149] Example 1: Website design for the Japanese market

[1150] Enter your user information:

[1151] The user enters into the interface: "E-commerce site design for the Japanese market," "Target region: Japan," and "Emotional tone: modern and trustworthy."

[1152] Receiving and analyzing data:

[1153] The server extracts keywords such as "Japan," "modern," and "trustworthy."

[1154] Candidate selection from font database:

[1155] The server generates candidates such as "Font A," "Font B," and "Font C" from the database and creates a ranking.

[1156] Show recommended fonts:

[1157] The terminal will display "Font A," "Font B," and "Font C" to the user.

[1158] User Choices and Feedback Collection:

[1159] The user selects "Font A" and enters feedback that "I felt it was easier to read than the other fonts."

[1160] Receiving and analyzing feedback:

[1161] The server analyzes that "Font A was chosen because it is highly readable."

[1162] Machine learning algorithm improvement:

[1163] The server uses this feedback to improve its algorithm to prioritize "readability" the next time it recommends a font.

[1164] In this manner, the present invention can efficiently recommend fonts that are appropriate for different cultures and regions, and support creative projects.

[1165] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1166] Step 1:

[1167] Entering user information

[1168] User: The user uses the terminal interface to input project information, for example, "Target region: Japan" and "Emotional tone: Modern and trustworthy."

[1169] Input: Project information (target region, emotional tone, design objectives, etc.)

[1170] Terminal: The terminal collects input information and stores it in JSON format.

[1171] (Application example 1)

[1172] 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."

[1173] Content distribution services face the challenge of making it difficult for users to easily find the optimal font that matches a specific region, culture, or emotional tone. Additionally, when designing content while taking legibility and cultural compatibility into consideration, selecting the appropriate font from the vast number of available fonts can be time-consuming.

[1174] 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.

[1175] In this invention, the server includes means for receiving project information entered by a user, means for analyzing the received project information and extracting keywords and attributes, means for selecting appropriate candidates from a font database based on the extracted keywords and attributes, means for presenting the selected candidates to the user in a ranked format, means for automatically applying a font selected by the user in a content distribution service based on legibility and cultural suitability, means for receiving feedback regarding the font selected by the user, and means for improving a recommendation algorithm based on the received feedback. This allows users to quickly find fonts suitable for the purpose of their project and enables content design with improved legibility and cultural suitability.

[1176] "Project information" refers to specific requirements and goals, such as target area, emotional tone, and purpose, entered by the user.

[1177] "Keywords and attributes" refer to features such as specific local area names, cultural backgrounds, and emotional tones extracted from project information.

[1178] A "font database" is a database that stores information about various fonts and is a source of information for selecting appropriate fonts based on specific keywords or attributes.

[1179] The "ranking format" refers to a format in which the results evaluated by a recommendation algorithm are ranked and presented to the user.

[1180] "Viewability" refers to the degree to which a user can easily read content.

[1181] "Cultural suitability" refers to the degree to which a font is suitable for a particular region or cultural context.

[1182] "Feedback" refers to the ratings and opinions that users provide about their selected fonts.

[1183] "Recommendation algorithm" refers to a computational method for selecting the best font based on input project information and feedback.

[1184] "Machine learning model" refers to a computer model that has a learning process to improve the accuracy of its recommendation algorithm based on collected data.

[1185] MODE FOR CARRYING OUT THE INVENTION

[1186] This invention is an AI-based system that recommends appropriate fonts based on project information entered by the user. The system selects fonts that are appropriate for a specific region or culture, and continuously improves the recommendation accuracy based on user feedback.

[1187] System configuration

[1188] The system mainly includes the following elements:

[1189] 1. User interface (terminal): An interface for users to input project information and view font recommendation results.

[1190] 2. Server: Analyzes project information, recommends fonts, and collects and analyzes feedback.

[1191] 3. Font Database: A database that stores information about various fonts and is used by the recommendation algorithm.

[1192] Program processing explanation

[1193] 1. User information input phase:

[1194] The user uses a terminal to input project information, such as "Target region: Japan" and "Emotional tone: Modern and trustworthy." They also input "Blog article design" as a situation for the content distribution service.

[1195] 2. Data reception and analysis phase:

[1196] The server receives project information sent from the device, analyzes the received data, and extracts keywords and attributes related to the project's purpose, cultural background, and emotional tone.

[1197] 3. Font database candidate selection phase:

[1198] The server accesses the font database and generates a list of suitable fonts based on the extracted keywords and attributes. An AI algorithm is then applied to the generated font list to evaluate the characteristics of each font and create a ranking.

[1199] 4. Recommended font display phase:

[1200] The server sends a list of fonts in a ranking format to the terminal, which then displays the received font list on the user interface.

[1201] 5. Font auto-application phase:

[1202] The font selected by the user in the content distribution service is automatically applied based on visibility and cultural compatibility, so that the font selected by the user is automatically reflected in accordance with the content design.

[1203] 6. User selection and feedback gathering phase:

[1204] The user selects the most suitable font from the displayed font list, and after completing the selection, inputs the reason for the selection and feedback.

[1205] 7. Feedback receiving and analysis phase:

[1206] The server receives the selection information and feedback sent by the user, analyzes the received feedback, and extracts the characteristics of the selected font and the reasons for its selection.

[1207] 8. Algorithm improvement phase using machine learning:

[1208] The server uses the analysis results to perform machine learning to improve the font recommendation algorithm, adding new data to the learning model and improving the algorithm's accuracy for the next recommendation.

[1209] Specific examples

[1210] A user who wants to design a blog post for the Japanese market enters "Target region: Japan," "Emotional tone: Modern and trustworthy," and "Content type: Blog post design." In this case, the server extracts keywords such as "Japan," "modern," and "trustworthy," and recommends appropriate fonts. The recommended fonts are then automatically applied to the content design.

[1211] Prompt Sentence Examples

[1212] "I'd like to design a blog post for the Japanese market. The target region is Japan, and the emotional tone should be modern and trustworthy. I'd like you to recommend which font would be best for this."

[1213] In this way, the present invention can efficiently recommend fonts that are appropriate for different cultures and regions, supporting creative projects, and continuously improve its accuracy based on user feedback.

[1214] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1215] Step 1:

[1216] The user enters project information using a device, such as "Target region: Japan," "Emotional tone: Modern and trustworthy," and "Content type: Blog article design." This input information is saved as project information.

[1217] Step 2:

[1218] The device converts the input project information into an appropriate format and sends it to the server. The input information is converted into a data structure such as JSON or XML and sent to the server via the network.

[1219] Step 3:

[1220] The server analyzes the received project information. Specifically, it uses natural language processing technology to extract keywords and attributes such as "target region" and "emotional tone." As a result of this analysis, keywords such as "Japan," "modern," and "trustworthy" are obtained.

[1221] Step 4:

[1222] The server accesses the font database and generates a list of suitable font candidates based on the extracted keywords and attributes. The font information is retrieved from the font database, and each font is evaluated using an AI algorithm.

[1223] Step 5:

[1224] The server generates a list of fonts and sends it to the terminal in a ranked format. The fonts are ranked based on the evaluation results, and the list is sent to the terminal.

[1225] Step 6:

[1226] The terminal displays the received font list on the user interface. For example, candidates such as "Font A," "Font B," and "Font C" are presented to the user.

[1227] Step 7:

[1228] In a content distribution service, the font selected by the user is automatically applied based on visibility and cultural suitability. The font selected by the user is automatically reflected in the content design.

[1229] Step 8:

[1230] The user enters feedback about the selected font. For example, the user enters and submits an evaluation such as "I found Font A to be the easiest to read."

[1231] Step 9:

[1232] The server analyzes the received feedback and extracts the characteristics of the selected font and the reasons for its selection.

[1233] Step 10:

[1234] The server uses machine learning models to refine the recommendation algorithm. Based on the collected feedback, it runs a learning process to improve the algorithm's accuracy, which will improve the accuracy of the next font recommendation.

[1235] 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.

[1236] This invention provides an AI-based system that inputs project information from users, analyzes the user's emotional state based on that information using an emotion engine, and recommends appropriate fonts. Furthermore, by improving the recommendation algorithm based on user feedback, the accuracy of the recommendation is continuously improved.

[1237] System configuration

[1238] The system mainly includes the following elements:

[1239] 1. User interface (terminal): An interface for users to input project information and display font recommendation results.

[1240] 2. Server: Analyzes project information, recognizes emotional states through an emotion engine, recommends fonts, and collects and analyzes feedback.

[1241] 3. Font database: A database that stores information about various fonts and is used by the recommendation algorithm.

[1242] 4. Emotion engine: An engine that analyzes the user's emotional state from their input and reactions and reflects this in font selection.

[1243] Program processing explanation

[1244] The program processing of this system will be specifically explained below.

[1245] 1. User information input phase

[1246] Device: The user uses the device to enter project information, such as "Target region: Japan" and "Emotional tone: Modern and trustworthy," into an input form.

[1247] Terminal: The entered project information is converted into an appropriate format and sent to the server.

[1248] 2. Data Receipt and Analysis Phase

[1249] Server: The server receives project information sent from the device, temporarily stores the received information, and prepares it for analysis.

[1250] Server: Analyzes the received project information and extracts keywords and attributes such as target region and emotional tone. For example, it identifies keywords such as "Japan," "modern," and "trustworthy."

[1251] 3. Emotional state analysis phase

[1252] Server: Activates the emotion engine and analyzes the user's emotional state based on the project information and their reactions to the project. For example, the server identifies emotional states such as "relief" or "vigor" based on the user's input and past selection history.

[1253] 4. Candidate selection phase from font database

[1254] Server: Based on the emotional state provided by the emotion engine and the extracted keywords and attributes, the server accesses the font database and searches for suitable font candidates.

[1255] Server: Based on the search results, an AI algorithm is used to evaluate each font and generate a ranked list of candidate fonts.

[1256] 5. Recommended font display phase

[1257] Server: Sends the generated list of font candidates to the device. The list includes the font names and their respective evaluation scores.

[1258] Terminal: The terminal displays the received font list on the user interface. For example, candidates such as "Font A," "Font B," and "Font C" are presented.

[1259] 6. User selection and feedback gathering phase

[1260] User: Select the best font from the list of fonts presented. After selecting, the user can also provide feedback and justify their choice.

[1261] Terminal: Sends the user's selection information and feedback to the server. The feedback may include specific reasons for the selection, such as "I felt that font A was the easiest to read."

[1262] 7. Feedback Receiving and Analysis Phase

[1263] Server: Receives the selection information and feedback sent. Analyzes the received feedback and extracts the characteristics of the selected font and the reasons for its selection.

[1264] 8. Algorithm improvement phase using machine learning

[1265] Server: Using the analysis results, we perform machine learning to improve the font recommendation algorithm. We add new data to the learning model to make the algorithm more accurate for the next font recommendation.

[1266] Specific examples

[1267] Example 1: Website design for the Japanese market

[1268] 1. User information input phase

[1269] Device: User inputs "E-commerce site design for the Japanese market", "Target region: Japan", "Emotional tone: modern and trustworthy".

[1270] 2. Data Receipt and Analysis Phase

[1271] Server: The server extracts keywords such as "Japan," "modern," and "trustworthy."

[1272] 3. Emotional state analysis phase

[1273] Server: Using the emotion engine, determine whether the user has a "sense of security" based on their input and past selection history.

[1274] 4. Candidate selection phase from font database

[1275] Server: The server generates candidates such as "Font A," "Font B," and "Font C" from the font database and creates a ranking.

[1276] 5. Recommended font display phase

[1277] Terminal: The terminal displays "Font A", "Font B", and "Font C" to the user.

[1278] 6. User selection and feedback gathering phase

[1279] User: The user selects "Font A" and types, "I found it to be more readable than the other fonts."

[1280] 7. Feedback Receiving and Analysis Phase

[1281] Server: The server analyzes that "Font A was chosen because it is highly readable."

[1282] 8. Algorithm improvement phase using machine learning

[1283] Server: The server uses this feedback to improve its algorithm to prioritize "readability" the next time it recommends a font.

[1284] In this manner, the present invention can take into account the user's emotional state and efficiently recommend fonts that are appropriate for different cultures and regions, supporting creative projects.

[1285] The processing flow will be explained below.

[1286] Step 1:

[1287] User: Enters project information using a device. For example, enters "Target region: Japan" and "Emotional tone: Modern and trustworthy" into an input form.

[1288] Step 2:

[1289] Terminal: Converts the entered project information into the appropriate format and sends it to the server.

[1290] Step 3:

[1291] Server: Receives the project information sent, temporarily stores the received information, and prepares it for analysis.

[1292] Step 4:

[1293] Server: Analyzes the received project information and extracts keywords and attributes such as target region and emotional tone. For example, it identifies keywords such as "Japan," "modern," and "trustworthy."

[1294] Step 5:

[1295] Server: Activates the emotion engine and analyzes the user's emotional state based on the project information and their reactions to the project. For example, it identifies emotional states such as "relief" and "vigor."

[1296] Step 6:

[1297] Server: Searches for suitable font candidates from the font database based on the extracted keywords and attributes and the emotional state analyzed by the emotion engine.

[1298] Step 7:

[1299] Server: Based on the search results, an AI algorithm is used to evaluate each font and generate a ranked list of candidate fonts.

[1300] Step 8:

[1301] Server: Sends the generated list of font candidates to the device. The list includes the font names and their respective evaluation scores.

[1302] Step 9:

[1303] Terminal: The received font candidate list is displayed on the user interface. For example, candidates such as "Font A," "Font B," and "Font C" are presented.

[1304] Step 10:

[1305] User: Selects the best font from a list of fonts presented, and when selected, optionally provides feedback and justification for the selection.

[1306] Step 11:

[1307] Terminal: Sends the user's selection information and feedback to the server. The feedback may include specific reasons for the selection, such as "I felt that font A was the easiest to read."

[1308] Step 12:

[1309] Server: Receives the selection information and feedback sent. Analyzes the received feedback and extracts the characteristics of the selected font and the reasons for its selection.

[1310] Step 13:

[1311] Server: Using the analysis results, we perform machine learning to improve the font recommendation algorithm. We add new data to the learning model to make the algorithm more accurate for the next font recommendation.

[1312] Step 14:

[1313] Server: Improved algorithms will be applied to the system, allowing it to more accurately recommend the best fonts the next time a user enters project information.

[1314] Example 2

[1315] 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."

[1316] Conventional font recommendation systems have difficulty recommending appropriate fonts because they do not sufficiently consider the user's emotional state or past selection history. Furthermore, they lack a mechanism for utilizing user feedback to improve the accuracy of the algorithm, making it difficult to continuously improve recommendation accuracy.

[1317] 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.

[1318] In this invention, the server includes means for receiving project information entered by a user, means for analyzing the received project information to extract keywords and attributes, means for selecting appropriate candidates from a database based on the extracted keywords and attributes, means for analyzing the user's emotional state based on the user's project information and past selection history using an emotion engine, means for presenting the selected candidates to the user in a ranked format, means for receiving feedback regarding the candidates selected by the user, means for improving a recommendation algorithm based on the received feedback, means for displaying the generated candidate list on a user interface, and means for applying a machine learning model using the received feedback. This enables appropriate font recommendations that take the user's emotional state into consideration and allows the recommendation algorithm to be continuously improved by utilizing user feedback.

[1319] "Project information" refers to information related to a task or project entered by a user.

[1320] "Keywords" are important words or phrases extracted from project information.

[1321] "Attributes" refer to characteristics or properties associated with keywords.

[1322] A "database" is a data store that stores information about various candidates (eg, fonts).

[1323] An "emotion engine" is a device or software that analyzes a user's emotional state based on their project information and past selection history.

[1324] The "ranking format" is a format in which the selected candidates are sorted based on their evaluation scores or rankings.

[1325] "Feedback" refers to the opinions and ratings provided by a user regarding a selected candidate.

[1326] A "recommendation algorithm" is a calculation method or procedure for recommending suitable candidates to a user.

[1327] A "machine learning model" is a model for improving and optimizing algorithms based on data.

[1328] "User interface" refers to the interface, such as input and output devices and screen displays, through which a user interacts with a system.

[1329] This invention provides an AI-based system that inputs project information, analyzes the user's emotional state using an emotion engine based on that information, and recommends appropriate fonts. Furthermore, by improving the recommendation algorithm based on user feedback, recommendation accuracy can be continuously improved.

[1330] System configuration

[1331] The system mainly includes the following elements:

[1332] 1. User interface (terminal): An interface for users to input project information and display font recommendation results.

[1333] 2. Server: This is the device that analyzes project information, recognizes emotional states using the emotion engine, recommends fonts, and collects and analyzes feedback.

[1334] 3. Font database: A database that stores information about various fonts and is used by the recommendation algorithm.

[1335] 4. Emotion engine: This engine analyzes the user's emotional state from their input and reactions and reflects this in font selection.

[1336] Program processing explanation

[1337] 1. User information input phase

[1338] Device: The user uses the device to enter project information, such as "Target region: Japan" and "Emotional tone: Modern and trustworthy," into an input form.

[1339] Terminal: The entered project information is converted into an appropriate format and sent to the server.

[1340] 2. Data Receipt and Analysis Phase

[1341] Server: The server receives the project information sent from the terminal and temporarily stores the received data in memory or a database.

[1342] Server: Analyzes project information using natural language processing algorithms to extract keywords and attributes such as target region and emotional tone. For example, identify keywords such as "Japan," "modern," and "trustworthy."

[1343] 3. Emotional state analysis phase

[1344] Server: Launches an emotion engine (e.g., a general commercial emotion analysis engine) and analyzes the user's emotional state based on the user's project information and past selection history. For example, it analyzes emotions such as "relief" and "liveliness."

[1345] Server: Temporarily stores the analysis results and uses them in the next phase.

[1346] 4. Candidate selection phase from font database

[1347] Server: Accesses the font database based on the emotional state provided by the emotion engine and the extracted keywords and attributes.

[1348] Server: Runs a database query to find suitable font candidates, such as "Font A" that gives a "comfortable feeling" and "Font B" that has a modern design.

[1349] Server: Evaluates each font using an AI algorithm (e.g., random forest) and generates a ranked list of candidate fonts.

[1350] 5. Recommended font display phase

[1351] Server: Sends the generated list of font candidates to the terminal, including the font names and their respective evaluation scores.

[1352] Terminal: The terminal displays the received font list on the user interface. For example, candidates such as "Font A," "Font B," and "Font C" are presented.

[1353] 6. User selection and feedback gathering phase

[1354] User: Select the most suitable font from the presented font list. For example, select "Font A".

[1355] User: After completing the selection, enter the reason for the selection and feedback. For example, enter a specific reason such as "I felt that font A was the easiest to read."

[1356] Terminal: Sends user selection information and feedback to the server.

[1357] 7. Feedback Receiving and Analysis Phase

[1358] Server: Receives the submitted selection information and feedback and stores it in memory or a database for analysis.

[1359] Server: The feedback is analyzed using natural language processing algorithms to extract the characteristics of the selected font and the reasons for its selection.

[1360] 8. Algorithm improvement phase using machine learning

[1361] Server: Uses the analysis results to perform machine learning to improve the font recommendation algorithm, for example, by adding new data to the learning model and retraining the algorithm's parameters.

[1362] Server: Check that the algorithm has improved and prepare the new model for the next font recommendation.

[1363] Specific examples

[1364] Example 1: Website design for the Japanese market

[1365] 1. User information input phase

[1366] Device: User inputs "E-commerce site design for the Japanese market", "Target region: Japan", "Emotional tone: modern and trustworthy".

[1367] Terminal: The terminal sends the input information to the server.

[1368] 2. Data Receipt and Analysis Phase

[1369] Server: The server extracts keywords such as "Japan," "modern," and "trustworthy" and temporarily stores them.

[1370] 3. Emotional state analysis phase

[1371] Server: Using the emotion engine, determine whether the user has a sense of security based on their input and past selection history.

[1372] 4. Candidate selection phase from font database

[1373] Server: The server generates candidates such as "Font A," "Font B," and "Font C" from the font database and creates a ranking.

[1374] 5. Recommended font display phase

[1375] Terminal: The terminal displays "Font A", "Font B", and "Font C" to the user.

[1376] 6. User selection and feedback gathering phase

[1377] User: The user selects "Font A" and types, "I found it to be more readable than the other fonts."

[1378] Terminal: Sends user selection information and feedback to the server.

[1379] 7. Feedback Receiving and Analysis Phase

[1380] Server: The server analyzes that "Font A was chosen because it is highly readable."

[1381] 8. Algorithm improvement phase using machine learning

[1382] Server: The server uses this feedback to improve its algorithm to prioritize "readability" the next time it recommends a font.

[1383] Example input to a generative AI model

[1384] I'd like to design a modern and trustworthy e-commerce website for the Japanese market. The target geography is Japan, and the emotional tone should ideally be modern and trustworthy. Please recommend a suitable font.

[1385] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1386] Step 1:

[1387] Entering user information

[1388] User: Enters project information into the input form provided on the device.

[1389] Specific actions: For example, enter information such as "Target region: Japan" and "Emotional tone: Modern and trustworthy."

[1390] Input: Project information entered by the user.

[1391] Output: Information entered into the terminal is converted into a data format for transmission from the terminal to the server.

[1392] Step 2:

[1393] Receiving data

[1394] Server: Receives project information sent from the device.

[1395] Specific operation: Temporarily store received data in memory or a database.

[1396] Input: Project information sent from the device.

[1397] Output: The received data converted into a parsable data format.

[1398] Step 3:

[1399] Project Information Analysis

[1400] Server: Analyzes project information using natural language processing algorithms.

[1401] What it does: Uses a natural language processing library (e.g., spaCy) to extract keywords and attributes such as "target region: Japan" and "emotional tone: modern and trustworthy."

[1402] Input: Received project information.

[1403] Output: Extracted keywords and attributes (e.g., "Japan," "modern," "trustworthy").

[1404] Step 4:

[1405] Emotional state analysis

[1406] Server: Launches the emotion engine and analyzes the user's emotional state based on project information and past selection history.

[1407] Specific behavior: Analyze emotions such as "relief" and "liveliness" using a commercial sentiment analysis engine (e.g., IBM Watson NLU).

[1408] Input: Parsed keywords and attributes, and the user's past selection history.

[1409] Output: Emotional state as a result of the analysis (e.g., "Relaxed," "Energetic").

[1410] Step 5:

[1411] Search for font suggestions

[1412] Server: Accesses the font database based on the emotional state provided by the emotion engine and the extracted keywords and attributes.

[1413] What it does: Runs a database query to find, for example, "Font A" that gives a "comfortable feeling" and "Font B" that has a modern design.

[1414] Input: Emotional state, extracted keywords and attributes.

[1415] Output: A list of searched font candidates.

[1416] Step 6:

[1417] Rating and ranking of font candidates

[1418] Server: Based on the search results, an AI algorithm is used to evaluate each font and generate a ranked list of font candidates.

[1419] What it does: It uses a random forest algorithm to calculate the font's rating score and then creates a ranking based on the rating score.

[1420] Input: Font candidate list.

[1421] Output: A ranked list of fonts with rating scores.

[1422] Step 7:

[1423] Displaying font recommendation results

[1424] Server: Sends the generated font candidate list to the terminal.

[1425] Specific behavior: Sends data to the device including font names and their respective rating scores.

[1426] Input: Ranked font list.

[1427] Output: Font candidate list sent to the terminal.

[1428] Step 8:

[1429] User selection and feedback input

[1430] User: Select the best font from the list of fonts presented and provide feedback and reasons for their choice.

[1431] Specific action: For example, the user selects "Font A" and enters "I felt it had higher readability than other fonts."

[1432] Input: User font selection and feedback.

[1433] Output: Selection information and feedback are sent from the device to the server.

[1434] Step 9:

[1435] Receiving and analyzing feedback

[1436] Server: Receives the submitted selection information and feedback and temporarily stores it for analysis.

[1437] What it does: It uses natural language processing algorithms to analyze the feedback and extract the characteristics of the selected font and the reasons for its selection.

[1438] Input: User selection information and feedback.

[1439] Output: Extracted selection reasons and font features.

[1440] Step 10:

[1441] Algorithm Improvements

[1442] Server: Uses the analysis results to perform machine learning to improve the font recommendation algorithm.

[1443] What it does: Adds new data to the learning model and retrains the algorithm's parameters.

[1444] Input: Feedback analysis results.

[1445] Output: An improved recommendation algorithm.

[1446] (Application example 2)

[1447] 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."

[1448] Current advertising design creation systems have difficulty recommending fonts that take into account the user's emotional state when selecting an appropriate font based on project information. Another problem is that font selection takes time, making it difficult to achieve an effective design. With conventional technologies, users often select fonts based on intuition or experience, which can result in suboptimal optimization of the advertisement's visual and emotional impact.

[1449] 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.

[1450] In this invention, the server includes: means for receiving project information input by a user; means for analyzing the received project information and extracting keywords and attributes; means for selecting appropriate candidates from a font database based on the extracted keywords and attributes; means for presenting the selected candidates to the user in a ranked format; means for receiving feedback on the font selected by the user; means for improving a recommendation algorithm based on the received feedback; means for including a smartphone application that inputs advertising design project information and recommends optimal fonts; and means for reflecting the user's emotional state in font selection using an emotion analysis engine that analyzes the user's emotional state. This makes it possible to recommend optimal fonts in real time taking into account the user's emotional state, thereby maximizing the visual and emotional impact of advertisements.

[1451] "Project Information" is detailed information a user provides about an advertising design or other design project, including target market, emotional tone, design objectives, and the like.

[1452] A "font database" is a database that stores information about various fonts, including data such as font names, styles, and uses.

[1453] The "ranking format" is a format in which multiple candidates are ranked based on specific criteria and presented, allowing the user to easily make the optimal selection.

[1454] "Feedback" is information such as opinions, ratings, and reasons for a particular font selection that a user provides, and is used to improve the recommendation algorithm next time.

[1455] An "emotion analysis engine" is an engine that analyzes a user's emotional state from their input information and reactions, and supports specific actions and choices based on the results.

[1456] A "smartphone application" is software that runs on a smartphone and allows users to input project information and receive recommendations for optimal fonts.

[1457] "Recommendation algorithm improvement" is the process of improving the accuracy and efficiency of the algorithm based on feedback received from users.

[1458] "Advertising design" is the process of creating the visual representation of an advertising campaign, selecting elements such as fonts, colors, and images to create the optimal advertisement.

[1459] "Emotional state" refers to the psychological or emotional state analyzed based on the user's input and reactions, and includes emotions such as a sense of security and trust.

[1460] MODE FOR CARRYING OUT THE INVENTION

[1461] This invention provides a system that allows users to input project information, such as advertising design, and then uses an emotion analysis engine to analyze the user's emotional state based on that information and recommend appropriate fonts. Furthermore, the recommendation algorithm is improved based on user feedback, continuously improving recommendation accuracy. This system mainly consists of the following components:

[1462] System Components

[1463] 1. User Interface (Smartphone Application): This is an interface where users can input project information for advertising design and view font recommendations. Users input project information such as target market, emotional tone, and design objectives.

[1464] 2. Server: Receives and analyzes project information, uses an emotion analysis engine to recognize the user's emotional state, recommends fonts, collects and analyzes feedback, and accesses the font database to select the appropriate font.

[1465] 3. Font Database: A database that stores information about various fonts, including font names, styles, and uses. The server uses a recommendation algorithm to select an appropriate font from the database.

[1466] 4. Sentiment Analysis Engine: This engine analyzes the user's emotional state from their input information and reactions, and can use non-specific emotion analysis engines such as IBM Watson Tone Analyzer. This engine identifies the user's emotional state from project information and past selection history and reflects this in the font selection.

[1467] System Operation

[1468] The server first receives advertising design project information entered by the user through a smartphone application, including the target market (e.g., Japan), emotional tone (e.g., modern and trustworthy), and design purpose (e.g., display advertising).

[1469] The server then analyzes the received project information and extracts keywords and attributes such as target market, emotional tone, and design purpose. It uses a sentiment analysis engine to analyze the user's emotional state (e.g., sense of security) and selects an appropriate font from a font database based on the results.

[1470] The selected fonts are presented to the user in a ranked format, and the user selects the most suitable font from the recommended fonts. After completing the selection, the user enters the reason for their selection and feedback, which is then sent to the server. For example, the user could provide feedback such as, "I felt that font A was easier to read than the other fonts."

[1471] The server analyzes the received feedback and extracts the characteristics of the selected font and the reasons for its selection. This is then used to apply a machine learning model to improve the accuracy of the recommendation algorithm. This adds new data to the learning model, improving the algorithm's accuracy for the next font recommendation.

[1472] Specific examples

[1473] For example, if a user inputs the project information "Target region: Japan," "Emotional tone: Modern and trustworthy," and "Ad type: Display ads," the system will extract keywords such as "Japan," "modern," and "trustworthy," and use the sentiment analysis engine to identify the emotional state as "reassuring." As a result, it will recommend fonts such as "Font A," "Font B," and "Font C," and continuously refine the algorithm based on user selection and feedback.

[1474] An example of a prompt is as follows:

[1475] "Please recommend a font that would be ideal for advertising designs that have a modern and trustworthy feel."

[1476] "The target region is Japan, and readability is important."

[1477] In this manner, the invention takes into account the user's emotional state and can efficiently recommend optimal fonts suited to different cultures and regions, thereby supporting creative design creation.

[1478] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1479] Step 1:

[1480] Users operate a smartphone application to input project information for advertising design, including the target market (e.g., "Japan"), emotional tone (e.g., "modern and trustworthy"), and design purpose (e.g., "display advertising"). This data is converted into an appropriate format by the application and sent to the server.

[1481] Inputs: Target market, emotional tone, design objectives

[1482] Output: Data converted into the appropriate format

[1483] Specific operation: A form is displayed on the smartphone screen, the user enters project information, the input is converted to JSON format and sent to the server.

[1484] Step 2:

[1485] The server receives project information sent from the smartphone application, temporarily stores the received information, and prepares it for the next analysis.

[1486] Input: Data converted into the appropriate format

[1487] Output: Temporarily saved project information

[1488] Specific operation: The server receives an HTTP request and temporarily stores the received data in a database.

[1489] Step 3:

[1490] The server analyzes the received project information and extracts keywords and attributes such as target market, emotional tone, design objectives, etc. Specifically, it uses text analysis algorithms to identify keywords.

[1491] Input: Temporarily saved project information

[1492] Output: Extracted keywords and attributes

[1493] What it does: The server uses a natural language processing library (e.g., NLTK or spaCy) to parse the project information text and extract important keywords.

[1494] Step 4:

[1495] The server runs an emotion analysis engine, such as IBM Watson Tone Analyzer, to analyze the user's emotional state based on their input and past selection history.

[1496] Input: Extracted keywords and attributes

[1497] Output: User's emotional state

[1498] Specific operation: Project information is sent to the emotion analysis engine, and the engine returns the emotional state as the analysis result.

[1499] Step 5:

[1500] The server accesses the font database and searches for suitable font candidates based on the emotional state provided by the emotion analysis engine and the extracted keywords and attributes. The searched fonts are then evaluated and a candidate list is generated in a ranked format.

[1501] Input: User's emotional state, extracted keywords and attributes

[1502] Output: Ranked list of font candidates

[1503] Specific operation: Runs an SQL query against the font database to extract fonts that match the search criteria, assigns a score to each font, and generates a ranking.

[1504] Step 6:

[1505] The server sends the generated font candidate list to the smartphone application, which displays the received font list on its user interface.

[1506] Input: A ranked list of font candidates

[1507] Output: A list of font candidates displayed in the user interface

[1508] Specific operation: The server sends an HTTP response, the application receives the response and displays the fonts on the screen in list format.

[1509] Step 7:

[1510] The user selects the most suitable font from the presented font list and inputs the reason for their selection and feedback, which is then sent to the server via the smartphone application.

[1511] Input: User font selection and feedback

[1512] Output: Feedback data converted into the appropriate format

[1513] Specific behavior: The user selects a font from a list in the application, fills out an input form explaining the reason for selecting it, and submits it to the server.

[1514] Step 8:

[1515] The server receives and analyzes the selection information and feedback, extracting the characteristics of the selected font and the reasons for its selection.

[1516] Input: Feedback data converted into the appropriate format

[1517] Output: The characteristics of the selected font and the reason for its selection

[1518] What it does: The server stores the feedback data in a database and uses text analysis algorithms to extract important features and reasons.

[1519] Step 9:

[1520] The server uses the analysis results to perform machine learning to improve the recommendation algorithm, adding new data to the learning model and improving the algorithm for the next font recommendation.

[1521] Input: The characteristics of the selected font and the reason for its selection

[1522] Output: Improved recommendation algorithm

[1523] What it does: Uses machine learning libraries (e.g., scikit-learn and TensorFlow) to train models based on feedback data and improve recommendation algorithms.

[1524] 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.

[1525] 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.

[1526] 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.

[1527] [Fourth embodiment]

[1528] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1529] 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.

[1530] 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).

[1531] 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.

[1532] 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.

[1533] 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).

[1534] 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.

[1535] 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.

[1536] 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.

[1537] 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.

[1538] 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.

[1539] 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.

[1540] 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."

[1541] The present invention provides an AI-based system that recommends appropriate fonts based on user input project information. The system selects fonts appropriate for a specific region or culture and continuously improves the recommendation accuracy based on user feedback.

[1542] System configuration

[1543] The system mainly includes the following elements:

[1544] 1. User interface (terminal): An interface for users to input project information and display font recommendation results.

[1545] 2. Server: Analyzes project information, recommends fonts, and collects and analyzes feedback.

[1546] 3. Font database: A database that stores information about various fonts and is used by the recommendation algorithm.

[1547] Program processing explanation

[1548] 1. User information input phase

[1549] Device: The user uses the device to input project information, such as "Target region: Japan" and "Emotional tone: Modern and trustworthy."

[1550] Terminal: The entered information is converted into an appropriate format and sent to the server.

[1551] 2. Data Receipt and Analysis Phase

[1552] Server: The server receives the project information sent from the terminal.

[1553] Server: Analyzes the received data and extracts keywords and attributes related to the project's purpose, cultural background, and emotional tone. For example, it analyzes keywords such as "Japan," "modern," and "trustworthy."

[1554] 3. Candidate selection phase from font database

[1555] Server: The server accesses the font database and generates a list of suitable fonts based on the extracted keywords and attributes.

[1556] Server: An AI algorithm is applied to the generated font list to evaluate the characteristics of each font and create a ranking.

[1557] 4. Recommended font display phase

[1558] Server: Sends a list of fonts in ranking format to the device.

[1559] Terminal: The terminal displays the received font list on the user interface, for example presenting candidates such as "Font A," "Font B," and "Font C."

[1560] 5. User selection and feedback gathering phase

[1561] User: The user selects the most suitable font from the displayed font list.

[1562] User: After completing the selection, the user may enter a reason for their selection or feedback. For example, they may send feedback such as "I found font A to be the easiest to read."

[1563] 6. Feedback Receiving and Analysis Phase

[1564] Server: The server receives the selection information and feedback sent by the user.

[1565] Server: Analyzes the received feedback and extracts the characteristics of the selected font and the reasons for its selection.

[1566] 7. Algorithm improvement phase using machine learning

[1567] Server: The server uses the analysis results to perform machine learning to improve the font recommendation algorithm.

[1568] Server: Adds new data to the learning model to improve the algorithm's accuracy for the next recommendation.

[1569] Specific examples

[1570] Example 1: Website design for the Japanese market

[1571] 1. User information input phase

[1572] Device: User inputs "E-commerce site design for the Japanese market", "Target region: Japan", "Emotional tone: modern and trustworthy".

[1573] 2. Data Receipt and Analysis Phase

[1574] Server: The server extracts keywords such as "Japan," "modern," and "trustworthy."

[1575] 3. Candidate selection phase from font database

[1576] Server: The server generates candidates such as "Font A," "Font B," and "Font C" from the font database and creates a ranking.

[1577] 4. Recommended font display phase

[1578] Terminal: The terminal displays "Font A", "Font B", and "Font C" to the user.

[1579] 5. User selection and feedback gathering phase

[1580] User: The user selects "Font A" and types, "I found it to be more readable than the other fonts."

[1581] 6. Feedback Receiving and Analysis Phase

[1582] Server: The server analyzes that "Font A was chosen because it is highly readable."

[1583] 7. Algorithm improvement phase using machine learning

[1584] Server: The server uses this feedback to improve its algorithm to prioritize "readability" the next time it recommends a font.

[1585] In this manner, the present invention can efficiently recommend fonts that are appropriate for different cultures and regions, and support creative projects.

[1586] The processing flow will be explained below.

[1587] Step 1:

[1588] User: Enters project information via a terminal. For example, the user enters information such as "Target region: Japan" and "Emotional tone: Modern and trustworthy" into an input form.

[1589] Step 2:

[1590] Terminal: Converts the entered project information into the appropriate format and sends it to the server.

[1591] Step 3:

[1592] Server: Receives the project information sent, temporarily stores the received information, and prepares it for analysis.

[1593] Step 4:

[1594] Server: Analyzes the received project information and extracts keywords and attributes such as target region and emotional tone. For example, it identifies keywords such as "Japan," "modern," and "trustworthy."

[1595] Step 5:

[1596] Server: Based on the extracted keywords and attributes, the server accesses a font database to find suitable font candidates. The database contains metadata about each font's cultural background and usage.

[1597] Step 6:

[1598] Server: Based on the search results, an AI algorithm is used to evaluate each font and generate a ranked list of candidate fonts.

[1599] Step 7:

[1600] Server: Sends the generated list of font candidates to the device. The list includes the font names and their respective evaluation scores.

[1601] Step 8:

[1602] Terminal: The received font candidate list is displayed on the user interface. For example, candidates such as "Font A," "Font B," and "Font C" are presented.

[1603] Step 9:

[1604] User: Select the best font from the list of fonts presented. After selecting, the user can also provide feedback and justify their choice.

[1605] Step 10:

[1606] Terminal: Sends the user's selection information and feedback to the server. The feedback may include specific reasons for the selection, such as "I felt that font A was the easiest to read."

[1607] Step 11:

[1608] Server: Receives the selection information and feedback sent. Analyzes the received feedback and extracts the characteristics of the selected font and the reasons for its selection.

[1609] Step 12:

[1610] Server: Using the analysis results, we perform machine learning to improve the font recommendation algorithm. We add new data to the learning model to make the algorithm more accurate for the next font recommendation.

[1611] Step 13:

[1612] Server: Improved algorithms will be applied to the system, allowing it to more accurately recommend the best fonts the next time a user enters project information.

[1613] Example 1

[1614] 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."

[1615] Conventional font recommendation systems have the problem of being unable to fully analyze user input information, resulting in low recommendation accuracy. Furthermore, the lack of a process for utilizing user feedback to improve the recommendation algorithm limits the system's learning ability. This makes it difficult to recommend fonts that are appropriate for different cultures and regions.

[1616] 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.

[1617] In this invention, the server includes means for receiving project information entered by a user, means for analyzing the received project information and extracting keywords and attributes, means for selecting appropriate candidates from a database based on the extracted keywords and attributes, means for presenting the selected candidates to the user in a ranked format, means for receiving feedback on elements selected by the user, means for improving a recommendation algorithm based on the received feedback, means for parsing the extracted keywords and attributes and analyzing them using natural language processing technology, and means for generating a candidate list using a machine learning model, evaluating the characteristics of each candidate, and performing scoring and ranking. This enables the server to accurately recommend the font best suited to the user's project.

[1618] "User" refers to an individual or organization that utilizes the System to input project information and receive font recommendations.

[1619] "Project Information" refers to information entered into the system by a user regarding target geography, emotional tone, design objectives, etc.

[1620] "Analysis" refers to the process of extracting specific keywords and attributes from received project information and using natural language processing or other data processing techniques to make sense of that information.

[1621] "Keywords and attributes" refers to characteristic words and phrases extracted from project information, such as target region, emotional tone, and design purpose.

[1622] The "database" refers to a storage system that stores various fonts and information about them, and is a collection of data used by the recommendation algorithm.

[1623] "Candidate List" refers to a collection of fonts selected from a database that are best suited to the project information.

[1624] "Ranking format" refers to providing multiple candidate fonts in a prioritized list format based on their evaluation scores.

[1625] "Feedback" refers to information such as impressions, opinions, and ratings regarding the font selected by the user.

[1626] "Recommendation algorithm" refers to a computational method or program for selecting the most appropriate font based on project information and user feedback.

[1627] "Natural language processing technology" refers to algorithms and methods that allow computers to understand, analyze, and generate human language.

[1628] A "machine learning model" refers to an algorithm or system that can learn from large amounts of data and perform predictions or classifications for certain tasks.

[1629] The present invention is an AI-based system that recommends appropriate fonts based on project information entered by the user. The system selects fonts appropriate for a specific region or culture and continuously improves the recommendation accuracy based on user feedback. The following describes specific embodiments of the present invention.

[1630] System configuration

[1631] The system mainly includes the following elements:

[1632] 1. User interface (terminal): This is the interface where the user inputs project information and displays font recommendation results.

[1633] 2. Server: Analyzes project information, recommends fonts, and collects and analyzes feedback.

[1634] 3. Database: A database containing information about various fonts, which is used in the recommendation algorithm.

[1635] Program processing overview

[1636] The system operates in the following steps:

[1637] 1. Enter your user information

[1638] The user uses the device to input project information, such as "Target region: Japan" and "Emotional tone: Modern and trustworthy." The device collects this information and sends it to the server as JSON-formatted data.

[1639] 2. Receipt and Analysis

[1640] The server receives the HTTP request and parses the JSON data sent from the device. It then analyzes the received data and extracts keywords and attributes such as the project's purpose, cultural background, and emotional tone. This analysis is performed using natural language processing (NLP) techniques.

[1641] 3. Selecting candidates from the font database

[1642] The server executes a database query to generate a list of suitable font candidates based on the extracted keywords and attributes, and then applies a machine learning model to the list to evaluate the characteristics of each font and perform scoring and ranking.

[1643] 4. Display recommended fonts

[1644] The server sends the ranked font list to the terminal and displays it on the user interface, for example, presenting information such as "Font A," "Font B," and "Font C."

[1645] 5. Feedback Collection

[1646] The user selects the desired font from the displayed font list. After selecting, the reason for the selection and feedback are entered through the terminal, which is converted into JSON format and sent to the server.

[1647] 6. Feedback Analysis

[1648] The server receives the feedback data and stores it in a database. It analyzes the received feedback and quantifies and structures the characteristics of the selected font and the reasons for its selection. This analysis also uses natural language processing technology.

[1649] 7. Algorithm Improvement

[1650] The server uses the analysis results to retrain the machine learning model and improve the font recommendation algorithm, thereby improving the accuracy of the algorithm for the next recommendation.

[1651] Specific examples

[1652] Example 1: Website design for the Japanese market

[1653] Enter your user information:

[1654] The user enters into the interface: "E-commerce site design for the Japanese market," "Target region: Japan," and "Emotional tone: modern and trustworthy."

[1655] Receiving and analyzing data:

[1656] The server extracts keywords such as "Japan," "modern," and "trustworthy."

[1657] Candidate selection from font database:

[1658] The server generates candidates such as "Font A," "Font B," and "Font C" from the database and creates a ranking.

[1659] Show recommended fonts:

[1660] The terminal will display "Font A," "Font B," and "Font C" to the user.

[1661] User Choices and Feedback Collection:

[1662] The user selects "Font A" and enters feedback that "I felt it was easier to read than the other fonts."

[1663] Receiving and analyzing feedback:

[1664] The server analyzes that "Font A was chosen because it is highly readable."

[1665] Machine learning algorithm improvement:

[1666] The server uses this feedback to improve its algorithm to prioritize "readability" the next time it recommends a font.

[1667] In this manner, the present invention can efficiently recommend fonts that are appropriate for different cultures and regions, and support creative projects.

[1668] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1669] Step 1:

[1670] Entering user information

[1671] User: The user uses the terminal interface to input project information, for example, "Target region: Japan" and "Emotional tone: Modern and trustworthy."

[1672] Input: Project information (target region, emotional tone, design objectives, etc.)

[1673] Terminal: The terminal collects input information and stores it in JSON format.

[1674] (Application example 1)

[1675] 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."

[1676] Content distribution services face the challenge of making it difficult for users to easily find the optimal font that matches a specific region, culture, or emotional tone. Additionally, when designing content while taking legibility and cultural compatibility into consideration, selecting the appropriate font from the vast number of available fonts can be time-consuming.

[1677] 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.

[1678] In this invention, the server includes means for receiving project information entered by a user, means for analyzing the received project information and extracting keywords and attributes, means for selecting appropriate candidates from a font database based on the extracted keywords and attributes, means for presenting the selected candidates to the user in a ranked format, means for automatically applying a font selected by the user in a content distribution service based on legibility and cultural suitability, means for receiving feedback regarding the font selected by the user, and means for improving a recommendation algorithm based on the received feedback. This allows users to quickly find fonts suitable for the purpose of their project and enables content design with improved legibility and cultural suitability.

[1679] "Project information" refers to specific requirements and goals, such as target area, emotional tone, and purpose, entered by the user.

[1680] "Keywords and attributes" refer to features such as specific local area names, cultural backgrounds, and emotional tones extracted from project information.

[1681] A "font database" is a database that stores information about various fonts and is a source of information for selecting appropriate fonts based on specific keywords or attributes.

[1682] The "ranking format" refers to a format in which the results evaluated by a recommendation algorithm are ranked and presented to the user.

[1683] "Viewability" refers to the degree to which a user can easily read content.

[1684] "Cultural suitability" refers to the degree to which a font is suitable for a particular region or cultural context.

[1685] "Feedback" refers to the ratings and opinions that users provide about their selected fonts.

[1686] "Recommendation algorithm" refers to a computational method for selecting the best font based on input project information and feedback.

[1687] "Machine learning model" refers to a computer model that has a learning process to improve the accuracy of its recommendation algorithm based on collected data.

[1688] MODE FOR CARRYING OUT THE INVENTION

[1689] This invention is an AI-based system that recommends appropriate fonts based on project information entered by the user. The system selects fonts that are appropriate for a specific region or culture, and continuously improves the recommendation accuracy based on user feedback.

[1690] System configuration

[1691] The system mainly includes the following elements:

[1692] 1. User interface (terminal): An interface for users to input project information and view font recommendation results.

[1693] 2. Server: Analyzes project information, recommends fonts, and collects and analyzes feedback.

[1694] 3. Font Database: A database that stores information about various fonts and is used by the recommendation algorithm.

[1695] Program processing explanation

[1696] 1. User information input phase:

[1697] The user uses a terminal to input project information, such as "Target region: Japan" and "Emotional tone: Modern and trustworthy." They also input "Blog article design" as a situation for the content distribution service.

[1698] 2. Data reception and analysis phase:

[1699] The server receives project information sent from the device, analyzes the received data, and extracts keywords and attributes related to the project's purpose, cultural background, and emotional tone.

[1700] 3. Font database candidate selection phase:

[1701] The server accesses the font database and generates a list of suitable fonts based on the extracted keywords and attributes. An AI algorithm is then applied to the generated font list to evaluate the characteristics of each font and create a ranking.

[1702] 4. Recommended font display phase:

[1703] The server sends a list of fonts in a ranking format to the terminal, which then displays the received font list on the user interface.

[1704] 5. Font auto-application phase:

[1705] The font selected by the user in the content distribution service is automatically applied based on visibility and cultural compatibility, so that the font selected by the user is automatically reflected in accordance with the content design.

[1706] 6. User selection and feedback gathering phase:

[1707] The user selects the most suitable font from the displayed font list, and after completing the selection, inputs the reason for the selection and feedback.

[1708] 7. Feedback receiving and analysis phase:

[1709] The server receives the selection information and feedback sent by the user, analyzes the received feedback, and extracts the characteristics of the selected font and the reasons for its selection.

[1710] 8. Algorithm improvement phase using machine learning:

[1711] The server uses the analysis results to perform machine learning to improve the font recommendation algorithm, adding new data to the learning model and improving the algorithm's accuracy for the next recommendation.

[1712] Specific examples

[1713] A user who wants to design a blog post for the Japanese market enters "Target region: Japan," "Emotional tone: Modern and trustworthy," and "Content type: Blog post design." In this case, the server extracts keywords such as "Japan," "modern," and "trustworthy," and recommends appropriate fonts. The recommended fonts are then automatically applied to the content design.

[1714] Prompt Sentence Examples

[1715] "I'd like to design a blog post for the Japanese market. The target region is Japan, and the emotional tone should be modern and trustworthy. I'd like you to recommend which font would be best for this."

[1716] In this way, the present invention can efficiently recommend fonts that are appropriate for different cultures and regions, supporting creative projects, and continuously improve its accuracy based on user feedback.

[1717] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1718] Step 1:

[1719] The user enters project information using a device, such as "Target region: Japan," "Emotional tone: Modern and trustworthy," and "Content type: Blog article design." This input information is saved as project information.

[1720] Step 2:

[1721] The device converts the input project information into an appropriate format and sends it to the server. The input information is converted into a data structure such as JSON or XML and sent to the server via the network.

[1722] Step 3:

[1723] The server analyzes the received project information. Specifically, it uses natural language processing technology to extract keywords and attributes such as "target region" and "emotional tone." As a result of this analysis, keywords such as "Japan," "modern," and "trustworthy" are obtained.

[1724] Step 4:

[1725] The server accesses the font database and generates a list of suitable font candidates based on the extracted keywords and attributes. The font information is retrieved from the font database, and each font is evaluated using an AI algorithm.

[1726] Step 5:

[1727] The server generates a list of fonts and sends it to the terminal in a ranked format. The fonts are ranked based on the evaluation results, and the list is sent to the terminal.

[1728] Step 6:

[1729] The terminal displays the received font list on the user interface. For example, candidates such as "Font A," "Font B," and "Font C" are presented to the user.

[1730] Step 7:

[1731] In a content distribution service, the font selected by the user is automatically applied based on visibility and cultural suitability. The font selected by the user is automatically reflected in the content design.

[1732] Step 8:

[1733] The user enters feedback about the selected font. For example, the user enters and submits an evaluation such as "I found Font A to be the easiest to read."

[1734] Step 9:

[1735] The server analyzes the received feedback and extracts the characteristics of the selected font and the reasons for its selection.

[1736] Step 10:

[1737] The server uses machine learning models to refine the recommendation algorithm. Based on the collected feedback, it runs a learning process to improve the algorithm's accuracy, which will improve the accuracy of the next font recommendation.

[1738] 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.

[1739] This invention provides an AI-based system that inputs project information from users, analyzes the user's emotional state based on that information using an emotion engine, and recommends appropriate fonts. Furthermore, by improving the recommendation algorithm based on user feedback, the accuracy of the recommendation is continuously improved.

[1740] System configuration

[1741] The system mainly includes the following elements:

[1742] 1. User interface (terminal): An interface for users to input project information and display font recommendation results.

[1743] 2. Server: Analyzes project information, recognizes emotional states through an emotion engine, recommends fonts, and collects and analyzes feedback.

[1744] 3. Font database: A database that stores information about various fonts and is used by the recommendation algorithm.

[1745] 4. Emotion engine: An engine that analyzes the user's emotional state from their input and reactions and reflects this in font selection.

[1746] Program processing explanation

[1747] The program processing of this system will be specifically explained below.

[1748] 1. User information input phase

[1749] Device: The user uses the device to enter project information, such as "Target region: Japan" and "Emotional tone: Modern and trustworthy," into an input form.

[1750] Terminal: The entered project information is converted into an appropriate format and sent to the server.

[1751] 2. Data Receipt and Analysis Phase

[1752] Server: The server receives project information sent from the device, temporarily stores the received information, and prepares it for analysis.

[1753] Server: Analyzes the received project information and extracts keywords and attributes such as target region and emotional tone. For example, it identifies keywords such as "Japan," "modern," and "trustworthy."

[1754] 3. Emotional state analysis phase

[1755] Server: Activates the emotion engine and analyzes the user's emotional state based on the project information and their reactions to the project. For example, the server identifies emotional states such as "relief" or "vigor" based on the user's input and past selection history.

[1756] 4. Candidate selection phase from font database

[1757] Server: Based on the emotional state provided by the emotion engine and the extracted keywords and attributes, the server accesses the font database and searches for suitable font candidates.

[1758] Server: Based on the search results, an AI algorithm is used to evaluate each font and generate a ranked list of candidate fonts.

[1759] 5. Recommended font display phase

[1760] Server: Sends the generated list of font candidates to the device. The list includes the font names and their respective evaluation scores.

[1761] Terminal: The terminal displays the received font list on the user interface. For example, candidates such as "Font A," "Font B," and "Font C" are presented.

[1762] 6. User selection and feedback gathering phase

[1763] User: Select the best font from the list of fonts presented. After selecting, the user can also provide feedback and justify their choice.

[1764] Terminal: Sends the user's selection information and feedback to the server. The feedback may include specific reasons for the selection, such as "I felt that font A was the easiest to read."

[1765] 7. Feedback Receiving and Analysis Phase

[1766] Server: Receives the selection information and feedback sent. Analyzes the received feedback and extracts the characteristics of the selected font and the reasons for its selection.

[1767] 8. Algorithm improvement phase using machine learning

[1768] Server: Using the analysis results, we perform machine learning to improve the font recommendation algorithm. We add new data to the learning model to make the algorithm more accurate for the next font recommendation.

[1769] Specific examples

[1770] Example 1: Website design for the Japanese market

[1771] 1. User information input phase

[1772] Device: User inputs "E-commerce site design for the Japanese market", "Target region: Japan", "Emotional tone: modern and trustworthy".

[1773] 2. Data Receipt and Analysis Phase

[1774] Server: The server extracts keywords such as "Japan," "modern," and "trustworthy."

[1775] 3. Emotional state analysis phase

[1776] Server: Using the emotion engine, determine whether the user has a "sense of security" based on their input and past selection history.

[1777] 4. Candidate selection phase from font database

[1778] Server: The server generates candidates such as "Font A," "Font B," and "Font C" from the font database and creates a ranking.

[1779] 5. Recommended font display phase

[1780] Terminal: The terminal displays "Font A", "Font B", and "Font C" to the user.

[1781] 6. User selection and feedback gathering phase

[1782] User: The user selects "Font A" and types, "I found it to be more readable than the other fonts."

[1783] 7. Feedback Receiving and Analysis Phase

[1784] Server: The server analyzes that "Font A was chosen because it is highly readable."

[1785] 8. Algorithm improvement phase using machine learning

[1786] Server: The server uses this feedback to improve its algorithm to prioritize "readability" the next time it recommends a font.

[1787] In this manner, the present invention can take into account the user's emotional state and efficiently recommend fonts that are appropriate for different cultures and regions, supporting creative projects.

[1788] The processing flow will be explained below.

[1789] Step 1:

[1790] User: Enters project information using a device. For example, enters "Target region: Japan" and "Emotional tone: Modern and trustworthy" into an input form.

[1791] Step 2:

[1792] Terminal: Converts the entered project information into the appropriate format and sends it to the server.

[1793] Step 3:

[1794] Server: Receives the project information sent, temporarily stores the received information, and prepares it for analysis.

[1795] Step 4:

[1796] Server: Analyzes the received project information and extracts keywords and attributes such as target region and emotional tone. For example, it identifies keywords such as "Japan," "modern," and "trustworthy."

[1797] Step 5:

[1798] Server: Activates the emotion engine and analyzes the user's emotional state based on the project information and their reactions to the project. For example, it identifies emotional states such as "relief" and "vigor."

[1799] Step 6:

[1800] Server: Searches for suitable font candidates from the font database based on the extracted keywords and attributes and the emotional state analyzed by the emotion engine.

[1801] Step 7:

[1802] Server: Based on the search results, an AI algorithm is used to evaluate each font and generate a ranked list of candidate fonts.

[1803] Step 8:

[1804] Server: Sends the generated list of font candidates to the device. The list includes the font names and their respective evaluation scores.

[1805] Step 9:

[1806] Terminal: The received font candidate list is displayed on the user interface. For example, candidates such as "Font A," "Font B," and "Font C" are presented.

[1807] Step 10:

[1808] User: Selects the best font from a list of fonts presented, and when selected, optionally provides feedback and justification for the selection.

[1809] Step 11:

[1810] Terminal: Sends the user's selection information and feedback to the server. The feedback may include specific reasons for the selection, such as "I felt that font A was the easiest to read."

[1811] Step 12:

[1812] Server: Receives the selection information and feedback sent. Analyzes the received feedback and extracts the characteristics of the selected font and the reasons for its selection.

[1813] Step 13:

[1814] Server: Using the analysis results, we perform machine learning to improve the font recommendation algorithm. We add new data to the learning model to make the algorithm more accurate for the next font recommendation.

[1815] Step 14:

[1816] Server: Improved algorithms will be applied to the system, allowing it to more accurately recommend the best fonts the next time a user enters project information.

[1817] Example 2

[1818] 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."

[1819] Conventional font recommendation systems have difficulty recommending appropriate fonts because they do not sufficiently consider the user's emotional state or past selection history. Furthermore, they lack a mechanism for utilizing user feedback to improve the accuracy of the algorithm, making it difficult to continuously improve recommendation accuracy.

[1820] 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.

[1821] In this invention, the server includes means for receiving project information entered by a user, means for analyzing the received project information to extract keywords and attributes, means for selecting appropriate candidates from a database based on the extracted keywords and attributes, means for analyzing the user's emotional state based on the user's project information and past selection history using an emotion engine, means for presenting the selected candidates to the user in a ranked format, means for receiving feedback regarding the candidates selected by the user, means for improving a recommendation algorithm based on the received feedback, means for displaying the generated candidate list on a user interface, and means for applying a machine learning model using the received feedback. This enables appropriate font recommendations that take the user's emotional state into consideration and allows the recommendation algorithm to be continuously improved by utilizing user feedback.

[1822] "Project information" refers to information related to a task or project entered by a user.

[1823] "Keywords" are important words or phrases extracted from project information.

[1824] "Attributes" refer to characteristics or properties associated with keywords.

[1825] A "database" is a data store that stores information about various candidates (eg, fonts).

[1826] An "emotion engine" is a device or software that analyzes a user's emotional state based on their project information and past selection history.

[1827] The "ranking format" is a format in which the selected candidates are sorted based on their evaluation scores or rankings.

[1828] "Feedback" refers to the opinions and ratings provided by a user regarding a selected candidate.

[1829] A "recommendation algorithm" is a calculation method or procedure for recommending suitable candidates to a user.

[1830] A "machine learning model" is a model for improving and optimizing algorithms based on data.

[1831] "User interface" refers to the interface, such as input and output devices and screen displays, through which a user interacts with a system.

[1832] This invention provides an AI-based system that inputs project information, analyzes the user's emotional state using an emotion engine based on that information, and recommends appropriate fonts. Furthermore, by improving the recommendation algorithm based on user feedback, recommendation accuracy can be continuously improved.

[1833] System configuration

[1834] The system mainly includes the following elements:

[1835] 1. User interface (terminal): An interface for users to input project information and display font recommendation results.

[1836] 2. Server: This is the device that analyzes project information, recognizes emotional states using the emotion engine, recommends fonts, and collects and analyzes feedback.

[1837] 3. Font database: A database that stores information about various fonts and is used by the recommendation algorithm.

[1838] 4. Emotion engine: This engine analyzes the user's emotional state from their input and reactions and reflects this in font selection.

[1839] Program processing explanation

[1840] 1. User information input phase

[1841] Device: The user uses the device to enter project information, such as "Target region: Japan" and "Emotional tone: Modern and trustworthy," into an input form.

[1842] Terminal: The entered project information is converted into an appropriate format and sent to the server.

[1843] 2. Data Receipt and Analysis Phase

[1844] Server: The server receives the project information sent from the terminal and temporarily stores the received data in memory or a database.

[1845] Server: Analyzes project information using natural language processing algorithms to extract keywords and attributes such as target region and emotional tone. For example, identify keywords such as "Japan," "modern," and "trustworthy."

[1846] 3. Emotional state analysis phase

[1847] Server: Launches an emotion engine (e.g., a general commercial emotion analysis engine) and analyzes the user's emotional state based on the user's project information and past selection history. For example, it analyzes emotions such as "relief" and "liveliness."

[1848] Server: Temporarily stores the analysis results and uses them in the next phase.

[1849] 4. Candidate selection phase from font database

[1850] Server: Accesses the font database based on the emotional state provided by the emotion engine and the extracted keywords and attributes.

[1851] Server: Runs a database query to find suitable font candidates, such as "Font A" that gives a "comfortable feeling" and "Font B" that has a modern design.

[1852] Server: Evaluates each font using an AI algorithm (e.g., random forest) and generates a ranked list of candidate fonts.

[1853] 5. Recommended font display phase

[1854] Server: Sends the generated list of font candidates to the terminal, including the font names and their respective evaluation scores.

[1855] Terminal: The terminal displays the received font list on the user interface. For example, candidates such as "Font A," "Font B," and "Font C" are presented.

[1856] 6. User selection and feedback gathering phase

[1857] User: Select the most suitable font from the presented font list. For example, select "Font A".

[1858] User: After completing the selection, enter the reason for the selection and feedback. For example, enter a specific reason such as "I felt that font A was the easiest to read."

[1859] Terminal: Sends user selection information and feedback to the server.

[1860] 7. Feedback Receiving and Analysis Phase

[1861] Server: Receives the submitted selection information and feedback and stores it in memory or a database for analysis.

[1862] Server: The feedback is analyzed using natural language processing algorithms to extract the characteristics of the selected font and the reasons for its selection.

[1863] 8. Algorithm improvement phase using machine learning

[1864] Server: Uses the analysis results to perform machine learning to improve the font recommendation algorithm, for example, by adding new data to the learning model and retraining the algorithm's parameters.

[1865] Server: Check that the algorithm has improved and prepare the new model for the next font recommendation.

[1866] Specific examples

[1867] Example 1: Website design for the Japanese market

[1868] 1. User information input phase

[1869] Device: User inputs "E-commerce site design for the Japanese market", "Target region: Japan", "Emotional tone: modern and trustworthy".

[1870] Terminal: The terminal sends the input information to the server.

[1871] 2. Data Receipt and Analysis Phase

[1872] Server: The server extracts keywords such as "Japan," "modern," and "trustworthy" and temporarily stores them.

[1873] 3. Emotional state analysis phase

[1874] Server: Using the emotion engine, determine whether the user has a sense of security based on their input and past selection history.

[1875] 4. Candidate selection phase from font database

[1876] Server: The server generates candidates such as "Font A," "Font B," and "Font C" from the font database and creates a ranking.

[1877] 5. Recommended font display phase

[1878] Terminal: The terminal displays "Font A", "Font B", and "Font C" to the user.

[1879] 6. User selection and feedback gathering phase

[1880] User: The user selects "Font A" and types, "I found it to be more readable than the other fonts."

[1881] Terminal: Sends user selection information and feedback to the server.

[1882] 7. Feedback Receiving and Analysis Phase

[1883] Server: The server analyzes that "Font A was chosen because it is highly readable."

[1884] 8. Algorithm improvement phase using machine learning

[1885] Server: The server uses this feedback to improve its algorithm to prioritize "readability" the next time it recommends a font.

[1886] Example input to a generative AI model

[1887] I'd like to design a modern and trustworthy e-commerce website for the Japanese market. The target geography is Japan, and the emotional tone should ideally be modern and trustworthy. Please recommend a suitable font.

[1888] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1889] Step 1:

[1890] Entering user information

[1891] User: Enters project information into the input form provided on the device.

[1892] Specific actions: For example, enter information such as "Target region: Japan" and "Emotional tone: Modern and trustworthy."

[1893] Input: Project information entered by the user.

[1894] Output: Information entered into the terminal is converted into a data format for transmission from the terminal to the server.

[1895] Step 2:

[1896] Receiving data

[1897] Server: Receives project information sent from the device.

[1898] Specific operation: Temporarily store received data in memory or a database.

[1899] Input: Project information sent from the device.

[1900] Output: The received data converted into a parsable data format.

[1901] Step 3:

[1902] Project Information Analysis

[1903] Server: Analyzes project information using natural language processing algorithms.

[1904] What it does: Uses a natural language processing library (e.g., spaCy) to extract keywords and attributes such as "target region: Japan" and "emotional tone: modern and trustworthy."

[1905] Input: Received project information.

[1906] Output: Extracted keywords and attributes (e.g., "Japan," "modern," "trustworthy").

[1907] Step 4:

[1908] Emotional state analysis

[1909] Server: Launches the emotion engine and analyzes the user's emotional state based on project information and past selection history.

[1910] Specific behavior: Analyze emotions such as "relief" and "liveliness" using a commercial sentiment analysis engine (e.g., IBM Watson NLU).

[1911] Input: Parsed keywords and attributes, and the user's past selection history.

[1912] Output: Emotional state as a result of the analysis (e.g., "Relaxed," "Energetic").

[1913] Step 5:

[1914] Search for font suggestions

[1915] Server: Accesses the font database based on the emotional state provided by the emotion engine and the extracted keywords and attributes.

[1916] What it does: Runs a database query to find, for example, "Font A" that gives a "comfortable feeling" and "Font B" that has a modern design.

[1917] Input: Emotional state, extracted keywords and attributes.

[1918] Output: A list of searched font candidates.

[1919] Step 6:

[1920] Rating and ranking of font candidates

[1921] Server: Based on the search results, an AI algorithm is used to evaluate each font and generate a ranked list of font candidates.

[1922] What it does: It uses a random forest algorithm to calculate the font's rating score and then creates a ranking based on the rating score.

[1923] Input: Font candidate list.

[1924] Output: A ranked list of fonts with rating scores.

[1925] Step 7:

[1926] Displaying font recommendation results

[1927] Server: Sends the generated font candidate list to the terminal.

[1928] Specific behavior: Sends data to the device including font names and their respective rating scores.

[1929] Input: Ranked font list.

[1930] Output: Font candidate list sent to the terminal.

[1931] Step 8:

[1932] User selection and feedback input

[1933] User: Select the best font from the list of fonts presented and provide feedback and reasons for their choice.

[1934] Specific action: For example, the user selects "Font A" and enters "I felt it had higher readability than other fonts."

[1935] Input: User font selection and feedback.

[1936] Output: Selection information and feedback are sent from the device to the server.

[1937] Step 9:

[1938] Receiving and analyzing feedback

[1939] Server: Receives the submitted selection information and feedback and temporarily stores it for analysis.

[1940] What it does: It uses natural language processing algorithms to analyze the feedback and extract the characteristics of the selected font and the reasons for its selection.

[1941] Input: User selection information and feedback.

[1942] Output: Extracted selection reasons and font features.

[1943] Step 10:

[1944] Algorithm Improvements

[1945] Server: Uses the analysis results to perform machine learning to improve the font recommendation algorithm.

[1946] What it does: Adds new data to the learning model and retrains the algorithm's parameters.

[1947] Input: Feedback analysis results.

[1948] Output: An improved recommendation algorithm.

[1949] (Application example 2)

[1950] 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."

[1951] Current advertising design creation systems have difficulty recommending fonts that take into account the user's emotional state when selecting an appropriate font based on project information. Another problem is that font selection takes time, making it difficult to achieve an effective design. With conventional technologies, users often select fonts based on intuition or experience, which can result in suboptimal optimization of the advertisement's visual and emotional impact.

[1952] 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.

[1953] In this invention, the server includes: means for receiving project information input by a user; means for analyzing the received project information and extracting keywords and attributes; means for selecting appropriate candidates from a font database based on the extracted keywords and attributes; means for presenting the selected candidates to the user in a ranked format; means for receiving feedback on the font selected by the user; means for improving a recommendation algorithm based on the received feedback; means for including a smartphone application that inputs advertising design project information and recommends optimal fonts; and means for reflecting the user's emotional state in font selection using an emotion analysis engine that analyzes the user's emotional state. This makes it possible to recommend optimal fonts in real time taking into account the user's emotional state, thereby maximizing the visual and emotional impact of advertisements.

[1954] "Project Information" is detailed information a user provides about an advertising design or other design project, including target market, emotional tone, design objectives, and the like.

[1955] A "font database" is a database that stores information about various fonts, including data such as font names, styles, and uses.

[1956] The "ranking format" is a format in which multiple candidates are ranked based on specific criteria and presented, allowing the user to easily make the optimal selection.

[1957] "Feedback" is information such as opinions, ratings, and reasons for a particular font selection that a user provides, and is used to improve the recommendation algorithm next time.

[1958] An "emotion analysis engine" is an engine that analyzes a user's emotional state from their input information and reactions, and supports specific actions and choices based on the results.

[1959] A "smartphone application" is software that runs on a smartphone and allows users to input project information and receive recommendations for optimal fonts.

[1960] "Recommendation algorithm improvement" is the process of improving the accuracy and efficiency of the algorithm based on feedback received from users.

[1961] "Advertising design" is the process of creating the visual representation of an advertising campaign, selecting elements such as fonts, colors, and images to create the optimal advertisement.

[1962] "Emotional state" refers to the psychological or emotional state analyzed based on the user's input and reactions, and includes emotions such as a sense of security and trust.

[1963] MODE FOR CARRYING OUT THE INVENTION

[1964] This invention provides a system that allows users to input project information, such as advertising design, and then uses an emotion analysis engine to analyze the user's emotional state based on that information and recommend appropriate fonts. Furthermore, the recommendation algorithm is improved based on user feedback, continuously improving recommendation accuracy. This system mainly consists of the following components:

[1965] System Components

[1966] 1. User Interface (Smartphone Application): This is an interface where users can input project information for advertising design and view font recommendations. Users input project information such as target market, emotional tone, and design objectives.

[1967] 2. Server: Receives and analyzes project information, uses an emotion analysis engine to recognize the user's emotional state, recommends fonts, collects and analyzes feedback, and accesses the font database to select the appropriate font.

[1968] 3. Font Database: A database that stores information about various fonts, including font names, styles, and uses. The server uses a recommendation algorithm to select an appropriate font from the database.

[1969] 4. Sentiment Analysis Engine: This engine analyzes the user's emotional state from their input information and reactions, and can use non-specific emotion analysis engines such as IBM Watson Tone Analyzer. This engine identifies the user's emotional state from project information and past selection history and reflects this in the font selection.

[1970] System Operation

[1971] The server first receives advertising design project information entered by the user through a smartphone application, including the target market (e.g., Japan), emotional tone (e.g., modern and trustworthy), and design purpose (e.g., display advertising).

[1972] The server then analyzes the received project information and extracts keywords and attributes such as target market, emotional tone, and design purpose. It uses a sentiment analysis engine to analyze the user's emotional state (e.g., sense of security) and selects an appropriate font from a font database based on the results.

[1973] The selected fonts are presented to the user in a ranked format, and the user selects the most suitable font from the recommended fonts. After completing the selection, the user enters the reason for their selection and feedback, which is then sent to the server. For example, the user could provide feedback such as, "I felt that font A was easier to read than the other fonts."

[1974] The server analyzes the received feedback and extracts the characteristics of the selected font and the reasons for its selection. This is then used to apply a machine learning model to improve the accuracy of the recommendation algorithm. This adds new data to the learning model, improving the algorithm's accuracy for the next font recommendation.

[1975] Specific examples

[1976] For example, if a user inputs the project information "Target region: Japan," "Emotional tone: Modern and trustworthy," and "Ad type: Display ads," the system will extract keywords such as "Japan," "modern," and "trustworthy," and use the sentiment analysis engine to identify the emotional state as "reassuring." As a result, it will recommend fonts such as "Font A," "Font B," and "Font C," and continuously refine the algorithm based on user selection and feedback.

[1977] An example of a prompt is as follows:

[1978] "Please recommend a font that would be ideal for advertising designs that have a modern and trustworthy feel."

[1979] "The target region is Japan, and readability is important."

[1980] In this manner, the invention takes into account the user's emotional state and can efficiently recommend optimal fonts suited to different cultures and regions, thereby supporting creative design creation.

[1981] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1982] Step 1:

[1983] Users operate a smartphone application to input project information for advertising design, including the target market (e.g., "Japan"), emotional tone (e.g., "modern and trustworthy"), and design purpose (e.g., "display advertising"). This data is converted into an appropriate format by the application and sent to the server.

[1984] Inputs: Target market, emotional tone, design objectives

[1985] Output: Data converted into the appropriate format

[1986] Specific operation: A form is displayed on the smartphone screen, the user enters project information, the input is converted to JSON format and sent to the server.

[1987] Step 2:

[1988] The server receives project information sent from the smartphone application, temporarily stores the received information, and prepares it for the next analysis.

[1989] Input: Data converted into the appropriate format

[1990] Output: Temporarily saved project information

[1991] Specific operation: The server receives an HTTP request and temporarily stores the received data in a database.

[1992] Step 3:

[1993] The server analyzes the received project information and extracts keywords and attributes such as target market, emotional tone, design objectives, etc. Specifically, it uses text analysis algorithms to identify keywords.

[1994] Input: Temporarily saved project information

[1995] Output: Extracted keywords and attributes

[1996] What it does: The server uses a natural language processing library (e.g., NLTK or spaCy) to parse the project information text and extract important keywords.

[1997] Step 4:

[1998] The server runs an emotion analysis engine, such as IBM Watson Tone Analyzer, to analyze the user's emotional state based on their input and past selection history.

[1999] Input: Extracted keywords and attributes

[2000] Output: User's emotional state

[2001] Specific operation: Project information is sent to the emotion analysis engine, and the engine returns the emotional state as the analysis result.

[2002] Step 5:

[2003] The server accesses the font database and searches for suitable font candidates based on the emotional state provided by the emotion analysis engine and the extracted keywords and attributes. The searched fonts are then evaluated and a candidate list is generated in a ranked format.

[2004] Input: User's emotional state, extracted keywords and attributes

[2005] Output: Ranked list of font candidates

[2006] Specific operation: Runs an SQL query against the font database to extract fonts that match the search criteria, assigns a score to each font, and generates a ranking.

[2007] Step 6:

[2008] The server sends the generated font candidate list to the smartphone application, which displays the received font list on its user interface.

[2009] Input: A ranked list of font candidates

[2010] Output: A list of font candidates displayed in the user interface

[2011] Specific operation: The server sends an HTTP response, the application receives the response and displays the fonts on the screen in list format.

[2012] Step 7:

[2013] The user selects the most suitable font from the presented font list and inputs the reason for their selection and feedback, which is then sent to the server via the smartphone application.

[2014] Input: User font selection and feedback

[2015] Output: Feedback data converted into the appropriate format

[2016] Specific behavior: The user selects a font from a list in the application, fills out an input form explaining the reason for selecting it, and submits it to the server.

[2017] Step 8:

[2018] The server receives and analyzes the selection information and feedback, extracting the characteristics of the selected font and the reasons for its selection.

[2019] Input: Feedback data converted into the appropriate format

[2020] Output: The characteristics of the selected font and the reason for its selection

[2021] What it does: The server stores the feedback data in a database and uses text analysis algorithms to extract important features and reasons.

[2022] Step 9:

[2023] The server uses the analysis results to perform machine learning to improve the recommendation algorithm, adding new data to the learning model and improving the algorithm for the next font recommendation.

[2024] Input: The characteristics of the selected font and the reason for its selection

[2025] Output: Improved recommendation algorithm

[2026] What it does: Uses machine learning libraries (e.g., scikit-learn and TensorFlow) to train models based on feedback data and improve recommendation algorithms.

[2027] 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.

[2028] 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.

[2029] 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.

[2030] 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.

[2031] 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.

[2032] 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.

[2033] 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).

[2034] 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.

[2035] 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."

[2036] 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.

[2037] 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).

[2038] 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.

[2039] 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.

[2040] 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.

[2041] 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.

[2042] 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.

[2043] 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.

[2044] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[2045] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[2046] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[2047] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[2048] The following is further disclosed regarding the above embodiment.

[2049] (Claim 1)

[2050] means for receiving project information entered by a user;

[2051] A means for analyzing received project information and extracting keywords and attributes;

[2052] A means for selecting suitable candidates from a font database based on the extracted keywords and attributes;

[2053] a means for presenting the selected candidates to a user in a ranked format;

[2054] means for receiving feedback regarding the font selected by the user;

[2055] means for improving the recommendation algorithm based on the received feedback;

[2056] A system including:

[2057] (Claim 2)

[2058] 10. The system of claim 1, further comprising means for analyzing the received feedback and extracting characteristics of the selected font and reasons for its selection.

[2059] (Claim 3)

[2060] 10. The system of claim 1, further comprising means for applying a machine learning model using user feedback to improve the accuracy of the recommendation algorithm.

[2061] "Example 1"

[2062] (Claim 1)

[2063] means for receiving project information entered by a user;

[2064] A means for analyzing received project information and extracting keywords and attributes;

[2065] A means for selecting suitable candidates from a database based on the extracted keywords and attributes;

[2066] a means for presenting the selected candidates to a user in a ranked format;

[2067] means for receiving feedback regarding the element selected by the user;

[2068] means for improving the recommendation algorithm based on the received feedback;

[2069] A means for parsing and analyzing the extracted keywords and attributes using natural language processing technology;

[2070] A means for generating a candidate list using a machine learning model, evaluating the characteristics of each candidate, and scoring and ranking the candidates;

[2071] A system including:

[2072] (Claim 2)

[2073] 10. The system of claim 1, further comprising means for analyzing the received feedback and quantifying and structuring the characteristics of the selected elements and the reasons for their selection.

[2074] (Claim 3)

[2075] 10. The system of claim 1, further comprising means for applying a machine learning model using user feedback to improve the accuracy of the recommendation algorithm.

[2076] "Application Example 1"

[2077] (Claim 1)

[2078] means for receiving project information entered by a user;

[2079] A means for analyzing received project information and extracting keywords and attributes;

[2080] A means for selecting suitable candidates from a font database based on the extracted keywords and attributes;

[2081] a means for presenting the selected candidates to a user in a ranked format;

[2082] A means for automatically applying a user-selected font in a content distribution service based on legibility and cultural suitability;

[2083] means for receiving feedback regarding the font selected by the user;

[2084] means for improving the recommendation algorithm based on the received feedback;

[2085] A system including:

[2086] (Claim 2)

[2087] 10. The system of claim 1, further comprising means for analyzing the received feedback and extracting characteristics of the selected font and reasons for its selection.

[2088] (Claim 3)

[2089] 10. The system of claim 1, further comprising means for applying a machine learning model using user feedback to improve the accuracy of the recommendation algorithm.

[2090] "Example 2: Combining Emotion Engines"

[2091] (Claim 1)

[2092] means for receiving project information entered by a user;

[2093] A means for analyzing received project information and extracting keywords and attributes;

[2094] A means for selecting suitable candidates from a database based on the extracted keywords and attributes;

[2095] A means for analyzing a user's emotional state from project information and past selection history using an emotion engine;

[2096] a means for presenting the selected candidates to a user in a ranked format;

[2097] means for receiving feedback regarding the candidate selected by the user;

[2098] means for improving the recommendation algorithm based on the received feedback;

[2099] means for displaying the generated candidate list on a user interface;

[2100] means for applying a machine learning model using the received feedback;

[2101] A system including:

[2102] (Claim 2)

[2103] 10. The system of claim 1, further comprising means for analyzing the received feedback and extracting characteristics of the selected candidate and reasons for selection.

[2104] (Claim 3)

[2105] 10. The system of claim 1, further comprising means for applying a machine learning model using user feedback to improve the accuracy of the recommendation algorithm.

[2106] "Application example 2 when combining emotion engines"

[2107] (Claim 1)

[2108] means for receiving project information entered by a user;

[2109] A means for analyzing received project information and extracting keywords and attributes;

[2110] A means for selecting suitable candidates from a font database based on the extracted keywords and attributes;

[2111] a means for presenting the selected candidates to a user in a ranked format;

[2112] means for receiving feedback regarding the font selected by the user;

[2113] means for improving the recommendation algorithm based on the received feedback;

[2114] A means including a smartphone application for inputting project information of an advertising design and recommending an optimal font;

[2115] A means for reflecting the user's emotional state in font selection using an emotion analysis engine that analyzes the user's emotional state;

[2116] A system including:

[2117] (Claim 2)

[2118] 10. The system of claim 1, further comprising means for analyzing the received feedback and extracting characteristics of the selected font and reasons for its selection.

[2119] (Claim 3)

[2120] 10. The system of claim 1, further comprising means for applying a machine learning model using user feedback to improve the accuracy of the recommendation algorithm. [Explanation of symbols]

[2121] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving project information entered by a user; A means for analyzing received project information and extracting keywords and attributes; A means for selecting suitable candidates from a font database based on the extracted keywords and attributes; a means for presenting the selected candidates to a user in a ranked format; means for receiving feedback regarding the font selected by the user; means for improving the recommendation algorithm based on the received feedback; A system including:

2. 10. The system of claim 1, further comprising means for analyzing the received feedback and extracting characteristics of the selected font and reasons for its selection.

3. The system of claim 1 , further comprising means for applying a machine learning model using user feedback to improve the accuracy of the recommendation algorithm.

Images