System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving preference information of a user; means for storing the received preference information; data analysis means utilizing generative artificial intelligence for analyzing the stored preference information and identifying a preference pattern of the user; means for generating or selecting an artwork suitable for the user based on the identified preference pattern; and means for providing the generated or selected artwork to the user.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] For many people interested in art, it is extremely difficult to find artwork that suits their tastes. In particular, for beginners who are not familiar with art or users who are exploring a particular art style for the first time, the wide range of choices can be overwhelming. In such situations, users may spend a lot of time trying to find artwork that suits their tastes, which can result in a loss of enjoyment in art appreciation. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention proposes the following configuration: a system including: means for receiving user preference information; means for storing the received preference information; means for analyzing the stored preference information and using generative artificial intelligence to identify the user's preference pattern; means for generating or selecting an artwork suited to the user based on the identified preference pattern; and means for providing the generated or selected artwork to the user. This system allows users to easily find artwork that matches their preferences, improving their art appreciation experience.

[0006] "User" refers to a person who uses the system to receive recommendations for artworks.

[0007] "Preference information" is data relating to a user's preferences and interests, including favorite colors, favorite artists, and a history of artworks viewed in the past.

[0008] The "receiving means" is a mechanism by which the system acquires the preference information input by the user.

[0009] The "storage means" is a mechanism for digitally recording and storing preference information acquired through the receiving means.

[0010] "Data analysis means" refers to methods and technologies for analyzing stored preference information and identifying user preference patterns.

[0011] "Generative artificial intelligence" is a technology that uses techniques such as machine learning and deep learning to analyze user preference patterns and includes algorithms that generate or select new artworks.

[0012] "Artwork creation means" refers to the technology and mechanisms for creating new artwork based on the user's preferences.

[0013] The "artwork selection means" refers to the technology and mechanism for selecting artworks that match the user's preferences from an existing art database.

[0014] The "means for providing" is a mechanism for displaying and providing the generated or selected artwork to the user. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0023] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0036] The system of the present invention is for recommending personalized art based on a user's preferences, and includes a series of steps for analyzing the user's preferences and generating or selecting and providing artworks based on the preferences. The program processing of the system is described in detail below.

[0037] Program Overview

[0038] This system is an online platform that receives input from users' devices, analyzes that information on the server side, and uses generative AI to recommend personalized art, allowing users to easily discover and appreciate artworks that suit their tastes.

[0039] User information acquisition

[0040] After logging in to the system, a user enters their art preferences. Specifically, the user enters their favorite colors, favorite art styles, favorite artists, artworks they have viewed in the past, etc. through an input form. For example, suppose a user enters that they like "Impressionism" and that "blue" is their favorite color.

[0041] User information transmission

[0042] Once the input is complete, the device collects this preference information and sends it to the server as an HTTP request. The server receives this request and proceeds to the next processing step.

[0043] Saving user information

[0044] The server analyzes the received preference information and stores it in a database, so that the user does not have to re-enter it when they use the system again in the future.

[0045] Data analysis

[0046] The server then begins analyzing the data to identify the user's preferences based on the stored preference information. Specifically, it uses generative AI to analyze the preference information and extract the user's preferred characteristics. These characteristics are based on patterns, such as "the user likes impressionist art, and particularly prefers blue artworks."

[0047] Art recommendation generation

[0048] Based on the results of the data analysis, the server activates the AI ​​to generate artwork that matches the user's preferences or select artwork from an existing database. For example, if the user likes the color blue, the AI ​​will generate impressionist artwork that contains a lot of blue.

[0049] Returning the results

[0050] The server sends the generated art recommendation list to the device as an HTTP response. The device receives the list and displays appropriate artworks for the user. The user can click on the recommended artworks to view more information or bookmark their favorite artworks.

[0051] Specific examples

[0052] As a specific example, suppose a user logs in and enters preference information such as "Impressionism," "blue," and "Monet." The server receives this data, stores it in a database, and uses generative AI to generate impressionist art with a blue base that matches the user's preferences. As a result, the server generates a recommended list such as "a new artwork depicting a Monet-esque blue water surface," and sends it back to the user's device. The user can browse this list and find their favorite works.

[0053] As described above, this system significantly improves the user's art appreciation experience, allowing everyone to easily find art that suits their tastes.

[0054] The processing flow will be explained below.

[0055] Step 1:

[0056] A user logs into the system. The user enters their login information and, if authentication is successful, a user session begins.

[0057] Step 2:

[0058] The user enters their preferences, including their favorite art style, favorite colors, and names of artists they often watch, into an input form.

[0059] Step 3:

[0060] The device collects the input preference information and organizes it into a data structure, such as JSON, which is formatted for easy analysis later.

[0061] Step 4:

[0062] The device sends the formatted data structure to the server as an HTTP request, which includes the user's preference information.

[0063] Step 5:

[0064] The server parses the received HTTP request, extracts the preference information from the request body, and stores it in a database in an appropriate format.

[0065] Step 6:

[0066] The server retrieves the user's preference information stored in the database and begins analysis, using a generative AI model to analyze the data to identify user preference patterns.

[0067] Step 7:

[0068] A generative AI model generates new artworks based on identified preference patterns, or selects artworks from an existing database that match the user's preferences.

[0069] Step 8:

[0070] The server compiles a list of generated or selected artworks into a recommendation list, which also includes the reason for the recommendation and related information.

[0071] Step 9:

[0072] The server sends the created recommendation list to the terminal as an HTTP response, which also includes detailed information about the recommended artworks.

[0073] Step 10:

[0074] The device analyzes the received HTTP response, extracts the recommendation list, and displays it in a user-friendly format.

[0075] Step 11:

[0076] Users can browse recommended artworks and bookmark their favorites. Users can also click on artworks to get more detailed information.

[0077] Example 1

[0078] 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."

[0079] Conventional art recommendation systems have struggled to provide personalized artworks that fully reflect a user's preferences. As a result, users are unable to efficiently find artworks that interest them, resulting in an unsatisfactory art appreciation experience. Furthermore, users must re-enter their preference information each time they use the system, which is inconvenient.

[0080] 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.

[0081] In this invention, the server includes a means for receiving user preference information, a means for storing the received preference information, and a data analysis means for analyzing the stored preference information and using artificial intelligence to identify the user's preference patterns. This enables personalized recommendations of artworks based on the user's preferences. Furthermore, by including a means for transmitting the generated art recommendation list to the terminal as an HTTP response, which the terminal receives and displays to the user, the user can easily find artworks that suit their preferences, eliminating the need for re-entry when using the system again, improving convenience.

[0082] "Preference information" is information that indicates the user's preferences, such as the user's favorite colors, favorite art styles, favorite artists, and the history of artworks that the user has viewed in the past.

[0083] The "receiving means" is a function or device for receiving preference information input by a user via a network.

[0084] The "storing means" is a function or device for storing the received preference information in a database or storage.

[0085] The "data analysis means" is a function or device that analyzes the stored preference information and identifies the user's preference patterns, and is the part that uses generative artificial intelligence.

[0086] "Generative AI" is software or a system that has the ability to generate new artworks using specific rules and algorithms based on user preferences.

[0087] The "means for identifying" is a function or device for extracting and clarifying a user's preference patterns through data analysis.

[0088] A "generative means" is a function or device for creating new artworks using generative artificial intelligence.

[0089] The "selection means" is a function or device for selecting artworks that match the user's preferences from an existing database.

[0090] The "means for providing" is a function or device for transmitting the generated or selected artwork to the user's terminal and displaying it.

[0091] A "terminal" is a device such as a computer, smartphone, or tablet that a user uses to input preference information and view provided artworks.

[0092] An "HTTP request" is a type of web protocol that allows a user's device to send information to a server.

[0093] An "HTTP response" is a type of web protocol that allows a server to return information to a user's device.

[0094] A "database" is a storage system that stores received preference information for later retrieval and analysis.

[0095] A "recommendation list" is a generated or selected list of artworks that is provided to a user.

[0096] The system according to the present invention is for recommending personalized art based on a user's preferences, and includes a series of steps for analyzing the user's preferences and generating or selecting and providing artwork based on the user's preferences. Specific embodiments of the system are described in detail below.

[0097] User information acquisition

[0098] A user first logs in to the system. After logging in, the user enters their art-related preference information. This information includes favorite colors, favorite art styles, favorite artists, and a history of artworks they have viewed in the past. As a specific example, consider the case where a user enters preference information such as "Impressionism," "blue," and "Monet."

[0099] User information transmission

[0100] Once the user has completed entering their preference information, the device sends this information to the server. The HTTP protocol is used for transmission, and the request is in JSON format. For example, the device sends the preference information as an HTTP request "POST / api / preferences".

[0101] Saving user information

[0102] The server analyzes the received preference information and stores it in a database (e.g., MySQL or MongoDB). The received JSON data is parsed and stored in an appropriate format.

[0103] Data analysis

[0104] The server then begins data analysis to identify the user's preferences based on the preference information stored in the database. In this step, the data is analyzed using programming languages ​​such as Python and R, and generative artificial intelligence (e.g., GPT-4) is utilized. Through this analysis, the user's preference patterns are extracted, and characteristics such as "the user likes impressionist art, and particularly prefers blue works" are identified.

[0105] Art recommendation generation

[0106] Based on the results of the data analysis, the server launches a generative AI model to generate artwork that matches the user's preferences, or selects suitable artwork from an existing database. For example, a Python script can be used to send a prompt to the generative AI model, such as, "The user likes impressionist artwork and is particularly fond of the color blue. Please generate a new artwork based on these conditions."

[0107] Returning the results

[0108] The server sends the generated art recommendation list to the device as an HTTP response. The device receives this response and displays appropriate art works to the user. The display is visually organized using HTML and CSS, making it easy for the user to browse.

[0109] User art appreciation

[0110] Users can click on artworks displayed on their devices to view detailed information or bookmark artworks they like. Specifically, users can click on the thumbnail of a displayed artwork to go to the details page where they can view a description of the artwork and information about the artist. They can also use the bookmark function to easily find their favorite artworks later.

[0111] Specific examples

[0112] The user logs in and enters preference information such as "Impressionist," "blue," and "Monet." The user's device then sends the preference information to the server via an HTTP request. The server stores this data in a database and sends a prompt to the generative AI model: "The user likes Impressionist artwork, and is particularly fond of the color blue. Please generate a new artwork based on these conditions." This generates an Impressionist artwork with a blue base. The server then compiles these artworks into a list and sends it back to the user's device. The user can then browse the displayed list of artworks, check detailed information, and bookmark artworks.

[0113] As described above, this system significantly improves the user's art appreciation experience, allowing everyone to easily find art that suits their tastes.

[0114] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0115] Step 1: Enter your user information

[0116] The user logs in to the system. After logging in, the user enters their preference information through an input form. The information entered includes favorite colors, favorite art styles, favorite artists, and a history of artworks viewed in the past. Specific examples of input include preference information such as "Impressionism," "blue," and "Monet." This input becomes the initial data for the system.

[0117] Input: User preferences (favorite colors, art styles, artists, etc.)

[0118] Output: Input preference information

[0119] Step 2: Submit user information

[0120] When the user has finished entering their preference information, the device compiles this information and sends it to the server as an HTTP request. The request uses the POST method, and data is sent in JSON format. Specifically, the device sends a request to the endpoint "POST / api / preferences".

[0121] Input: User-entered preferences

[0122] Output: HTTP request for preferences sent to the server

[0123] Step 3: Save user information

[0124] The server analyzes the received preference information and stores it in a database (e.g., MySQL or MongoDB). The received JSON data is parsed, converted into an appropriate format, and then stored in the database. This allows the user's preference information to be stored in a reusable format.

[0125] Input: HTTP request for preference information sent to the server

[0126] Output: User preferences stored in a database

[0127] Step 4: Data analysis

[0128] The server analyzes the data to identify the user's preferences based on the preference information stored in the database. Specifically, it uses programming languages ​​such as Python and R and generative artificial intelligence (e.g., GPT-4) to analyze the preference information. As feedback, it extracts specific patterns, such as the user's "I like impressionist paintings, and I particularly like blue works."

[0129] Input: User preferences stored in a database

[0130] Output: User preference pattern (e.g., "I like impressionist art, and I especially like blue artworks")

[0131] Step 5: Art recommendation generation

[0132] The server then launches a generative AI model based on the data analysis results to generate artwork that matches the user's preferences, or selects a suitable artwork from an existing database. Specifically, the server sends the generative AI model a prompt such as, "The user likes impressionist artwork, and is particularly fond of the color blue. Please generate a new artwork based on these conditions."

[0133] Input: User preference patterns

[0134] Output: Generated artwork or selected existing artwork

[0135] Step 6: Returning the results

[0136] The server sends the generated art recommendation list to the device as an HTTP response. The sent data is in JSON format and is structured to display appropriate art works to the user. The display is visually organized using HTML and CSS.

[0137] Input: Generated artwork or selected existing artwork

[0138] Output: Art recommendation list sent to user device (HTTP response)

[0139] Step 7: User Art Appreciation

[0140] Users can click on artworks displayed on their devices to view detailed information. They can also bookmark artworks they like. Specifically, users can click on a thumbnail of a displayed artwork to move to a detailed page where they can view a description of the artwork and information about the artist. Viewing and bookmarking operations are performed based on this information.

[0141] Input: Art recommendation list sent to user device

[0142] Output: User can view details of artwork and bookmark it

[0143] Through the above steps, a personalized art recommendation system based on the user's preferences is realized.

[0144] (Application example 1)

[0145] 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."

[0146] In today's brick-and-mortar stores, it is difficult to efficiently and effectively present artworks that match the tastes of visitors. This can result in missed opportunities to capture visitors' interest and lower satisfaction. Furthermore, while there is a demand for providing personalized experiences based on the preferences of each individual visitor, there is a lack of suitable means to achieve this.

[0147] 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.

[0148] In this invention, the server includes means for receiving user preference information, means for storing the received preference information, means for analyzing the stored preference information and using artificial intelligence to identify the user's preference pattern, means for generating or selecting an artwork suited to the user based on the identified preference pattern, means for providing the generated or selected artwork to the user, and means for visually presenting the artwork on a user-dedicated display device, thereby enabling visitors to experience artwork suited to their preferences in real time at a physical store.

[0149] The "means for receiving user preference information" refers to an interface for obtaining information about a user's preferences regarding art.

[0150] The "means for storing received preference information" refers to a database or storage system for storing acquired user preference information for a long period of time.

[0151] "Generative AI-based data analysis means" refers to a process that uses artificial intelligence techniques to analyze received and stored preference information and identify user preference patterns.

[0152] "Means for generating or selecting artwork" refers to a function for generating a new artwork based on the user's preferences or selecting an appropriate artwork from existing artworks.

[0153] "Means for providing generated or selected artwork" refers to a method or system for presenting generated or selected artwork to a user.

[0154] "User-only display device" refers to a device that visually presents artwork to a user only.

[0155] "Smart glasses" refers to a glasses-type device that has the function of visually displaying information when worn by a user.

[0156] The system for implementing the present invention includes a series of functions for receiving user preference information and recommending personalized art based on the information. The program processing of the system is described in detail below.

[0157] User information acquisition

[0158] First, a user logs in to the system and inputs their preferences regarding art. Specifically, the user inputs their favorite color, favorite art style, favorite artist, artworks they have viewed in the past, etc. through an input form. For example, a user may input that they like "Impressionism" and "the color blue," and that they like "Monet."

[0159] User information transmission

[0160] The terminal collects the input preference information and sends it to the server as an HTTP request. The server receives this request and proceeds to the next processing step.

[0161] Saving user information

[0162] The server analyzes the received preference information and stores it in a database, which saves the user the trouble of having to re-enter the information when they use the system again in the future.

[0163] Data analysis

[0164] The server then begins data analysis to identify the user's preferences based on the stored preference information. Specifically, it uses generative artificial intelligence (generative AI) to analyze the preference information and extract the user's preferred features. This generative AI uses a generative AI model such as OpenAI GPT-3.

[0165] Art recommendation generation

[0166] Based on the results of the data analysis, the server activates the AI ​​to generate artwork that matches the user's preferences or select artwork from an existing database. For example, if the user likes the color blue, the AI ​​will generate impressionist artwork that contains a lot of blue.

[0167] Returning the results

[0168] The server sends the generated or selected art recommendation list to the terminal as an HTTP response. The terminal receives the list and displays appropriate artworks to the user. The user can click on the recommended artworks to view detailed information or bookmark their favorite artworks.

[0169] User-specific display device

[0170] Users can visually experience recommended artworks in real time using a user-specific display device, including smart glasses. For example, when visiting a physical store, a user wearing smart glasses scans a specific area, and artworks generated by the server are displayed on the glasses' display.

[0171] Specific examples

[0172] As a concrete example, suppose a user logs in and enters preferences such as "Impressionist," "blue," and "Monet." The server analyzes this data and feeds the generative AI model the following prompt:

[0173] "User A's preferences are 'blue,' 'Impressionism,' and 'Monet.' Generate a new artwork based on these preferences."

[0174] Based on this prompt, the AI ​​will generate a "new artwork depicting a Monet-esque blue water surface," and the server will send this recommendation to the user's smart glasses. The user can then view the artwork in real time through the glasses, obtain more information on it, and purchase the artwork they like.

[0175] As described above, by using the system of the present invention, users can easily find artworks that suit their tastes and enjoy them visually in real time.

[0176] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0177] Step 1:

[0178] A user logs in to the system and enters information about their favorite art. For example, the user may specify through an input form that they like the color "blue," "Impressionism," and "Monet." The information entered includes favorite colors, art styles, favorite artists, and a history of artworks they have viewed in the past.

[0179] Input: User preferences (color, style, artist)

[0180] Output: User input is saved on the device

[0181] Step 2:

[0182] The device sends the received preference information to the server as an HTTP request. The server analyzes this request and stores the contents in a database. The stored data includes the preference information along with the user ID.

[0183] Input: User preference information

[0184] Output: Server-side preference storage

[0185] Step 3:

[0186] The server begins data analysis based on the stored preference information. Specifically, it uses generative artificial intelligence (generative AI) to analyze the preference information and extract the user's preferred features. The generative AI model used here is, for example, OpenAI GPT-3.

[0187] Input: Saved Preferences

[0188] Output: Identifying user preference patterns

[0189] Step 4:

[0190] Based on the identified preference patterns, the server activates a generative AI to generate or select from an existing database an artwork that matches the user's preferences. During this process, a prompt is input into the generative AI model. For example, a prompt such as "User A's preferences are 'blue,' 'Impressionism,' and 'Monet.' Please generate a new artwork based on these preferences" is used.

[0191] Input: User preference patterns

[0192] Output: Recommended artwork

[0193] Step 5:

[0194] The server sends the generated or selected artwork as an HTTP response to the terminal, which receives the response and displays the artwork to the user.

[0195] Input: Recommended Artwork

[0196] Output: Display of artwork on user device

[0197] Step 6:

[0198] By wearing the smart glasses, users can visually experience recommended artworks in real time. For example, when visiting a physical store, they can scan a specific area and artworks generated by the server will appear on the glasses' display.

[0199] Input: Recommended Artwork

[0200] Output: Artwork displayed on smart glasses

[0201] These are the processing steps of this system, which allows users to easily find artworks that suit their tastes and enjoy them visually in real time.

[0202] 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.

[0203] The system of the present invention recommends personalized art based on a user's preference information and emotional state, and analyzes the user's preferences and current emotional state to provide the most suitable artwork. The system includes a means for receiving and storing user preference information, a generative artificial intelligence for analyzing the data, an emotion engine, and a means for generating or selecting and providing artwork based on the analysis results.

[0204] User information acquisition

[0205] After logging in to the system, users enter their preferences. Specifically, they enter their favorite art style, favorite colors, names of artists they often watch, and so on into an input form. The system also activates an emotion engine to recognize the user's emotional state. The emotion engine obtains the user's current emotional state through facial expression analysis, voice analysis, and biometric information (such as heart rate).

[0206] User information transmission and storage

[0207] After the user inputs their preference information and the emotion engine collects their emotional data, the device compiles this data and sends it to the server. The server analyzes the received data and stores it in a database. By storing it, the user's preference information and emotional state can be referenced in future uses.

[0208] Data analysis

[0209] The server performs data analysis based on the preference information and emotional state stored in the database. This analysis uses a generative AI model to identify individual characteristics based on the user's preference patterns and current emotional state. For example, if a user likes "Impressionist" art and often likes the color "blue," but is currently feeling stressed, these factors will be taken into account when conducting the analysis.

[0210] Art recommendation generation

[0211] The server generates or selects from an existing database a suitable artwork for the user based on the preference patterns and emotional state identified by the generative AI model. The server can recommend a calming landscape painting with impressionist blue tones to help the user relax.

[0212] Return and provision of results

[0213] The server generates a list of recommended artworks and sends it to the device as an HTTP response. The device analyzes the received art recommendation list and displays it in a user-friendly format. The user can browse the recommended artworks and bookmark the ones they like. They can also click to view more detailed information.

[0214] Specific examples

[0215] As a specific example, suppose a user logs in and enters their preference information as "Impressionism," "blue color," and "frequently viewed artist: Monet." At the same time, the emotion engine analyzes the user's facial expressions and heart rate and recognizes that the user is feeling stressed. The server receives this information and generates artworks that match the user's preferences and current emotional state based on past records stored in the database and the generative AI model. For example, a recommendation list might include "serene landscapes with a Monet-esque blue theme." This list is sent to the device and displayed to the user. The user can view the recommended artworks and spend a pleasant time.

[0216] As described above, this system greatly enhances the art appreciation experience by personalizing artworks based on the user's preferences and emotional state, allowing users to easily find artworks that match their tastes and emotions and relieve daily stress.

[0217] The processing flow will be explained below.

[0218] Step 1:

[0219] A user logs into the system. The user enters their login information and, if authentication is successful, a user session begins.

[0220] Step 2:

[0221] The user enters their preferences, such as "favorite art style," "favorite color," and "frequently watched artists," into an input form.

[0222] Step 3:

[0223] The emotion engine is activated to recognize the user's emotional state in real time by analyzing the user's facial expressions, voice tone, and biometric information (e.g., heart rate).

[0224] Step 4:

[0225] The device compiles preference information and emotion data into a data structure in JSON format or similar, which is then formatted for easy analysis in subsequent processing.

[0226] Step 5:

[0227] The device sends the formatted data structure to the server as an HTTP request, which includes the user's preference information and emotion data.

[0228] Step 6:

[0229] The server analyzes the received HTTP request, extracts preference information and emotion data from the request body, and stores them in a database.

[0230] Step 7:

[0231] The server retrieves the user's preference information and emotional data stored in the database and begins analysis. Using a generative AI model, it identifies the user's preference patterns and current emotional state.

[0232] Step 8:

[0233] The generative AI model generates or selects the most suitable artwork for the user based on the identified preference patterns and emotional state. The server generates a new artwork or selects the most suitable artwork from an existing database.

[0234] Step 9:

[0235] The server compiles a list of generated or selected artworks into a recommendation list, which also includes the reason for the recommendation and related information.

[0236] Step 10:

[0237] The server sends the created recommendation list to the terminal as an HTTP response, which includes detailed information about the recommended artworks.

[0238] Step 11:

[0239] The device analyzes the HTTP response received and displays a list of recommendations in an easy-to-read format for the user.

[0240] Step 12:

[0241] Users can browse recommended artworks and bookmark their favorites. Users can also click on artworks to view additional information for more details.

[0242] Specific examples

[0243] Suppose a user logs in and enters their preferences, such as "Impressionism," "blue," and "Favorite Artist: Monet." At the same time, the emotion engine analyzes the user's facial expressions and heart rate and recognizes that the user is relaxed. The server receives this information and generates artworks that match the user's preferences and current emotional state based on past records stored in the database and the generative AI model. For example, a recommendation list might be generated that includes "serene landscapes with a Monet-esque blue theme." This list is sent to the device and displayed to the user. The user can browse these recommended artworks and spend a pleasant time.

[0244] As described above, this system greatly enhances the art appreciation experience by personalizing artworks based on the user's preferences and emotional state, allowing users to easily find artworks that match their tastes and emotions and relieve daily stress.

[0245] Example 2

[0246] 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."

[0247] Conventional art recommendation systems only consider user preference information and do not reflect the user's current emotional state, making it difficult to provide artworks that suit the user's psychological state. Furthermore, they are limited to static selection of artworks and lack the ability to generate new artworks. This makes it difficult to sufficiently increase user satisfaction.

[0248] 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.

[0249] In this invention, the server includes means for receiving user preference information, means for saving the received preference information, means for analyzing the saved preference information and the user's emotional state and identifying the preference pattern and the emotional state using a generative artificial intelligence to analyze the saved preference information and the user's emotional state, means for generating or selecting an artwork suited to the user based on the identified preference pattern and the emotional state, and means for providing the generated or selected artwork to the user, thereby making it possible to provide the optimal artwork based on the user's preferences and current emotional state.

[0250] "Preference information" refers to user-specified preferred art styles, colors, artist names, and past browsing history.

[0251] "Emotional state" is information that indicates the user's current emotional and psychological state, and is collected from facial expression analysis, voice analysis, and biometric information (heart rate, etc.).

[0252] "Generative AI" is a general term for AI technology that uses machine learning algorithms and AI models to analyze data and generate new information and objects.

[0253] "Data analysis means" refers to techniques and methods for analyzing stored preference information and emotional states to extract specific patterns and characteristics.

[0254] "Generative means" refers to the methods and techniques used to create new artworks based on the analyzed information.

[0255] "Selection method" refers to the method or technology used to select the most suitable artwork from the existing database based on the analyzed information.

[0256] "Delivery means" refers to the technology or method for visually displaying the generated or selected artwork to the user.

[0257] The system of the present invention recommends personalized art based on a user's preference information and emotional state, and provides the most suitable artwork by analyzing the user's preferences and current emotional state. The system includes a means for receiving and storing user preference information, a generative artificial intelligence for analyzing the data, an emotion engine, and a means for generating or selecting and providing artwork based on the analysis results.

[0258] Users log in to the system using their devices and enter their preferences. Specifically, they enter their art style, favorite colors, and names of artists they often visit into an input form. The system also uses an emotion engine to obtain the user's current emotional state through facial expression analysis, voice analysis, and biometric information (such as heart rate). The emotion engine includes facial expression analysis using the OpenCV library, voice analysis using the Librosa library, and real-time heart rate data collection.

[0259] The device combines the user's input preference information and the emotion data acquired by the emotion engine into a single packet and sends it to the server as an HTTP POST request. The server analyzes the received data and stores it in a database (MongoDB). The stored data is used for subsequent analysis and reference.

[0260] The server performs data analysis based on the stored preference information and emotional state. This analysis utilizes generative artificial intelligence, with a generative AI model (using TensorFlow) identifying individual characteristics based on the user's preference patterns and current emotional state. For example, if a user likes "Impressionist" art, has a history of using the color "blue," and is currently feeling stressed, these factors will be taken into account in the analysis.

[0261] Based on the analysis results, the server generates the most suitable artwork using a generative AI model or selects one from an existing database. An example of a generated prompt is, "User preference information: Impressionism, blue color, popular artists. Current emotional state: stress. Please recommend the most suitable artwork based on this."

[0262] The server generates a list of recommended artworks and sends it to the device as an HTTP response. The device analyzes the received art recommendation list and displays it on the screen in a format that is easy for the user to view. The user can view the recommended artworks and bookmark the ones they like. The user can also click to view more detailed information.

[0263] For example, suppose a user logs in and enters their preferences, such as "Impressionist," "blue," and "frequently viewed artists." At the same time, the emotion engine analyzes the user's facial expressions and heart rate and recognizes that the user is feeling stressed. The server receives this information and, based on past records stored in the database and the generative AI model, generates artworks that match the user's preferences and current emotional state. For example, a recommendation list might include "serene landscape paintings with blue Impressionist tones." This list is sent to the device and displayed to the user. The user can browse these recommended artworks and spend a pleasant time.

[0264] As described above, this system significantly improves the art appreciation experience by personalizing artworks based on the user's preferences and emotional state, allowing users to easily find artworks that match their tastes and emotions, helping to relieve everyday stress.

[0265] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0266] Step 1: Obtain user information

[0267] Users log in to the system and enter their preferences, such as their favorite art style, favorite colors, and the names of artists they often visit, into an input form. This input form is web-based, and the data entered by the user is sent to the device in JSON format. The device then uses its camera and microphone to activate the emotion engine. The emotion engine uses OpenCV to analyze the user's facial expressions and Librosa to analyze audio data. Biometric information, such as heart rate, is also collected in real time from the smartwatch. All of this data is compiled into emotional state data.

[0268] Input: User preference information (art style, color, artist name), facial expression data, voice data, biometric information

[0269] Output: Analyzed preference information and emotional state data

[0270] Step 2: Send and save user information

[0271] The device combines the user's input preferences and the emotional state data collected by the emotion engine into a single JSON packet. The combined data is then sent to the server as an HTTP POST request. The server receives the data and performs initial analysis using the Pandas library. The data is then stored in MongoDB, where it can be retained for future reference and analysis.

[0272] Input: A JSON packet containing preference information and emotional state data

[0273] Output: Parsed data stored in a database

[0274] Step 3: Data analysis

[0275] The server references the user's preference information and emotional state data stored in MongoDB and performs data analysis. A generative AI model is used for the analysis, using the TensorFlow library. The generative AI model uses this data to identify the user's preference patterns and current emotional state. For example, if a user likes "Impressionist" art, values ​​the color "blue," and is currently feeling stressed, the model combines these factors to perform an analysis.

[0276] Input: Preference information and emotional state data stored in a database

[0277] Output: Analysis results based on user preference patterns and emotional state

[0278] Step 4: Art recommendation generation

[0279] Based on the analysis results, the server uses a generative AI model to generate the most suitable artwork or select one from an existing database. An example of a generated prompt is, "User's preferences: Impressionism, blue, popular artists. Current emotional state: stress. Please recommend the most suitable artwork based on this." This generates or selects the artwork that best suits the user's preferences and emotional state.

[0280] Input: Analysis results of user preference patterns and emotional state

[0281] Output: A list of recommended artworks

[0282] Step 5: Return and provide results

[0283] The server generates a list of recommended artworks in JSON format and sends it to the device as an HTTP response. The device parses the received JSON data and displays it in a user-friendly format on the web browser. The user can browse the recommended artworks and bookmark their favorites. They can also click to view detailed information. This allows users to easily find artworks that match their tastes and emotional state.

[0284] Input: JSON data containing a list of recommended artworks

[0285] Output: A list of artworks visually displayed to the user

[0286] (Application example 2)

[0287] 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."

[0288] In modern society, it is difficult to select meals that match the individual preferences and emotional state of users, so methods to improve user satisfaction are required in food delivery services.In addition, because there are few personalized meal suggestions that reflect the user's preferences and emotional state, there is a lack of services that meet the needs of users, such as relaxation and health improvement, especially in stressful environments.

[0289] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving user preference information, means for saving the received preference information, data analysis means using generative artificial intelligence to analyze the saved preference information and emotional state and identify the user's preference pattern and emotional state, means for generating or selecting a meal suited to the user based on the identified preference pattern and emotional state, and means for providing the generated or selected meal to the user. This makes it possible to provide meals that suit the user's individual preferences and emotional state, which is expected to not only improve user satisfaction but also have effects such as maintaining health and reducing stress.

[0290] "Preference information" is information about the preferences of individual users, such as the user's favorite cuisine genres, specific ingredients, and the history of meals ordered in the past.

[0291] "Emotional state" refers to the user's current psychological or physiological state, and is information obtained through facial expression analysis, voice analysis, and biometric information (such as heart rate).

[0292] "Generative AI" is an AI that analyzes the user's preference patterns and emotional state based on the received data and generates new meal menus.

[0293] The "data analysis means" is a means for performing analysis based on the preference information and emotional state received from the user, and for suggesting the most suitable meal for the user.

[0294] A "meal generation or selection means" is a means for using artificial intelligence to generate a meal menu tailored to the user based on the identified preference patterns and emotional state, or for selecting from an existing menu.

[0295] "Means for storing" refers to means for storing the received user preference information and emotional state in a database for future use.

[0296] The "means for providing" is a means for transmitting the generated or selected meal menu to the user's terminal and displaying it.

[0297] The system of the present invention recommends personalized meals based on a user's preference information and emotional state. To provide optimal meal menus by analyzing a user's preferences and current emotional state, the system operates as follows: Specifically, the system includes the steps of acquiring user information, transmitting and saving data, analyzing the data, generating meal recommendations, and returning and providing the results.

[0298] User information acquisition

[0299] After logging in to the system, the user enters their preference information. Specifically, the user enters their preferred cuisine genre (e.g., Italian, Japanese, Chinese, etc.), specific ingredients, and past meal ordering history into an input form. The system also activates an emotion engine to recognize the user's emotional state. The emotion engine obtains the user's current emotional state through facial expression analysis using the smartphone camera, voice analysis using the microphone, and biometric information (heart rate, etc.) using a wearable device.

[0300] Data transmission and storage

[0301] After the user inputs their preference information and the emotion engine collects their emotional data, the device compiles this data and sends it to the server. The server analyzes the received data and stores it in a database. By storing it, the user's preference information and emotional state can be referenced in future uses.

[0302] Data analysis

[0303] The server performs data analysis based on the preference information and emotional state stored in the database. This analysis uses a generative AI model to identify individual characteristics based on the user's preference patterns and emotional state. For example, if a user likes Italian food, has a history of ordering a lot of pasta dishes in the past, and is currently feeling stressed, the analysis will take these factors into account.

[0304] Food recommendation generation

[0305] The server generates or selects from an existing database a meal plan tailored to the user based on the preference patterns and emotional state identified by the generative AI model. The server can recommend healthy Italian dishes or menus containing ingredients with stress-reducing properties to help the user relax.

[0306] Return and provision of results

[0307] The server generates a list of recommended food menus and sends it to the device as an HTTP response. The device analyzes the received food recommendation list and displays it in a user-friendly format. The user can browse the recommended menus and order the meals they like.

[0308] Examples and prompts

[0309] As a specific example, suppose a user logs in and enters their preference information as "Italian," "Pasta," and "Previously ordered menu: Carbonara." At the same time, the emotion engine analyzes the user's facial expressions and heart rate and recognizes that the user is feeling stressed. The server receives this information and generates a meal menu that matches the user's preferences and current emotional state based on past records stored in the database and the generative AI model. For example, a recommendation list of "Carbonara-style pasta served with relaxing herbal tea" is generated. This list is sent to the device and displayed to the user. The user can view the recommended menu and place an order.

[0310] Example prompt sentence:

[0311] "User's favorite dishes: pasta, salad. Current emotional state: stress. Generate a healthy and relaxing menu."

[0312] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0313] Step 1: Enter your user information

[0314] Input: A user logs into the application and enters their preferences (e.g., favorite cuisines, specific ingredients, past orders, etc.).

[0315] How it works: The device receives preference information through an input form and temporarily stores it.

[0316] Output: Preference information is saved on the device.

[0317] Step 2: Obtaining emotional states

[0318] Input: User's facial expressions, voice, and biometric information (heart rate, etc.).

[0319] How it works: The device captures facial expressions with a built-in camera and analyzes them using the emotion engine. It also records audio with a microphone and acquires biometric information from the wearable device.

[0320] Output: Emotional state data analyzed on the device.

[0321] Step 3: Sending data

[0322] Input: Stored preference information and retrieved emotional state data.

[0323] Operation: The device sends this data to the server.

[0324] Output: Preference information and emotional state data are sent to the server.

[0325] Step 4: Save your data

[0326] Input: Preference information and emotional state data sent to the server.

[0327] How it works: The server stores the received data persistently in a database.

[0328] Output: Preference information and emotional state data stored in a database.

[0329] Step 5: Analyze the data

[0330] Input: Preference information and emotional state data stored in a database.

[0331] How it works: The server uses a generative AI model to analyze preference patterns and emotional states. For example, if a user likes Italian food and is feeling stressed, it makes a calculation based on this information.

[0332] Output: Analysis results based on preference patterns and emotional states.

[0333] Step 6: Generate or select a meal menu

[0334] Input: Analysis of preference patterns and emotional states.

[0335] How it works: Based on the analysis results, the server uses a generative AI model to generate a new meal menu or select the best option from an existing menu.

[0336] Output: A list of recommended meals is generated.

[0337] Step 7: Returning the results

[0338] Input: A list of recommended meals.

[0339] Operation: The server sends the generated recommended menu list to the terminal as an HTTP response.

[0340] Output: A list of recommended meals is sent to the device.

[0341] Step 8: Viewing the results

[0342] Input: A list of recommended meals.

[0343] How it works: The device analyzes the received meal recommendation list and displays it in an easy-to-read format for the user.

[0344] Output: The user can view a list of recommended meals.

[0345] Step 9: Complete your order

[0346] Input: The meal selected by the user.

[0347] Operation: The user selects the menu item they like and completes the order. The terminal sends the order information to the server.

[0348] Output: The order information is sent to the server and the order is received.

[0349] These steps allow users to easily select and order the meal that best suits their tastes and emotional state.

[0350] 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.

[0351] 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.

[0352] 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.

[0353] [Second embodiment]

[0354] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0355] 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.

[0356] 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).

[0357] 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.

[0358] 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.

[0359] 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).

[0360] 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.

[0361] 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.

[0362] 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.

[0363] 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.

[0364] 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.

[0365] 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."

[0366] The system of the present invention is for recommending personalized art based on a user's preferences, and includes a series of steps for analyzing the user's preferences and generating or selecting and providing artworks based on the preferences. The program processing of the system is described in detail below.

[0367] Program Overview

[0368] This system is an online platform that receives input from users' devices, analyzes that information on the server side, and uses generative AI to recommend personalized art, allowing users to easily discover and appreciate artworks that suit their tastes.

[0369] User information acquisition

[0370] After logging in to the system, a user enters their art preferences. Specifically, the user enters their favorite colors, favorite art styles, favorite artists, artworks they have viewed in the past, etc. through an input form. For example, suppose a user enters that they like "Impressionism" and that "blue" is their favorite color.

[0371] User information transmission

[0372] Once the input is complete, the device collects this preference information and sends it to the server as an HTTP request. The server receives this request and proceeds to the next processing step.

[0373] Saving user information

[0374] The server analyzes the received preference information and stores it in a database, so that the user does not have to re-enter it when they use the system again in the future.

[0375] Data analysis

[0376] The server then begins analyzing the data to identify the user's preferences based on the stored preference information. Specifically, it uses generative AI to analyze the preference information and extract the user's preferred characteristics. These characteristics are based on patterns, such as "the user likes impressionist art, and particularly prefers blue artworks."

[0377] Art recommendation generation

[0378] Based on the results of the data analysis, the server activates the AI ​​to generate artwork that matches the user's preferences or select artwork from an existing database. For example, if the user likes the color blue, the AI ​​will generate impressionist artwork that contains a lot of blue.

[0379] Returning the results

[0380] The server sends the generated art recommendation list to the device as an HTTP response. The device receives the list and displays appropriate artworks for the user. The user can click on the recommended artworks to view more information or bookmark their favorite artworks.

[0381] Specific examples

[0382] As a specific example, suppose a user logs in and enters preference information such as "Impressionism," "blue," and "Monet." The server receives this data, stores it in a database, and uses generative AI to generate impressionist art with a blue base that matches the user's preferences. As a result, the server generates a recommended list such as "a new artwork depicting a Monet-esque blue water surface," and sends it back to the user's device. The user can browse this list and find their favorite works.

[0383] As described above, this system significantly improves the user's art appreciation experience, allowing everyone to easily find art that suits their tastes.

[0384] The processing flow will be explained below.

[0385] Step 1:

[0386] A user logs into the system. The user enters their login information and, if authentication is successful, a user session begins.

[0387] Step 2:

[0388] The user enters their preferences, including their favorite art style, favorite colors, and names of artists they often watch, into an input form.

[0389] Step 3:

[0390] The device collects the input preference information and organizes it into a data structure, such as JSON, which is formatted for easy analysis later.

[0391] Step 4:

[0392] The device sends the formatted data structure to the server as an HTTP request, which includes the user's preference information.

[0393] Step 5:

[0394] The server parses the received HTTP request, extracts the preference information from the request body, and stores it in a database in an appropriate format.

[0395] Step 6:

[0396] The server retrieves the user's preference information stored in the database and begins analysis, using a generative AI model to analyze the data to identify user preference patterns.

[0397] Step 7:

[0398] A generative AI model generates new artworks based on identified preference patterns, or selects artworks from an existing database that match the user's preferences.

[0399] Step 8:

[0400] The server compiles a list of generated or selected artworks into a recommendation list, which also includes the reason for the recommendation and related information.

[0401] Step 9:

[0402] The server sends the created recommendation list to the terminal as an HTTP response, which also includes detailed information about the recommended artworks.

[0403] Step 10:

[0404] The device analyzes the received HTTP response, extracts the recommendation list, and displays it in a user-friendly format.

[0405] Step 11:

[0406] Users can browse recommended artworks and bookmark their favorites. Users can also click on artworks to get more detailed information.

[0407] Example 1

[0408] 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."

[0409] Conventional art recommendation systems have struggled to provide personalized artworks that fully reflect a user's preferences. As a result, users are unable to efficiently find artworks that interest them, resulting in an unsatisfactory art appreciation experience. Furthermore, users must re-enter their preference information each time they use the system, which is inconvenient.

[0410] 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.

[0411] In this invention, the server includes a means for receiving user preference information, a means for storing the received preference information, and a data analysis means for analyzing the stored preference information and using artificial intelligence to identify the user's preference patterns. This enables personalized recommendations of artworks based on the user's preferences. Furthermore, by including a means for transmitting the generated art recommendation list to the terminal as an HTTP response, which the terminal receives and displays to the user, the user can easily find artworks that suit their preferences, eliminating the need for re-entry when using the system again, improving convenience.

[0412] "Preference information" is information that indicates the user's preferences, such as the user's favorite colors, favorite art styles, favorite artists, and the history of artworks that the user has viewed in the past.

[0413] The "receiving means" is a function or device for receiving preference information input by a user via a network.

[0414] The "storing means" is a function or device for storing the received preference information in a database or storage.

[0415] The "data analysis means" is a function or device that analyzes the stored preference information and identifies the user's preference patterns, and is the part that uses generative artificial intelligence.

[0416] "Generative AI" is software or a system that has the ability to generate new artworks using specific rules and algorithms based on user preferences.

[0417] The "means for identifying" is a function or device for extracting and clarifying a user's preference patterns through data analysis.

[0418] A "generative means" is a function or device for creating new artworks using generative artificial intelligence.

[0419] The "selection means" is a function or device for selecting artworks that match the user's preferences from an existing database.

[0420] The "means for providing" is a function or device for transmitting the generated or selected artwork to the user's terminal and displaying it.

[0421] A "terminal" is a device such as a computer, smartphone, or tablet that a user uses to input preference information and view provided artworks.

[0422] An "HTTP request" is a type of web protocol that allows a user's device to send information to a server.

[0423] An "HTTP response" is a type of web protocol that allows a server to return information to a user's device.

[0424] A "database" is a storage system that stores received preference information for later retrieval and analysis.

[0425] A "recommendation list" is a generated or selected list of artworks that is provided to a user.

[0426] The system according to the present invention is for recommending personalized art based on a user's preferences, and includes a series of steps for analyzing the user's preferences and generating or selecting and providing artwork based on the user's preferences. Specific embodiments of the system are described in detail below.

[0427] User information acquisition

[0428] A user first logs in to the system. After logging in, the user enters their art-related preference information. This information includes favorite colors, favorite art styles, favorite artists, and a history of artworks they have viewed in the past. As a specific example, consider the case where a user enters preference information such as "Impressionism," "blue," and "Monet."

[0429] User information transmission

[0430] Once the user has completed entering their preference information, the device sends this information to the server. The HTTP protocol is used for transmission, and the request is in JSON format. For example, the device sends the preference information as an HTTP request "POST / api / preferences".

[0431] Saving user information

[0432] The server analyzes the received preference information and stores it in a database (e.g., MySQL or MongoDB). The received JSON data is parsed and stored in an appropriate format.

[0433] Data analysis

[0434] The server then begins data analysis to identify the user's preferences based on the preference information stored in the database. In this step, the data is analyzed using programming languages ​​such as Python and R, and generative artificial intelligence (e.g., GPT-4) is utilized. Through this analysis, the user's preference patterns are extracted, and characteristics such as "the user likes impressionist art, and particularly prefers blue works" are identified.

[0435] Art recommendation generation

[0436] Based on the results of the data analysis, the server launches a generative AI model to generate artwork that matches the user's preferences, or selects suitable artwork from an existing database. For example, a Python script can be used to send a prompt to the generative AI model, such as, "The user likes impressionist artwork and is particularly fond of the color blue. Please generate a new artwork based on these conditions."

[0437] Returning the results

[0438] The server sends the generated art recommendation list to the device as an HTTP response. The device receives this response and displays appropriate art works to the user. The display is visually organized using HTML and CSS, making it easy for the user to browse.

[0439] User art appreciation

[0440] Users can click on artworks displayed on their devices to view detailed information or bookmark artworks they like. Specifically, users can click on the thumbnail of a displayed artwork to go to the details page where they can view a description of the artwork and information about the artist. They can also use the bookmark function to easily find their favorite artworks later.

[0441] Specific examples

[0442] The user logs in and enters preference information such as "Impressionist," "blue," and "Monet." The user's device then sends the preference information to the server via an HTTP request. The server stores this data in a database and sends a prompt to the generative AI model: "The user likes Impressionist artwork, and is particularly fond of the color blue. Please generate a new artwork based on these conditions." This generates an Impressionist artwork with a blue base. The server then compiles these artworks into a list and sends it back to the user's device. The user can then browse the displayed list of artworks, check detailed information, and bookmark artworks.

[0443] As described above, this system significantly improves the user's art appreciation experience, allowing everyone to easily find art that suits their tastes.

[0444] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0445] Step 1: Enter your user information

[0446] The user logs in to the system. After logging in, the user enters their preference information through an input form. The information entered includes favorite colors, favorite art styles, favorite artists, and a history of artworks viewed in the past. Specific examples of input include preference information such as "Impressionism," "blue," and "Monet." This input becomes the initial data for the system.

[0447] Input: User preferences (favorite colors, art styles, artists, etc.)

[0448] Output: Input preference information

[0449] Step 2: Submit user information

[0450] When the user has finished entering their preference information, the device compiles this information and sends it to the server as an HTTP request. The request uses the POST method, and data is sent in JSON format. Specifically, the device sends a request to the endpoint "POST / api / preferences".

[0451] Input: User-entered preferences

[0452] Output: HTTP request for preferences sent to the server

[0453] Step 3: Save user information

[0454] The server analyzes the received preference information and stores it in a database (e.g., MySQL or MongoDB). The received JSON data is parsed, converted into an appropriate format, and then stored in the database. This allows the user's preference information to be stored in a reusable format.

[0455] Input: HTTP request for preference information sent to the server

[0456] Output: User preferences stored in a database

[0457] Step 4: Data analysis

[0458] The server analyzes the data to identify the user's preferences based on the preference information stored in the database. Specifically, it uses programming languages ​​such as Python and R and generative artificial intelligence (e.g., GPT-4) to analyze the preference information. As feedback, it extracts specific patterns, such as the user's "I like impressionist paintings, and I particularly like blue works."

[0459] Input: User preferences stored in a database

[0460] Output: User preference pattern (e.g., "I like impressionist art, and I especially like blue artworks")

[0461] Step 5: Art recommendation generation

[0462] The server then launches a generative AI model based on the data analysis results to generate artwork that matches the user's preferences, or selects a suitable artwork from an existing database. Specifically, the server sends the generative AI model a prompt such as, "The user likes impressionist artwork, and is particularly fond of the color blue. Please generate a new artwork based on these conditions."

[0463] Input: User preference patterns

[0464] Output: Generated artwork or selected existing artwork

[0465] Step 6: Returning the results

[0466] The server sends the generated art recommendation list to the device as an HTTP response. The sent data is in JSON format and is structured to display appropriate art works to the user. The display is visually organized using HTML and CSS.

[0467] Input: Generated artwork or selected existing artwork

[0468] Output: Art recommendation list sent to user device (HTTP response)

[0469] Step 7: User Art Appreciation

[0470] Users can click on artworks displayed on their devices to view detailed information. They can also bookmark artworks they like. Specifically, users can click on a thumbnail of a displayed artwork to move to a detailed page where they can view a description of the artwork and information about the artist. Viewing and bookmarking operations are performed based on this information.

[0471] Input: Art recommendation list sent to user device

[0472] Output: User can view details of artwork and bookmark it

[0473] Through the above steps, a personalized art recommendation system based on the user's preferences is realized.

[0474] (Application example 1)

[0475] 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."

[0476] In today's brick-and-mortar stores, it is difficult to efficiently and effectively present artworks that match the tastes of visitors. This can result in missed opportunities to capture visitors' interest and lower satisfaction. Furthermore, while there is a demand for providing personalized experiences based on the preferences of each individual visitor, there is a lack of suitable means to achieve this.

[0477] 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.

[0478] In this invention, the server includes means for receiving user preference information, means for storing the received preference information, means for analyzing the stored preference information and using artificial intelligence to identify the user's preference pattern, means for generating or selecting an artwork suited to the user based on the identified preference pattern, means for providing the generated or selected artwork to the user, and means for visually presenting the artwork on a user-dedicated display device, thereby enabling visitors to experience artwork suited to their preferences in real time at a physical store.

[0479] The "means for receiving user preference information" refers to an interface for obtaining information about a user's preferences regarding art.

[0480] The "means for storing received preference information" refers to a database or storage system for storing acquired user preference information for a long period of time.

[0481] "Generative AI-based data analysis means" refers to a process that uses artificial intelligence techniques to analyze received and stored preference information and identify user preference patterns.

[0482] "Means for generating or selecting artwork" refers to a function for generating a new artwork based on the user's preferences or selecting an appropriate artwork from existing artworks.

[0483] "Means for providing generated or selected artwork" refers to a method or system for presenting generated or selected artwork to a user.

[0484] "User-only display device" refers to a device that visually presents artwork to a user only.

[0485] "Smart glasses" refers to a glasses-type device that has the function of visually displaying information when worn by a user.

[0486] The system for implementing the present invention includes a series of functions for receiving user preference information and recommending personalized art based on the information. The program processing of the system is described in detail below.

[0487] User information acquisition

[0488] First, a user logs in to the system and inputs their preferences regarding art. Specifically, the user inputs their favorite color, favorite art style, favorite artist, artworks they have viewed in the past, etc. through an input form. For example, a user may input that they like "Impressionism" and "the color blue," and that they like "Monet."

[0489] User information transmission

[0490] The terminal collects the input preference information and sends it to the server as an HTTP request. The server receives this request and proceeds to the next processing step.

[0491] Saving user information

[0492] The server analyzes the received preference information and stores it in a database, which saves the user the trouble of having to re-enter the information when they use the system again in the future.

[0493] Data analysis

[0494] The server then begins data analysis to identify the user's preferences based on the stored preference information. Specifically, it uses generative artificial intelligence (generative AI) to analyze the preference information and extract the user's preferred features. This generative AI uses a generative AI model such as OpenAI GPT-3.

[0495] Art recommendation generation

[0496] Based on the results of the data analysis, the server activates the AI ​​to generate artwork that matches the user's preferences or select artwork from an existing database. For example, if the user likes the color blue, the AI ​​will generate impressionist artwork that contains a lot of blue.

[0497] Returning the results

[0498] The server sends the generated or selected art recommendation list to the terminal as an HTTP response. The terminal receives the list and displays appropriate artworks to the user. The user can click on the recommended artworks to view detailed information or bookmark their favorite artworks.

[0499] User-specific display device

[0500] Users can visually experience recommended artworks in real time using a user-specific display device, including smart glasses. For example, when visiting a physical store, a user wearing smart glasses scans a specific area, and artworks generated by the server are displayed on the glasses' display.

[0501] Specific examples

[0502] As a concrete example, suppose a user logs in and enters preferences such as "Impressionist," "blue," and "Monet." The server analyzes this data and feeds the generative AI model the following prompt:

[0503] "User A's preferences are 'blue,' 'Impressionism,' and 'Monet.' Generate a new artwork based on these preferences."

[0504] Based on this prompt, the AI ​​will generate a "new artwork depicting a Monet-esque blue water surface," and the server will send this recommendation to the user's smart glasses. The user can then view the artwork in real time through the glasses, obtain more information on it, and purchase the artwork they like.

[0505] As described above, by using the system of the present invention, users can easily find artworks that suit their tastes and enjoy them visually in real time.

[0506] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0507] Step 1:

[0508] A user logs in to the system and enters information about their favorite art. For example, the user may specify through an input form that they like the color "blue," "Impressionism," and "Monet." The information entered includes favorite colors, art styles, favorite artists, and a history of artworks they have viewed in the past.

[0509] Input: User preferences (color, style, artist)

[0510] Output: User input is saved on the device

[0511] Step 2:

[0512] The device sends the received preference information to the server as an HTTP request. The server analyzes this request and stores the contents in a database. The stored data includes the preference information along with the user ID.

[0513] Input: User preference information

[0514] Output: Server-side preference storage

[0515] Step 3:

[0516] The server begins data analysis based on the stored preference information. Specifically, it uses generative artificial intelligence (generative AI) to analyze the preference information and extract the user's preferred features. The generative AI model used here is, for example, OpenAI GPT-3.

[0517] Input: Saved Preferences

[0518] Output: Identifying user preference patterns

[0519] Step 4:

[0520] Based on the identified preference patterns, the server activates a generative AI to generate or select from an existing database an artwork that matches the user's preferences. During this process, a prompt is input into the generative AI model. For example, a prompt such as "User A's preferences are 'blue,' 'Impressionism,' and 'Monet.' Please generate a new artwork based on these preferences" is used.

[0521] Input: User preference patterns

[0522] Output: Recommended artwork

[0523] Step 5:

[0524] The server sends the generated or selected artwork as an HTTP response to the terminal, which receives the response and displays the artwork to the user.

[0525] Input: Recommended Artwork

[0526] Output: Display of artwork on user device

[0527] Step 6:

[0528] By wearing the smart glasses, users can visually experience recommended artworks in real time. For example, when visiting a physical store, they can scan a specific area and artworks generated by the server will appear on the glasses' display.

[0529] Input: Recommended Artwork

[0530] Output: Artwork displayed on smart glasses

[0531] These are the processing steps of this system, which allows users to easily find artworks that suit their tastes and enjoy them visually in real time.

[0532] 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.

[0533] The system of the present invention recommends personalized art based on a user's preference information and emotional state, and analyzes the user's preferences and current emotional state to provide the most suitable artwork. The system includes a means for receiving and storing user preference information, a generative artificial intelligence for analyzing the data, an emotion engine, and a means for generating or selecting and providing artwork based on the analysis results.

[0534] User information acquisition

[0535] After logging in to the system, users enter their preferences. Specifically, they enter their favorite art style, favorite colors, names of artists they often watch, and so on into an input form. The system also activates an emotion engine to recognize the user's emotional state. The emotion engine obtains the user's current emotional state through facial expression analysis, voice analysis, and biometric information (such as heart rate).

[0536] User information transmission and storage

[0537] After the user inputs their preference information and the emotion engine collects their emotional data, the device compiles this data and sends it to the server. The server analyzes the received data and stores it in a database. By storing it, the user's preference information and emotional state can be referenced in future uses.

[0538] Data analysis

[0539] The server performs data analysis based on the preference information and emotional state stored in the database. This analysis uses a generative AI model to identify individual characteristics based on the user's preference patterns and current emotional state. For example, if a user likes "Impressionist" art and often likes the color "blue," but is currently feeling stressed, these factors will be taken into account when conducting the analysis.

[0540] Art recommendation generation

[0541] The server generates or selects from an existing database a suitable artwork for the user based on the preference patterns and emotional state identified by the generative AI model. The server can recommend a calming landscape painting with impressionist blue tones to help the user relax.

[0542] Return and provision of results

[0543] The server generates a list of recommended artworks and sends it to the device as an HTTP response. The device analyzes the received art recommendation list and displays it in a user-friendly format. The user can browse the recommended artworks and bookmark the ones they like. They can also click to view more detailed information.

[0544] Specific examples

[0545] As a specific example, suppose a user logs in and enters their preference information as "Impressionism," "blue color," and "frequently viewed artist: Monet." At the same time, the emotion engine analyzes the user's facial expressions and heart rate and recognizes that the user is feeling stressed. The server receives this information and generates artworks that match the user's preferences and current emotional state based on past records stored in the database and the generative AI model. For example, a recommendation list might include "serene landscapes with a Monet-esque blue theme." This list is sent to the device and displayed to the user. The user can view the recommended artworks and spend a pleasant time.

[0546] As described above, this system greatly enhances the art appreciation experience by personalizing artworks based on the user's preferences and emotional state, allowing users to easily find artworks that match their tastes and emotions and relieve daily stress.

[0547] The processing flow will be explained below.

[0548] Step 1:

[0549] A user logs into the system. The user enters their login information and, if authentication is successful, a user session begins.

[0550] Step 2:

[0551] The user enters their preferences, such as "favorite art style," "favorite color," and "frequently watched artists," into an input form.

[0552] Step 3:

[0553] The emotion engine is activated to recognize the user's emotional state in real time by analyzing the user's facial expressions, voice tone, and biometric information (e.g., heart rate).

[0554] Step 4:

[0555] The device compiles preference information and emotion data into a data structure in JSON format or similar, which is then formatted for easy analysis in subsequent processing.

[0556] Step 5:

[0557] The device sends the formatted data structure to the server as an HTTP request, which includes the user's preference information and emotion data.

[0558] Step 6:

[0559] The server analyzes the received HTTP request, extracts preference information and emotion data from the request body, and stores them in a database.

[0560] Step 7:

[0561] The server retrieves the user's preference information and emotional data stored in the database and begins analysis. Using a generative AI model, it identifies the user's preference patterns and current emotional state.

[0562] Step 8:

[0563] The generative AI model generates or selects the most suitable artwork for the user based on the identified preference patterns and emotional state. The server generates a new artwork or selects the most suitable artwork from an existing database.

[0564] Step 9:

[0565] The server compiles a list of generated or selected artworks into a recommendation list, which also includes the reason for the recommendation and related information.

[0566] Step 10:

[0567] The server sends the created recommendation list to the terminal as an HTTP response, which includes detailed information about the recommended artworks.

[0568] Step 11:

[0569] The device analyzes the HTTP response received and displays a list of recommendations in an easy-to-read format for the user.

[0570] Step 12:

[0571] Users can browse recommended artworks and bookmark their favorites. Users can also click on artworks to view additional information for more details.

[0572] Specific examples

[0573] Suppose a user logs in and enters their preferences, such as "Impressionism," "blue," and "Favorite Artist: Monet." At the same time, the emotion engine analyzes the user's facial expressions and heart rate and recognizes that the user is relaxed. The server receives this information and generates artworks that match the user's preferences and current emotional state based on past records stored in the database and the generative AI model. For example, a recommendation list might be generated that includes "serene landscapes with a Monet-esque blue theme." This list is sent to the device and displayed to the user. The user can browse these recommended artworks and spend a pleasant time.

[0574] As described above, this system greatly enhances the art appreciation experience by personalizing artworks based on the user's preferences and emotional state, allowing users to easily find artworks that match their tastes and emotions and relieve daily stress.

[0575] Example 2

[0576] 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."

[0577] Conventional art recommendation systems only consider user preference information and do not reflect the user's current emotional state, making it difficult to provide artworks that suit the user's psychological state. Furthermore, they are limited to static selection of artworks and lack the ability to generate new artworks. This makes it difficult to sufficiently increase user satisfaction.

[0578] 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.

[0579] In this invention, the server includes means for receiving user preference information, means for saving the received preference information, means for analyzing the saved preference information and the user's emotional state and identifying the preference pattern and the emotional state using a generative artificial intelligence to analyze the saved preference information and the user's emotional state, means for generating or selecting an artwork suited to the user based on the identified preference pattern and the emotional state, and means for providing the generated or selected artwork to the user, thereby making it possible to provide the optimal artwork based on the user's preferences and current emotional state.

[0580] "Preference information" refers to user-specified preferred art styles, colors, artist names, and past browsing history.

[0581] "Emotional state" is information that indicates the user's current emotional and psychological state, and is collected from facial expression analysis, voice analysis, and biometric information (heart rate, etc.).

[0582] "Generative AI" is a general term for AI technology that uses machine learning algorithms and AI models to analyze data and generate new information and objects.

[0583] "Data analysis means" refers to techniques and methods for analyzing stored preference information and emotional states to extract specific patterns and characteristics.

[0584] "Generative means" refers to the methods and techniques used to create new artworks based on the analyzed information.

[0585] "Selection method" refers to the method or technology used to select the most suitable artwork from the existing database based on the analyzed information.

[0586] "Delivery means" refers to the technology or method for visually displaying the generated or selected artwork to the user.

[0587] The system of the present invention recommends personalized art based on a user's preference information and emotional state, and provides the most suitable artwork by analyzing the user's preferences and current emotional state. The system includes a means for receiving and storing user preference information, a generative artificial intelligence for analyzing the data, an emotion engine, and a means for generating or selecting and providing artwork based on the analysis results.

[0588] Users log in to the system using their devices and enter their preferences. Specifically, they enter their art style, favorite colors, and names of artists they often visit into an input form. The system also uses an emotion engine to obtain the user's current emotional state through facial expression analysis, voice analysis, and biometric information (such as heart rate). The emotion engine includes facial expression analysis using the OpenCV library, voice analysis using the Librosa library, and real-time heart rate data collection.

[0589] The device combines the user's input preference information and the emotion data acquired by the emotion engine into a single packet and sends it to the server as an HTTP POST request. The server analyzes the received data and stores it in a database (MongoDB). The stored data is used for subsequent analysis and reference.

[0590] The server performs data analysis based on the stored preference information and emotional state. This analysis utilizes generative artificial intelligence, with a generative AI model (using TensorFlow) identifying individual characteristics based on the user's preference patterns and current emotional state. For example, if a user likes "Impressionist" art, has a history of using the color "blue," and is currently feeling stressed, these factors will be taken into account in the analysis.

[0591] Based on the analysis results, the server generates the most suitable artwork using a generative AI model or selects one from an existing database. An example of a generated prompt is, "User preference information: Impressionism, blue color, popular artists. Current emotional state: stress. Please recommend the most suitable artwork based on this."

[0592] The server generates a list of recommended artworks and sends it to the device as an HTTP response. The device analyzes the received art recommendation list and displays it on the screen in a format that is easy for the user to view. The user can view the recommended artworks and bookmark the ones they like. The user can also click to view more detailed information.

[0593] For example, suppose a user logs in and enters their preferences, such as "Impressionist," "blue," and "frequently viewed artists." At the same time, the emotion engine analyzes the user's facial expressions and heart rate and recognizes that the user is feeling stressed. The server receives this information and, based on past records stored in the database and the generative AI model, generates artworks that match the user's preferences and current emotional state. For example, a recommendation list might include "serene landscape paintings with blue Impressionist tones." This list is sent to the device and displayed to the user. The user can browse these recommended artworks and spend a pleasant time.

[0594] As described above, this system significantly improves the art appreciation experience by personalizing artworks based on the user's preferences and emotional state, allowing users to easily find artworks that match their tastes and emotions, helping to relieve everyday stress.

[0595] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0596] Step 1: Obtain user information

[0597] Users log in to the system and enter their preferences, such as their favorite art style, favorite colors, and the names of artists they often visit, into an input form. This input form is web-based, and the data entered by the user is sent to the device in JSON format. The device then uses its camera and microphone to activate the emotion engine. The emotion engine uses OpenCV to analyze the user's facial expressions and Librosa to analyze audio data. Biometric information, such as heart rate, is also collected in real time from the smartwatch. All of this data is compiled into emotional state data.

[0598] Input: User preference information (art style, color, artist name), facial expression data, voice data, biometric information

[0599] Output: Analyzed preference information and emotional state data

[0600] Step 2: Send and save user information

[0601] The device combines the user's input preferences and the emotional state data collected by the emotion engine into a single JSON packet. The combined data is then sent to the server as an HTTP POST request. The server receives the data and performs initial analysis using the Pandas library. The data is then stored in MongoDB, where it can be retained for future reference and analysis.

[0602] Input: A JSON packet containing preference information and emotional state data

[0603] Output: Parsed data stored in a database

[0604] Step 3: Data analysis

[0605] The server references the user's preference information and emotional state data stored in MongoDB and performs data analysis. A generative AI model is used for the analysis, using the TensorFlow library. The generative AI model uses this data to identify the user's preference patterns and current emotional state. For example, if a user likes "Impressionist" art, values ​​the color "blue," and is currently feeling stressed, the model combines these factors to perform an analysis.

[0606] Input: Preference information and emotional state data stored in a database

[0607] Output: Analysis results based on user preference patterns and emotional state

[0608] Step 4: Art recommendation generation

[0609] Based on the analysis results, the server uses a generative AI model to generate the most suitable artwork or select one from an existing database. An example of a generated prompt is, "User's preferences: Impressionism, blue, popular artists. Current emotional state: stress. Please recommend the most suitable artwork based on this." This generates or selects the artwork that best suits the user's preferences and emotional state.

[0610] Input: Analysis results of user preference patterns and emotional state

[0611] Output: A list of recommended artworks

[0612] Step 5: Return and provide results

[0613] The server generates a list of recommended artworks in JSON format and sends it to the device as an HTTP response. The device parses the received JSON data and displays it in a user-friendly format on the web browser. The user can browse the recommended artworks and bookmark their favorites. They can also click to view detailed information. This allows users to easily find artworks that match their tastes and emotional state.

[0614] Input: JSON data containing a list of recommended artworks

[0615] Output: A list of artworks visually displayed to the user

[0616] (Application example 2)

[0617] 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."

[0618] In modern society, it is difficult to select meals that match the individual preferences and emotional state of users, so methods to improve user satisfaction are required in food delivery services.In addition, because there are few personalized meal suggestions that reflect the user's preferences and emotional state, there is a lack of services that meet the needs of users, such as relaxation and health improvement, especially in stressful environments.

[0619] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving user preference information, means for saving the received preference information, data analysis means using generative artificial intelligence to analyze the saved preference information and emotional state and identify the user's preference pattern and emotional state, means for generating or selecting a meal suited to the user based on the identified preference pattern and emotional state, and means for providing the generated or selected meal to the user. This makes it possible to provide meals that suit the user's individual preferences and emotional state, which is expected to not only improve user satisfaction but also have effects such as maintaining health and reducing stress.

[0620] "Preference information" is information about the preferences of individual users, such as the user's favorite cuisine genres, specific ingredients, and the history of meals ordered in the past.

[0621] "Emotional state" refers to the user's current psychological or physiological state, and is information obtained through facial expression analysis, voice analysis, and biometric information (such as heart rate).

[0622] "Generative AI" is an AI that analyzes the user's preference patterns and emotional state based on the received data and generates new meal menus.

[0623] The "data analysis means" is a means for performing analysis based on the preference information and emotional state received from the user, and for suggesting the most suitable meal for the user.

[0624] A "meal generation or selection means" is a means for using artificial intelligence to generate a meal menu tailored to the user based on the identified preference patterns and emotional state, or for selecting from an existing menu.

[0625] "Means for storing" refers to means for storing the received user preference information and emotional state in a database for future use.

[0626] The "means for providing" is a means for transmitting the generated or selected meal menu to the user's terminal and displaying it.

[0627] The system of the present invention recommends personalized meals based on a user's preference information and emotional state. To provide optimal meal menus by analyzing a user's preferences and current emotional state, the system operates as follows: Specifically, the system includes the steps of acquiring user information, transmitting and saving data, analyzing the data, generating meal recommendations, and returning and providing the results.

[0628] User information acquisition

[0629] After logging in to the system, the user enters their preference information. Specifically, the user enters their preferred cuisine genre (e.g., Italian, Japanese, Chinese, etc.), specific ingredients, and past meal ordering history into an input form. The system also activates an emotion engine to recognize the user's emotional state. The emotion engine obtains the user's current emotional state through facial expression analysis using the smartphone camera, voice analysis using the microphone, and biometric information (heart rate, etc.) using a wearable device.

[0630] Data transmission and storage

[0631] After the user inputs their preference information and the emotion engine collects their emotional data, the device compiles this data and sends it to the server. The server analyzes the received data and stores it in a database. By storing it, the user's preference information and emotional state can be referenced in future uses.

[0632] Data analysis

[0633] The server performs data analysis based on the preference information and emotional state stored in the database. This analysis uses a generative AI model to identify individual characteristics based on the user's preference patterns and emotional state. For example, if a user likes Italian food, has a history of ordering a lot of pasta dishes in the past, and is currently feeling stressed, the analysis will take these factors into account.

[0634] Food recommendation generation

[0635] The server generates or selects from an existing database a meal plan tailored to the user based on the preference patterns and emotional state identified by the generative AI model. The server can recommend healthy Italian dishes or menus containing ingredients with stress-reducing properties to help the user relax.

[0636] Return and provision of results

[0637] The server generates a list of recommended food menus and sends it to the device as an HTTP response. The device analyzes the received food recommendation list and displays it in a user-friendly format. The user can browse the recommended menus and order the meals they like.

[0638] Examples and prompts

[0639] As a specific example, suppose a user logs in and enters their preference information as "Italian," "Pasta," and "Previously ordered menu: Carbonara." At the same time, the emotion engine analyzes the user's facial expressions and heart rate and recognizes that the user is feeling stressed. The server receives this information and generates a meal menu that matches the user's preferences and current emotional state based on past records stored in the database and the generative AI model. For example, a recommendation list of "Carbonara-style pasta served with relaxing herbal tea" is generated. This list is sent to the device and displayed to the user. The user can view the recommended menu and place an order.

[0640] Example prompt sentence:

[0641] "User's favorite dishes: pasta, salad. Current emotional state: stress. Generate a healthy and relaxing menu."

[0642] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0643] Step 1: Enter your user information

[0644] Input: A user logs into the application and enters their preferences (e.g., favorite cuisines, specific ingredients, past orders, etc.).

[0645] How it works: The device receives preference information through an input form and temporarily stores it.

[0646] Output: Preference information is saved on the device.

[0647] Step 2: Obtaining emotional states

[0648] Input: User's facial expressions, voice, and biometric information (heart rate, etc.).

[0649] How it works: The device captures facial expressions with a built-in camera and analyzes them using the emotion engine. It also records audio with a microphone and acquires biometric information from the wearable device.

[0650] Output: Emotional state data analyzed on the device.

[0651] Step 3: Sending data

[0652] Input: Stored preference information and retrieved emotional state data.

[0653] Operation: The device sends this data to the server.

[0654] Output: Preference information and emotional state data are sent to the server.

[0655] Step 4: Save your data

[0656] Input: Preference information and emotional state data sent to the server.

[0657] How it works: The server stores the received data persistently in a database.

[0658] Output: Preference information and emotional state data stored in a database.

[0659] Step 5: Analyze the data

[0660] Input: Preference information and emotional state data stored in a database.

[0661] How it works: The server uses a generative AI model to analyze preference patterns and emotional states. For example, if a user likes Italian food and is feeling stressed, it makes a calculation based on this information.

[0662] Output: Analysis results based on preference patterns and emotional states.

[0663] Step 6: Generate or select a meal menu

[0664] Input: Analysis of preference patterns and emotional states.

[0665] How it works: Based on the analysis results, the server uses a generative AI model to generate a new meal menu or select the best option from an existing menu.

[0666] Output: A list of recommended meals is generated.

[0667] Step 7: Returning the results

[0668] Input: A list of recommended meals.

[0669] Operation: The server sends the generated recommended menu list to the terminal as an HTTP response.

[0670] Output: A list of recommended meals is sent to the device.

[0671] Step 8: Viewing the results

[0672] Input: A list of recommended meals.

[0673] How it works: The device analyzes the received meal recommendation list and displays it in an easy-to-read format for the user.

[0674] Output: The user can view a list of recommended meals.

[0675] Step 9: Complete your order

[0676] Input: The meal selected by the user.

[0677] Operation: The user selects the menu item they like and completes the order. The terminal sends the order information to the server.

[0678] Output: The order information is sent to the server and the order is received.

[0679] These steps allow users to easily select and order the meal that best suits their tastes and emotional state.

[0680] 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.

[0681] 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.

[0682] 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.

[0683] [Third embodiment]

[0684] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0685] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0686] 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).

[0687] 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.

[0688] 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.

[0689] 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).

[0690] 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.

[0691] 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.

[0692] 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.

[0693] 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.

[0694] 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.

[0695] 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."

[0696] The system of the present invention is for recommending personalized art based on a user's preferences, and includes a series of steps for analyzing the user's preferences and generating or selecting and providing artworks based on the preferences. The program processing of the system is described in detail below.

[0697] Program Overview

[0698] This system is an online platform that receives input from users' devices, analyzes that information on the server side, and uses generative AI to recommend personalized art, allowing users to easily discover and appreciate artworks that suit their tastes.

[0699] User information acquisition

[0700] After logging in to the system, a user enters their art preferences. Specifically, the user enters their favorite colors, favorite art styles, favorite artists, artworks they have viewed in the past, etc. through an input form. For example, suppose a user enters that they like "Impressionism" and that "blue" is their favorite color.

[0701] User information transmission

[0702] Once the input is complete, the device collects this preference information and sends it to the server as an HTTP request. The server receives this request and proceeds to the next processing step.

[0703] Saving user information

[0704] The server analyzes the received preference information and stores it in a database, so that the user does not have to re-enter it when they use the system again in the future.

[0705] Data analysis

[0706] The server then begins analyzing the data to identify the user's preferences based on the stored preference information. Specifically, it uses generative AI to analyze the preference information and extract the user's preferred characteristics. These characteristics are based on patterns, such as "the user likes impressionist art, and particularly prefers blue artworks."

[0707] Art recommendation generation

[0708] Based on the results of the data analysis, the server activates the AI ​​to generate artwork that matches the user's preferences or select artwork from an existing database. For example, if the user likes the color blue, the AI ​​will generate impressionist artwork that contains a lot of blue.

[0709] Returning the results

[0710] The server sends the generated art recommendation list to the device as an HTTP response. The device receives the list and displays appropriate artworks for the user. The user can click on the recommended artworks to view more information or bookmark their favorite artworks.

[0711] Specific examples

[0712] As a specific example, suppose a user logs in and enters preference information such as "Impressionism," "blue," and "Monet." The server receives this data, stores it in a database, and uses generative AI to generate impressionist art with a blue base that matches the user's preferences. As a result, the server generates a recommended list such as "a new artwork depicting a Monet-esque blue water surface," and sends it back to the user's device. The user can browse this list and find their favorite works.

[0713] As described above, this system significantly improves the user's art appreciation experience, allowing everyone to easily find art that suits their tastes.

[0714] The processing flow will be explained below.

[0715] Step 1:

[0716] A user logs into the system. The user enters their login information and, if authentication is successful, a user session begins.

[0717] Step 2:

[0718] The user enters their preferences, including their favorite art style, favorite colors, and names of artists they often watch, into an input form.

[0719] Step 3:

[0720] The device collects the input preference information and organizes it into a data structure, such as JSON, which is formatted for easy analysis later.

[0721] Step 4:

[0722] The device sends the formatted data structure to the server as an HTTP request, which includes the user's preference information.

[0723] Step 5:

[0724] The server parses the received HTTP request, extracts the preference information from the request body, and stores it in a database in an appropriate format.

[0725] Step 6:

[0726] The server retrieves the user's preference information stored in the database and begins analysis, using a generative AI model to analyze the data to identify user preference patterns.

[0727] Step 7:

[0728] A generative AI model generates new artworks based on identified preference patterns, or selects artworks from an existing database that match the user's preferences.

[0729] Step 8:

[0730] The server compiles a list of generated or selected artworks into a recommendation list, which also includes the reason for the recommendation and related information.

[0731] Step 9:

[0732] The server sends the created recommendation list to the terminal as an HTTP response, which also includes detailed information about the recommended artworks.

[0733] Step 10:

[0734] The device analyzes the received HTTP response, extracts the recommendation list, and displays it in a user-friendly format.

[0735] Step 11:

[0736] Users can browse recommended artworks and bookmark their favorites. Users can also click on artworks to get more detailed information.

[0737] Example 1

[0738] 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."

[0739] Conventional art recommendation systems have struggled to provide personalized artworks that fully reflect a user's preferences. As a result, users are unable to efficiently find artworks that interest them, resulting in an unsatisfactory art appreciation experience. Furthermore, users must re-enter their preference information each time they use the system, which is inconvenient.

[0740] 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.

[0741] In this invention, the server includes a means for receiving user preference information, a means for storing the received preference information, and a data analysis means for analyzing the stored preference information and using artificial intelligence to identify the user's preference patterns. This enables personalized recommendations of artworks based on the user's preferences. Furthermore, by including a means for transmitting the generated art recommendation list to the terminal as an HTTP response, which the terminal receives and displays to the user, the user can easily find artworks that suit their preferences, eliminating the need for re-entry when using the system again, improving convenience.

[0742] "Preference information" is information that indicates the user's preferences, such as the user's favorite colors, favorite art styles, favorite artists, and the history of artworks that the user has viewed in the past.

[0743] The "receiving means" is a function or device for receiving preference information input by a user via a network.

[0744] The "storing means" is a function or device for storing the received preference information in a database or storage.

[0745] The "data analysis means" is a function or device that analyzes the stored preference information and identifies the user's preference patterns, and is the part that uses generative artificial intelligence.

[0746] "Generative AI" is software or a system that has the ability to generate new artworks using specific rules and algorithms based on user preferences.

[0747] The "means for identifying" is a function or device for extracting and clarifying a user's preference patterns through data analysis.

[0748] A "generative means" is a function or device for creating new artworks using generative artificial intelligence.

[0749] The "selection means" is a function or device for selecting artworks that match the user's preferences from an existing database.

[0750] The "means for providing" is a function or device for transmitting the generated or selected artwork to the user's terminal and displaying it.

[0751] A "terminal" is a device such as a computer, smartphone, or tablet that a user uses to input preference information and view provided artworks.

[0752] An "HTTP request" is a type of web protocol that allows a user's device to send information to a server.

[0753] An "HTTP response" is a type of web protocol that allows a server to return information to a user's device.

[0754] A "database" is a storage system that stores received preference information for later retrieval and analysis.

[0755] A "recommendation list" is a generated or selected list of artworks that is provided to a user.

[0756] The system according to the present invention is for recommending personalized art based on a user's preferences, and includes a series of steps for analyzing the user's preferences and generating or selecting and providing artwork based on the user's preferences. Specific embodiments of the system are described in detail below.

[0757] User information acquisition

[0758] A user first logs in to the system. After logging in, the user enters their art-related preference information. This information includes favorite colors, favorite art styles, favorite artists, and a history of artworks they have viewed in the past. As a specific example, consider the case where a user enters preference information such as "Impressionism," "blue," and "Monet."

[0759] User information transmission

[0760] Once the user has completed entering their preference information, the device sends this information to the server. The HTTP protocol is used for transmission, and the request is in JSON format. For example, the device sends the preference information as an HTTP request "POST / api / preferences".

[0761] Saving user information

[0762] The server analyzes the received preference information and stores it in a database (e.g., MySQL or MongoDB). The received JSON data is parsed and stored in an appropriate format.

[0763] Data analysis

[0764] The server then begins data analysis to identify the user's preferences based on the preference information stored in the database. In this step, the data is analyzed using programming languages ​​such as Python and R, and generative artificial intelligence (e.g., GPT-4) is utilized. Through this analysis, the user's preference patterns are extracted, and characteristics such as "the user likes impressionist art, and particularly prefers blue works" are identified.

[0765] Art recommendation generation

[0766] Based on the results of the data analysis, the server launches a generative AI model to generate artwork that matches the user's preferences, or selects suitable artwork from an existing database. For example, a Python script can be used to send a prompt to the generative AI model, such as, "The user likes impressionist artwork and is particularly fond of the color blue. Please generate a new artwork based on these conditions."

[0767] Returning the results

[0768] The server sends the generated art recommendation list to the device as an HTTP response. The device receives this response and displays appropriate art works to the user. The display is visually organized using HTML and CSS, making it easy for the user to browse.

[0769] User art appreciation

[0770] Users can click on artworks displayed on their devices to view detailed information or bookmark artworks they like. Specifically, users can click on the thumbnail of a displayed artwork to go to the details page where they can view a description of the artwork and information about the artist. They can also use the bookmark function to easily find their favorite artworks later.

[0771] Specific examples

[0772] The user logs in and enters preference information such as "Impressionist," "blue," and "Monet." The user's device then sends the preference information to the server via an HTTP request. The server stores this data in a database and sends a prompt to the generative AI model: "The user likes Impressionist artwork, and is particularly fond of the color blue. Please generate a new artwork based on these conditions." This generates an Impressionist artwork with a blue base. The server then compiles these artworks into a list and sends it back to the user's device. The user can then browse the displayed list of artworks, check detailed information, and bookmark artworks.

[0773] As described above, this system significantly improves the user's art appreciation experience, allowing everyone to easily find art that suits their tastes.

[0774] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0775] Step 1: Enter your user information

[0776] The user logs in to the system. After logging in, the user enters their preference information through an input form. The information entered includes favorite colors, favorite art styles, favorite artists, and a history of artworks viewed in the past. Specific examples of input include preference information such as "Impressionism," "blue," and "Monet." This input becomes the initial data for the system.

[0777] Input: User preferences (favorite colors, art styles, artists, etc.)

[0778] Output: Input preference information

[0779] Step 2: Submit user information

[0780] When the user has finished entering their preference information, the device compiles this information and sends it to the server as an HTTP request. The request uses the POST method, and data is sent in JSON format. Specifically, the device sends a request to the endpoint "POST / api / preferences".

[0781] Input: User-entered preferences

[0782] Output: HTTP request for preferences sent to the server

[0783] Step 3: Save user information

[0784] The server analyzes the received preference information and stores it in a database (e.g., MySQL or MongoDB). The received JSON data is parsed, converted into an appropriate format, and then stored in the database. This allows the user's preference information to be stored in a reusable format.

[0785] Input: HTTP request for preference information sent to the server

[0786] Output: User preferences stored in a database

[0787] Step 4: Data analysis

[0788] The server analyzes the data to identify the user's preferences based on the preference information stored in the database. Specifically, it uses programming languages ​​such as Python and R and generative artificial intelligence (e.g., GPT-4) to analyze the preference information. As feedback, it extracts specific patterns, such as the user's "I like impressionist paintings, and I particularly like blue works."

[0789] Input: User preferences stored in a database

[0790] Output: User preference pattern (e.g., "I like impressionist art, and I especially like blue artworks")

[0791] Step 5: Art recommendation generation

[0792] The server then launches a generative AI model based on the data analysis results to generate artwork that matches the user's preferences, or selects a suitable artwork from an existing database. Specifically, the server sends the generative AI model a prompt such as, "The user likes impressionist artwork, and is particularly fond of the color blue. Please generate a new artwork based on these conditions."

[0793] Input: User preference patterns

[0794] Output: Generated artwork or selected existing artwork

[0795] Step 6: Returning the results

[0796] The server sends the generated art recommendation list to the device as an HTTP response. The sent data is in JSON format and is structured to display appropriate art works to the user. The display is visually organized using HTML and CSS.

[0797] Input: Generated artwork or selected existing artwork

[0798] Output: Art recommendation list sent to user device (HTTP response)

[0799] Step 7: User Art Appreciation

[0800] Users can click on artworks displayed on their devices to view detailed information. They can also bookmark artworks they like. Specifically, users can click on a thumbnail of a displayed artwork to move to a detailed page where they can view a description of the artwork and information about the artist. Viewing and bookmarking operations are performed based on this information.

[0801] Input: Art recommendation list sent to user device

[0802] Output: User can view details of artwork and bookmark it

[0803] Through the above steps, a personalized art recommendation system based on the user's preferences is realized.

[0804] (Application example 1)

[0805] 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."

[0806] In today's brick-and-mortar stores, it is difficult to efficiently and effectively present artworks that match the tastes of visitors. This can result in missed opportunities to capture visitors' interest and lower satisfaction. Furthermore, while there is a demand for providing personalized experiences based on the preferences of each individual visitor, there is a lack of suitable means to achieve this.

[0807] 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.

[0808] In this invention, the server includes means for receiving user preference information, means for storing the received preference information, means for analyzing the stored preference information and using artificial intelligence to identify the user's preference pattern, means for generating or selecting an artwork suited to the user based on the identified preference pattern, means for providing the generated or selected artwork to the user, and means for visually presenting the artwork on a user-dedicated display device, thereby enabling visitors to experience artwork suited to their preferences in real time at a physical store.

[0809] The "means for receiving user preference information" refers to an interface for obtaining information about a user's preferences regarding art.

[0810] The "means for storing received preference information" refers to a database or storage system for storing acquired user preference information for a long period of time.

[0811] "Generative AI-based data analysis means" refers to a process that uses artificial intelligence techniques to analyze received and stored preference information and identify user preference patterns.

[0812] "Means for generating or selecting artwork" refers to a function for generating a new artwork based on the user's preferences or selecting an appropriate artwork from existing artworks.

[0813] "Means for providing generated or selected artwork" refers to a method or system for presenting generated or selected artwork to a user.

[0814] "User-only display device" refers to a device that visually presents artwork to a user only.

[0815] "Smart glasses" refers to a glasses-type device that has the function of visually displaying information when worn by a user.

[0816] The system for implementing the present invention includes a series of functions for receiving user preference information and recommending personalized art based on the information. The program processing of the system is described in detail below.

[0817] User information acquisition

[0818] First, a user logs in to the system and inputs their preferences regarding art. Specifically, the user inputs their favorite color, favorite art style, favorite artist, artworks they have viewed in the past, etc. through an input form. For example, a user may input that they like "Impressionism" and "the color blue," and that they like "Monet."

[0819] User information transmission

[0820] The terminal collects the input preference information and sends it to the server as an HTTP request. The server receives this request and proceeds to the next processing step.

[0821] Saving user information

[0822] The server analyzes the received preference information and stores it in a database, which saves the user the trouble of having to re-enter the information when they use the system again in the future.

[0823] Data analysis

[0824] The server then begins data analysis to identify the user's preferences based on the stored preference information. Specifically, it uses generative artificial intelligence (generative AI) to analyze the preference information and extract the user's preferred features. This generative AI uses a generative AI model such as OpenAI GPT-3.

[0825] Art recommendation generation

[0826] Based on the results of the data analysis, the server activates the AI ​​to generate artwork that matches the user's preferences or select artwork from an existing database. For example, if the user likes the color blue, the AI ​​will generate impressionist artwork that contains a lot of blue.

[0827] Returning the results

[0828] The server sends the generated or selected art recommendation list to the terminal as an HTTP response. The terminal receives the list and displays appropriate artworks to the user. The user can click on the recommended artworks to view detailed information or bookmark their favorite artworks.

[0829] User-specific display device

[0830] Users can visually experience recommended artworks in real time using a user-specific display device, including smart glasses. For example, when visiting a physical store, a user wearing smart glasses scans a specific area, and artworks generated by the server are displayed on the glasses' display.

[0831] Specific examples

[0832] As a concrete example, suppose a user logs in and enters preferences such as "Impressionist," "blue," and "Monet." The server analyzes this data and feeds the generative AI model the following prompt:

[0833] "User A's preferences are 'blue,' 'Impressionism,' and 'Monet.' Generate a new artwork based on these preferences."

[0834] Based on this prompt, the AI ​​will generate a "new artwork depicting a Monet-esque blue water surface," and the server will send this recommendation to the user's smart glasses. The user can then view the artwork in real time through the glasses, obtain more information on it, and purchase the artwork they like.

[0835] As described above, by using the system of the present invention, users can easily find artworks that suit their tastes and enjoy them visually in real time.

[0836] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0837] Step 1:

[0838] A user logs in to the system and enters information about their favorite art. For example, the user may specify through an input form that they like the color "blue," "Impressionism," and "Monet." The information entered includes favorite colors, art styles, favorite artists, and a history of artworks they have viewed in the past.

[0839] Input: User preferences (color, style, artist)

[0840] Output: User input is saved on the device

[0841] Step 2:

[0842] The device sends the received preference information to the server as an HTTP request. The server analyzes this request and stores the contents in a database. The stored data includes the preference information along with the user ID.

[0843] Input: User preference information

[0844] Output: Server-side preference storage

[0845] Step 3:

[0846] The server begins data analysis based on the stored preference information. Specifically, it uses generative artificial intelligence (generative AI) to analyze the preference information and extract the user's preferred features. The generative AI model used here is, for example, OpenAI GPT-3.

[0847] Input: Saved Preferences

[0848] Output: Identifying user preference patterns

[0849] Step 4:

[0850] Based on the identified preference patterns, the server activates a generative AI to generate or select from an existing database an artwork that matches the user's preferences. During this process, a prompt is input into the generative AI model. For example, a prompt such as "User A's preferences are 'blue,' 'Impressionism,' and 'Monet.' Please generate a new artwork based on these preferences" is used.

[0851] Input: User preference patterns

[0852] Output: Recommended artwork

[0853] Step 5:

[0854] The server sends the generated or selected artwork as an HTTP response to the terminal, which receives the response and displays the artwork to the user.

[0855] Input: Recommended Artwork

[0856] Output: Display of artwork on user device

[0857] Step 6:

[0858] By wearing the smart glasses, users can visually experience recommended artworks in real time. For example, when visiting a physical store, they can scan a specific area and artworks generated by the server will appear on the glasses' display.

[0859] Input: Recommended Artwork

[0860] Output: Artwork displayed on smart glasses

[0861] These are the processing steps of this system, which allows users to easily find artworks that suit their tastes and enjoy them visually in real time.

[0862] 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.

[0863] The system of the present invention recommends personalized art based on a user's preference information and emotional state, and analyzes the user's preferences and current emotional state to provide the most suitable artwork. The system includes a means for receiving and storing user preference information, a generative artificial intelligence for analyzing the data, an emotion engine, and a means for generating or selecting and providing artwork based on the analysis results.

[0864] User information acquisition

[0865] After logging in to the system, users enter their preferences. Specifically, they enter their favorite art style, favorite colors, names of artists they often watch, and so on into an input form. The system also activates an emotion engine to recognize the user's emotional state. The emotion engine obtains the user's current emotional state through facial expression analysis, voice analysis, and biometric information (such as heart rate).

[0866] User information transmission and storage

[0867] After the user inputs their preference information and the emotion engine collects their emotional data, the device compiles this data and sends it to the server. The server analyzes the received data and stores it in a database. By storing it, the user's preference information and emotional state can be referenced in future uses.

[0868] Data analysis

[0869] The server performs data analysis based on the preference information and emotional state stored in the database. This analysis uses a generative AI model to identify individual characteristics based on the user's preference patterns and current emotional state. For example, if a user likes "Impressionist" art and often likes the color "blue," but is currently feeling stressed, these factors will be taken into account when conducting the analysis.

[0870] Art recommendation generation

[0871] The server generates or selects from an existing database a suitable artwork for the user based on the preference patterns and emotional state identified by the generative AI model. The server can recommend a calming landscape painting with impressionist blue tones to help the user relax.

[0872] Return and provision of results

[0873] The server generates a list of recommended artworks and sends it to the device as an HTTP response. The device analyzes the received art recommendation list and displays it in a user-friendly format. The user can browse the recommended artworks and bookmark the ones they like. They can also click to view more detailed information.

[0874] Specific examples

[0875] As a specific example, suppose a user logs in and enters their preference information as "Impressionism," "blue color," and "frequently viewed artist: Monet." At the same time, the emotion engine analyzes the user's facial expressions and heart rate and recognizes that the user is feeling stressed. The server receives this information and generates artworks that match the user's preferences and current emotional state based on past records stored in the database and the generative AI model. For example, a recommendation list might include "serene landscapes with a Monet-esque blue theme." This list is sent to the device and displayed to the user. The user can view the recommended artworks and spend a pleasant time.

[0876] As described above, this system greatly enhances the art appreciation experience by personalizing artworks based on the user's preferences and emotional state, allowing users to easily find artworks that match their tastes and emotions and relieve daily stress.

[0877] The processing flow will be explained below.

[0878] Step 1:

[0879] A user logs into the system. The user enters their login information and, if authentication is successful, a user session begins.

[0880] Step 2:

[0881] The user enters their preferences, such as "favorite art style," "favorite color," and "frequently watched artists," into an input form.

[0882] Step 3:

[0883] The emotion engine is activated to recognize the user's emotional state in real time by analyzing the user's facial expressions, voice tone, and biometric information (e.g., heart rate).

[0884] Step 4:

[0885] The device compiles preference information and emotion data into a data structure in JSON format or similar, which is then formatted for easy analysis in subsequent processing.

[0886] Step 5:

[0887] The device sends the formatted data structure to the server as an HTTP request, which includes the user's preference information and emotion data.

[0888] Step 6:

[0889] The server analyzes the received HTTP request, extracts preference information and emotion data from the request body, and stores them in a database.

[0890] Step 7:

[0891] The server retrieves the user's preference information and emotional data stored in the database and begins analysis. Using a generative AI model, it identifies the user's preference patterns and current emotional state.

[0892] Step 8:

[0893] The generative AI model generates or selects the most suitable artwork for the user based on the identified preference patterns and emotional state. The server generates a new artwork or selects the most suitable artwork from an existing database.

[0894] Step 9:

[0895] The server compiles a list of generated or selected artworks into a recommendation list, which also includes the reason for the recommendation and related information.

[0896] Step 10:

[0897] The server sends the created recommendation list to the terminal as an HTTP response, which includes detailed information about the recommended artworks.

[0898] Step 11:

[0899] The device analyzes the HTTP response received and displays a list of recommendations in an easy-to-read format for the user.

[0900] Step 12:

[0901] Users can browse recommended artworks and bookmark their favorites. Users can also click on artworks to view additional information for more details.

[0902] Specific examples

[0903] Suppose a user logs in and enters their preferences, such as "Impressionism," "blue," and "Favorite Artist: Monet." At the same time, the emotion engine analyzes the user's facial expressions and heart rate and recognizes that the user is relaxed. The server receives this information and generates artworks that match the user's preferences and current emotional state based on past records stored in the database and the generative AI model. For example, a recommendation list might be generated that includes "serene landscapes with a Monet-esque blue theme." This list is sent to the device and displayed to the user. The user can browse these recommended artworks and spend a pleasant time.

[0904] As described above, this system greatly enhances the art appreciation experience by personalizing artworks based on the user's preferences and emotional state, allowing users to easily find artworks that match their tastes and emotions and relieve daily stress.

[0905] Example 2

[0906] 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."

[0907] Conventional art recommendation systems only consider user preference information and do not reflect the user's current emotional state, making it difficult to provide artworks that suit the user's psychological state. Furthermore, they are limited to static selection of artworks and lack the ability to generate new artworks. This makes it difficult to sufficiently increase user satisfaction.

[0908] 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.

[0909] In this invention, the server includes means for receiving user preference information, means for saving the received preference information, means for analyzing the saved preference information and the user's emotional state and identifying the preference pattern and the emotional state using a generative artificial intelligence to analyze the saved preference information and the user's emotional state, means for generating or selecting an artwork suited to the user based on the identified preference pattern and the emotional state, and means for providing the generated or selected artwork to the user, thereby making it possible to provide the optimal artwork based on the user's preferences and current emotional state.

[0910] "Preference information" refers to user-specified preferred art styles, colors, artist names, and past browsing history.

[0911] "Emotional state" is information that indicates the user's current emotional and psychological state, and is collected from facial expression analysis, voice analysis, and biometric information (heart rate, etc.).

[0912] "Generative AI" is a general term for AI technology that uses machine learning algorithms and AI models to analyze data and generate new information and objects.

[0913] "Data analysis means" refers to techniques and methods for analyzing stored preference information and emotional states to extract specific patterns and characteristics.

[0914] "Generative means" refers to the methods and techniques used to create new artworks based on the analyzed information.

[0915] "Selection method" refers to the method or technology used to select the most suitable artwork from the existing database based on the analyzed information.

[0916] "Delivery means" refers to the technology or method for visually displaying the generated or selected artwork to the user.

[0917] The system of the present invention recommends personalized art based on a user's preference information and emotional state, and provides the most suitable artwork by analyzing the user's preferences and current emotional state. The system includes a means for receiving and storing user preference information, a generative artificial intelligence for analyzing the data, an emotion engine, and a means for generating or selecting and providing artwork based on the analysis results.

[0918] Users log in to the system using their devices and enter their preferences. Specifically, they enter their art style, favorite colors, and names of artists they often visit into an input form. The system also uses an emotion engine to obtain the user's current emotional state through facial expression analysis, voice analysis, and biometric information (such as heart rate). The emotion engine includes facial expression analysis using the OpenCV library, voice analysis using the Librosa library, and real-time heart rate data collection.

[0919] The device combines the user's input preference information and the emotion data acquired by the emotion engine into a single packet and sends it to the server as an HTTP POST request. The server analyzes the received data and stores it in a database (MongoDB). The stored data is used for subsequent analysis and reference.

[0920] The server performs data analysis based on the stored preference information and emotional state. This analysis utilizes generative artificial intelligence, with a generative AI model (using TensorFlow) identifying individual characteristics based on the user's preference patterns and current emotional state. For example, if a user likes "Impressionist" art, has a history of using the color "blue," and is currently feeling stressed, these factors will be taken into account in the analysis.

[0921] Based on the analysis results, the server generates the most suitable artwork using a generative AI model or selects one from an existing database. An example of a generated prompt is, "User preference information: Impressionism, blue color, popular artists. Current emotional state: stress. Please recommend the most suitable artwork based on this."

[0922] The server generates a list of recommended artworks and sends it to the device as an HTTP response. The device analyzes the received art recommendation list and displays it on the screen in a format that is easy for the user to view. The user can view the recommended artworks and bookmark the ones they like. The user can also click to view more detailed information.

[0923] For example, suppose a user logs in and enters their preferences, such as "Impressionist," "blue," and "frequently viewed artists." At the same time, the emotion engine analyzes the user's facial expressions and heart rate and recognizes that the user is feeling stressed. The server receives this information and, based on past records stored in the database and the generative AI model, generates artworks that match the user's preferences and current emotional state. For example, a recommendation list might include "serene landscape paintings with blue Impressionist tones." This list is sent to the device and displayed to the user. The user can browse these recommended artworks and spend a pleasant time.

[0924] As described above, this system significantly improves the art appreciation experience by personalizing artworks based on the user's preferences and emotional state, allowing users to easily find artworks that match their tastes and emotions, helping to relieve everyday stress.

[0925] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0926] Step 1: Obtain user information

[0927] Users log in to the system and enter their preferences, such as their favorite art style, favorite colors, and the names of artists they often visit, into an input form. This input form is web-based, and the data entered by the user is sent to the device in JSON format. The device then uses its camera and microphone to activate the emotion engine. The emotion engine uses OpenCV to analyze the user's facial expressions and Librosa to analyze audio data. Biometric information, such as heart rate, is also collected in real time from the smartwatch. All of this data is compiled into emotional state data.

[0928] Input: User preference information (art style, color, artist name), facial expression data, voice data, biometric information

[0929] Output: Analyzed preference information and emotional state data

[0930] Step 2: Send and save user information

[0931] The device combines the user's input preferences and the emotional state data collected by the emotion engine into a single JSON packet. The combined data is then sent to the server as an HTTP POST request. The server receives the data and performs initial analysis using the Pandas library. The data is then stored in MongoDB, where it can be retained for future reference and analysis.

[0932] Input: A JSON packet containing preference information and emotional state data

[0933] Output: Parsed data stored in a database

[0934] Step 3: Data analysis

[0935] The server references the user's preference information and emotional state data stored in MongoDB and performs data analysis. A generative AI model is used for the analysis, using the TensorFlow library. The generative AI model uses this data to identify the user's preference patterns and current emotional state. For example, if a user likes "Impressionist" art, values ​​the color "blue," and is currently feeling stressed, the model combines these factors to perform an analysis.

[0936] Input: Preference information and emotional state data stored in a database

[0937] Output: Analysis results based on user preference patterns and emotional state

[0938] Step 4: Art recommendation generation

[0939] Based on the analysis results, the server uses a generative AI model to generate the most suitable artwork or select one from an existing database. An example of a generated prompt is, "User's preferences: Impressionism, blue, popular artists. Current emotional state: stress. Please recommend the most suitable artwork based on this." This generates or selects the artwork that best suits the user's preferences and emotional state.

[0940] Input: Analysis results of user preference patterns and emotional state

[0941] Output: A list of recommended artworks

[0942] Step 5: Return and provide results

[0943] The server generates a list of recommended artworks in JSON format and sends it to the device as an HTTP response. The device parses the received JSON data and displays it in a user-friendly format on the web browser. The user can browse the recommended artworks and bookmark their favorites. They can also click to view detailed information. This allows users to easily find artworks that match their tastes and emotional state.

[0944] Input: JSON data containing a list of recommended artworks

[0945] Output: A list of artworks visually displayed to the user

[0946] (Application example 2)

[0947] 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."

[0948] In modern society, it is difficult to select meals that match the individual preferences and emotional state of users, so methods to improve user satisfaction are required in food delivery services.In addition, because there are few personalized meal suggestions that reflect the user's preferences and emotional state, there is a lack of services that meet the needs of users, such as relaxation and health improvement, especially in stressful environments.

[0949] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving user preference information, means for saving the received preference information, data analysis means using generative artificial intelligence to analyze the saved preference information and emotional state and identify the user's preference pattern and emotional state, means for generating or selecting a meal suited to the user based on the identified preference pattern and emotional state, and means for providing the generated or selected meal to the user. This makes it possible to provide meals that suit the user's individual preferences and emotional state, which is expected to not only improve user satisfaction but also have effects such as maintaining health and reducing stress.

[0950] "Preference information" is information about the preferences of individual users, such as the user's favorite cuisine genres, specific ingredients, and the history of meals ordered in the past.

[0951] "Emotional state" refers to the user's current psychological or physiological state, and is information obtained through facial expression analysis, voice analysis, and biometric information (such as heart rate).

[0952] "Generative AI" is an AI that analyzes the user's preference patterns and emotional state based on the received data and generates new meal menus.

[0953] The "data analysis means" is a means for performing analysis based on the preference information and emotional state received from the user, and for suggesting the most suitable meal for the user.

[0954] A "meal generation or selection means" is a means for using artificial intelligence to generate a meal menu tailored to the user based on the identified preference patterns and emotional state, or for selecting from an existing menu.

[0955] "Means for storing" refers to means for storing the received user preference information and emotional state in a database for future use.

[0956] The "means for providing" is a means for transmitting the generated or selected meal menu to the user's terminal and displaying it.

[0957] The system of the present invention recommends personalized meals based on a user's preference information and emotional state. To provide optimal meal menus by analyzing a user's preferences and current emotional state, the system operates as follows: Specifically, the system includes the steps of acquiring user information, transmitting and saving data, analyzing the data, generating meal recommendations, and returning and providing the results.

[0958] User information acquisition

[0959] After logging in to the system, the user enters their preference information. Specifically, the user enters their preferred cuisine genre (e.g., Italian, Japanese, Chinese, etc.), specific ingredients, and past meal ordering history into an input form. The system also activates an emotion engine to recognize the user's emotional state. The emotion engine obtains the user's current emotional state through facial expression analysis using the smartphone camera, voice analysis using the microphone, and biometric information (heart rate, etc.) using a wearable device.

[0960] Data transmission and storage

[0961] After the user inputs their preference information and the emotion engine collects their emotional data, the device compiles this data and sends it to the server. The server analyzes the received data and stores it in a database. By storing it, the user's preference information and emotional state can be referenced in future uses.

[0962] Data analysis

[0963] The server performs data analysis based on the preference information and emotional state stored in the database. This analysis uses a generative AI model to identify individual characteristics based on the user's preference patterns and emotional state. For example, if a user likes Italian food, has a history of ordering a lot of pasta dishes in the past, and is currently feeling stressed, the analysis will take these factors into account.

[0964] Food recommendation generation

[0965] The server generates or selects from an existing database a meal plan tailored to the user based on the preference patterns and emotional state identified by the generative AI model. The server can recommend healthy Italian dishes or menus containing ingredients with stress-reducing properties to help the user relax.

[0966] Return and provision of results

[0967] The server generates a list of recommended food menus and sends it to the device as an HTTP response. The device analyzes the received food recommendation list and displays it in a user-friendly format. The user can browse the recommended menus and order the meals they like.

[0968] Examples and prompts

[0969] As a specific example, suppose a user logs in and enters their preference information as "Italian," "Pasta," and "Previously ordered menu: Carbonara." At the same time, the emotion engine analyzes the user's facial expressions and heart rate and recognizes that the user is feeling stressed. The server receives this information and generates a meal menu that matches the user's preferences and current emotional state based on past records stored in the database and the generative AI model. For example, a recommendation list of "Carbonara-style pasta served with relaxing herbal tea" is generated. This list is sent to the device and displayed to the user. The user can view the recommended menu and place an order.

[0970] Example prompt sentence:

[0971] "User's favorite dishes: pasta, salad. Current emotional state: stress. Generate a healthy and relaxing menu."

[0972] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0973] Step 1: Enter your user information

[0974] Input: A user logs into the application and enters their preferences (e.g., favorite cuisines, specific ingredients, past orders, etc.).

[0975] How it works: The device receives preference information through an input form and temporarily stores it.

[0976] Output: Preference information is saved on the device.

[0977] Step 2: Obtaining emotional states

[0978] Input: User's facial expressions, voice, and biometric information (heart rate, etc.).

[0979] How it works: The device captures facial expressions with a built-in camera and analyzes them using the emotion engine. It also records audio with a microphone and acquires biometric information from the wearable device.

[0980] Output: Emotional state data analyzed on the device.

[0981] Step 3: Sending data

[0982] Input: Stored preference information and retrieved emotional state data.

[0983] Operation: The device sends this data to the server.

[0984] Output: Preference information and emotional state data are sent to the server.

[0985] Step 4: Save your data

[0986] Input: Preference information and emotional state data sent to the server.

[0987] How it works: The server stores the received data persistently in a database.

[0988] Output: Preference information and emotional state data stored in a database.

[0989] Step 5: Analyze the data

[0990] Input: Preference information and emotional state data stored in a database.

[0991] How it works: The server uses a generative AI model to analyze preference patterns and emotional states. For example, if a user likes Italian food and is feeling stressed, it makes a calculation based on this information.

[0992] Output: Analysis results based on preference patterns and emotional states.

[0993] Step 6: Generate or select a meal menu

[0994] Input: Analysis of preference patterns and emotional states.

[0995] How it works: Based on the analysis results, the server uses a generative AI model to generate a new meal menu or select the best option from an existing menu.

[0996] Output: A list of recommended meals is generated.

[0997] Step 7: Returning the results

[0998] Input: A list of recommended meals.

[0999] Operation: The server sends the generated recommended menu list to the terminal as an HTTP response.

[1000] Output: A list of recommended meals is sent to the device.

[1001] Step 8: Viewing the results

[1002] Input: A list of recommended meals.

[1003] How it works: The device analyzes the received meal recommendation list and displays it in an easy-to-read format for the user.

[1004] Output: The user can view a list of recommended meals.

[1005] Step 9: Complete your order

[1006] Input: The meal selected by the user.

[1007] Operation: The user selects the menu item they like and completes the order. The terminal sends the order information to the server.

[1008] Output: The order information is sent to the server and the order is received.

[1009] These steps allow users to easily select and order the meal that best suits their tastes and emotional state.

[1010] 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.

[1011] 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.

[1012] 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.

[1013] [Fourth embodiment]

[1014] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1015] 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.

[1016] 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).

[1017] 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.

[1018] 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.

[1019] 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).

[1020] 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.

[1021] 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.

[1022] 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.

[1023] 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.

[1024] 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.

[1025] 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.

[1026] 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."

[1027] The system of the present invention is for recommending personalized art based on a user's preferences, and includes a series of steps for analyzing the user's preferences and generating or selecting and providing artworks based on the preferences. The program processing of the system is described in detail below.

[1028] Program Overview

[1029] This system is an online platform that receives input from users' devices, analyzes that information on the server side, and uses generative AI to recommend personalized art, allowing users to easily discover and appreciate artworks that suit their tastes.

[1030] User information acquisition

[1031] After logging in to the system, a user enters their art preferences. Specifically, the user enters their favorite colors, favorite art styles, favorite artists, artworks they have viewed in the past, etc. through an input form. For example, suppose a user enters that they like "Impressionism" and that "blue" is their favorite color.

[1032] User information transmission

[1033] Once the input is complete, the device collects this preference information and sends it to the server as an HTTP request. The server receives this request and proceeds to the next processing step.

[1034] Saving user information

[1035] The server analyzes the received preference information and stores it in a database, so that the user does not have to re-enter it when they use the system again in the future.

[1036] Data analysis

[1037] The server then begins analyzing the data to identify the user's preferences based on the stored preference information. Specifically, it uses generative AI to analyze the preference information and extract the user's preferred characteristics. These characteristics are based on patterns, such as "the user likes impressionist art, and particularly prefers blue artworks."

[1038] Art recommendation generation

[1039] Based on the results of the data analysis, the server activates the AI ​​to generate artwork that matches the user's preferences or select artwork from an existing database. For example, if the user likes the color blue, the AI ​​will generate impressionist artwork that contains a lot of blue.

[1040] Returning the results

[1041] The server sends the generated art recommendation list to the device as an HTTP response. The device receives the list and displays appropriate artworks for the user. The user can click on the recommended artworks to view more information or bookmark their favorite artworks.

[1042] Specific examples

[1043] As a specific example, suppose a user logs in and enters preference information such as "Impressionism," "blue," and "Monet." The server receives this data, stores it in a database, and uses generative AI to generate impressionist art with a blue base that matches the user's preferences. As a result, the server generates a recommended list such as "a new artwork depicting a Monet-esque blue water surface," and sends it back to the user's device. The user can browse this list and find their favorite works.

[1044] As described above, this system significantly improves the user's art appreciation experience, allowing everyone to easily find art that suits their tastes.

[1045] The processing flow will be explained below.

[1046] Step 1:

[1047] A user logs into the system. The user enters their login information and, if authentication is successful, a user session begins.

[1048] Step 2:

[1049] The user enters their preferences, including their favorite art style, favorite colors, and names of artists they often watch, into an input form.

[1050] Step 3:

[1051] The device collects the input preference information and organizes it into a data structure, such as JSON, which is formatted for easy analysis later.

[1052] Step 4:

[1053] The device sends the formatted data structure to the server as an HTTP request, which includes the user's preference information.

[1054] Step 5:

[1055] The server parses the received HTTP request, extracts the preference information from the request body, and stores it in a database in an appropriate format.

[1056] Step 6:

[1057] The server retrieves the user's preference information stored in the database and begins analysis, using a generative AI model to analyze the data to identify user preference patterns.

[1058] Step 7:

[1059] A generative AI model generates new artworks based on identified preference patterns, or selects artworks from an existing database that match the user's preferences.

[1060] Step 8:

[1061] The server compiles a list of generated or selected artworks into a recommendation list, which also includes the reason for the recommendation and related information.

[1062] Step 9:

[1063] The server sends the created recommendation list to the terminal as an HTTP response, which also includes detailed information about the recommended artworks.

[1064] Step 10:

[1065] The device analyzes the received HTTP response, extracts the recommendation list, and displays it in a user-friendly format.

[1066] Step 11:

[1067] Users can browse recommended artworks and bookmark their favorites. Users can also click on artworks to get more detailed information.

[1068] Example 1

[1069] 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."

[1070] Conventional art recommendation systems have struggled to provide personalized artworks that fully reflect a user's preferences. As a result, users are unable to efficiently find artworks that interest them, resulting in an unsatisfactory art appreciation experience. Furthermore, users must re-enter their preference information each time they use the system, which is inconvenient.

[1071] 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.

[1072] In this invention, the server includes a means for receiving user preference information, a means for storing the received preference information, and a data analysis means for analyzing the stored preference information and using artificial intelligence to identify the user's preference patterns. This enables personalized recommendations of artworks based on the user's preferences. Furthermore, by including a means for transmitting the generated art recommendation list to the terminal as an HTTP response, which the terminal receives and displays to the user, the user can easily find artworks that suit their preferences, eliminating the need for re-entry when using the system again, improving convenience.

[1073] "Preference information" is information that indicates the user's preferences, such as the user's favorite colors, favorite art styles, favorite artists, and the history of artworks that the user has viewed in the past.

[1074] The "receiving means" is a function or device for receiving preference information input by a user via a network.

[1075] The "storing means" is a function or device for storing the received preference information in a database or storage.

[1076] The "data analysis means" is a function or device that analyzes the stored preference information and identifies the user's preference patterns, and is the part that uses generative artificial intelligence.

[1077] "Generative AI" is software or a system that has the ability to generate new artworks using specific rules and algorithms based on user preferences.

[1078] The "means for identifying" is a function or device for extracting and clarifying a user's preference patterns through data analysis.

[1079] A "generative means" is a function or device for creating new artworks using generative artificial intelligence.

[1080] The "selection means" is a function or device for selecting artworks that match the user's preferences from an existing database.

[1081] The "means for providing" is a function or device for transmitting the generated or selected artwork to the user's terminal and displaying it.

[1082] A "terminal" is a device such as a computer, smartphone, or tablet that a user uses to input preference information and view provided artworks.

[1083] An "HTTP request" is a type of web protocol that allows a user's device to send information to a server.

[1084] An "HTTP response" is a type of web protocol that allows a server to return information to a user's device.

[1085] A "database" is a storage system that stores received preference information for later retrieval and analysis.

[1086] A "recommendation list" is a generated or selected list of artworks that is provided to a user.

[1087] The system according to the present invention is for recommending personalized art based on a user's preferences, and includes a series of steps for analyzing the user's preferences and generating or selecting and providing artwork based on the user's preferences. Specific embodiments of the system are described in detail below.

[1088] User information acquisition

[1089] A user first logs in to the system. After logging in, the user enters their art-related preference information. This information includes favorite colors, favorite art styles, favorite artists, and a history of artworks they have viewed in the past. As a specific example, consider the case where a user enters preference information such as "Impressionism," "blue," and "Monet."

[1090] User information transmission

[1091] Once the user has completed entering their preference information, the device sends this information to the server. The HTTP protocol is used for transmission, and the request is in JSON format. For example, the device sends the preference information as an HTTP request "POST / api / preferences".

[1092] Saving user information

[1093] The server analyzes the received preference information and stores it in a database (e.g., MySQL or MongoDB). The received JSON data is parsed and stored in an appropriate format.

[1094] Data analysis

[1095] The server then begins data analysis to identify the user's preferences based on the preference information stored in the database. In this step, the data is analyzed using programming languages ​​such as Python and R, and generative artificial intelligence (e.g., GPT-4) is utilized. Through this analysis, the user's preference patterns are extracted, and characteristics such as "the user likes impressionist art, and particularly prefers blue works" are identified.

[1096] Art recommendation generation

[1097] Based on the results of the data analysis, the server launches a generative AI model to generate artwork that matches the user's preferences, or selects suitable artwork from an existing database. For example, a Python script can be used to send a prompt to the generative AI model, such as, "The user likes impressionist artwork and is particularly fond of the color blue. Please generate a new artwork based on these conditions."

[1098] Returning the results

[1099] The server sends the generated art recommendation list to the device as an HTTP response. The device receives this response and displays appropriate art works to the user. The display is visually organized using HTML and CSS, making it easy for the user to browse.

[1100] User art appreciation

[1101] Users can click on artworks displayed on their devices to view detailed information or bookmark artworks they like. Specifically, users can click on the thumbnail of a displayed artwork to go to the details page where they can view a description of the artwork and information about the artist. They can also use the bookmark function to easily find their favorite artworks later.

[1102] Specific examples

[1103] The user logs in and enters preference information such as "Impressionist," "blue," and "Monet." The user's device then sends the preference information to the server via an HTTP request. The server stores this data in a database and sends a prompt to the generative AI model: "The user likes Impressionist artwork, and is particularly fond of the color blue. Please generate a new artwork based on these conditions." This generates an Impressionist artwork with a blue base. The server then compiles these artworks into a list and sends it back to the user's device. The user can then browse the displayed list of artworks, check detailed information, and bookmark artworks.

[1104] As described above, this system significantly improves the user's art appreciation experience, allowing everyone to easily find art that suits their tastes.

[1105] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1106] Step 1: Enter your user information

[1107] The user logs in to the system. After logging in, the user enters their preference information through an input form. The information entered includes favorite colors, favorite art styles, favorite artists, and a history of artworks viewed in the past. Specific examples of input include preference information such as "Impressionism," "blue," and "Monet." This input becomes the initial data for the system.

[1108] Input: User preferences (favorite colors, art styles, artists, etc.)

[1109] Output: Input preference information

[1110] Step 2: Submit user information

[1111] When the user has finished entering their preference information, the device compiles this information and sends it to the server as an HTTP request. The request uses the POST method, and data is sent in JSON format. Specifically, the device sends a request to the endpoint "POST / api / preferences".

[1112] Input: User-entered preferences

[1113] Output: HTTP request for preferences sent to the server

[1114] Step 3: Save user information

[1115] The server analyzes the received preference information and stores it in a database (e.g., MySQL or MongoDB). The received JSON data is parsed, converted into an appropriate format, and then stored in the database. This allows the user's preference information to be stored in a reusable format.

[1116] Input: HTTP request for preference information sent to the server

[1117] Output: User preferences stored in a database

[1118] Step 4: Data analysis

[1119] The server analyzes the data to identify the user's preferences based on the preference information stored in the database. Specifically, it uses programming languages ​​such as Python and R and generative artificial intelligence (e.g., GPT-4) to analyze the preference information. As feedback, it extracts specific patterns, such as the user's "I like impressionist paintings, and I particularly like blue works."

[1120] Input: User preferences stored in a database

[1121] Output: User preference pattern (e.g., "I like impressionist art, and I especially like blue artworks")

[1122] Step 5: Art recommendation generation

[1123] The server then launches a generative AI model based on the data analysis results to generate artwork that matches the user's preferences, or selects a suitable artwork from an existing database. Specifically, the server sends the generative AI model a prompt such as, "The user likes impressionist artwork, and is particularly fond of the color blue. Please generate a new artwork based on these conditions."

[1124] Input: User preference patterns

[1125] Output: Generated artwork or selected existing artwork

[1126] Step 6: Returning the results

[1127] The server sends the generated art recommendation list to the device as an HTTP response. The sent data is in JSON format and is structured to display appropriate art works to the user. The display is visually organized using HTML and CSS.

[1128] Input: Generated artwork or selected existing artwork

[1129] Output: Art recommendation list sent to user device (HTTP response)

[1130] Step 7: User Art Appreciation

[1131] Users can click on artworks displayed on their devices to view detailed information. They can also bookmark artworks they like. Specifically, users can click on a thumbnail of a displayed artwork to move to a detailed page where they can view a description of the artwork and information about the artist. Viewing and bookmarking operations are performed based on this information.

[1132] Input: Art recommendation list sent to user device

[1133] Output: User can view details of artwork and bookmark it

[1134] Through the above steps, a personalized art recommendation system based on the user's preferences is realized.

[1135] (Application example 1)

[1136] 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."

[1137] In today's brick-and-mortar stores, it is difficult to efficiently and effectively present artworks that match the tastes of visitors. This can result in missed opportunities to capture visitors' interest and lower satisfaction. Furthermore, while there is a demand for providing personalized experiences based on the preferences of each individual visitor, there is a lack of suitable means to achieve this.

[1138] 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.

[1139] In this invention, the server includes means for receiving user preference information, means for storing the received preference information, means for analyzing the stored preference information and using artificial intelligence to identify the user's preference pattern, means for generating or selecting an artwork suited to the user based on the identified preference pattern, means for providing the generated or selected artwork to the user, and means for visually presenting the artwork on a user-dedicated display device, thereby enabling visitors to experience artwork suited to their preferences in real time at a physical store.

[1140] The "means for receiving user preference information" refers to an interface for obtaining information about a user's preferences regarding art.

[1141] The "means for storing received preference information" refers to a database or storage system for storing acquired user preference information for a long period of time.

[1142] "Generative AI-based data analysis means" refers to a process that uses artificial intelligence techniques to analyze received and stored preference information and identify user preference patterns.

[1143] "Means for generating or selecting artwork" refers to a function for generating a new artwork based on the user's preferences or selecting an appropriate artwork from existing artworks.

[1144] "Means for providing generated or selected artwork" refers to a method or system for presenting generated or selected artwork to a user.

[1145] "User-only display device" refers to a device that visually presents artwork to a user only.

[1146] "Smart glasses" refers to a glasses-type device that has the function of visually displaying information when worn by a user.

[1147] The system for implementing the present invention includes a series of functions for receiving user preference information and recommending personalized art based on the information. The program processing of the system is described in detail below.

[1148] User information acquisition

[1149] First, a user logs in to the system and inputs their preferences regarding art. Specifically, the user inputs their favorite color, favorite art style, favorite artist, artworks they have viewed in the past, etc. through an input form. For example, a user may input that they like "Impressionism" and "the color blue," and that they like "Monet."

[1150] User information transmission

[1151] The terminal collects the input preference information and sends it to the server as an HTTP request. The server receives this request and proceeds to the next processing step.

[1152] Saving user information

[1153] The server analyzes the received preference information and stores it in a database, which saves the user the trouble of having to re-enter the information when they use the system again in the future.

[1154] Data analysis

[1155] The server then begins data analysis to identify the user's preferences based on the stored preference information. Specifically, it uses generative artificial intelligence (generative AI) to analyze the preference information and extract the user's preferred features. This generative AI uses a generative AI model such as OpenAI GPT-3.

[1156] Art recommendation generation

[1157] Based on the results of the data analysis, the server activates the AI ​​to generate artwork that matches the user's preferences or select artwork from an existing database. For example, if the user likes the color blue, the AI ​​will generate impressionist artwork that contains a lot of blue.

[1158] Returning the results

[1159] The server sends the generated or selected art recommendation list to the terminal as an HTTP response. The terminal receives the list and displays appropriate artworks to the user. The user can click on the recommended artworks to view detailed information or bookmark their favorite artworks.

[1160] User-specific display device

[1161] Users can visually experience recommended artworks in real time using a user-specific display device, including smart glasses. For example, when visiting a physical store, a user wearing smart glasses scans a specific area, and artworks generated by the server are displayed on the glasses' display.

[1162] Specific examples

[1163] As a concrete example, suppose a user logs in and enters preferences such as "Impressionist," "blue," and "Monet." The server analyzes this data and feeds the generative AI model the following prompt:

[1164] "User A's preferences are 'blue,' 'Impressionism,' and 'Monet.' Generate a new artwork based on these preferences."

[1165] Based on this prompt, the AI ​​will generate a "new artwork depicting a Monet-esque blue water surface," and the server will send this recommendation to the user's smart glasses. The user can then view the artwork in real time through the glasses, obtain more information on it, and purchase the artwork they like.

[1166] As described above, by using the system of the present invention, users can easily find artworks that suit their tastes and enjoy them visually in real time.

[1167] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1168] Step 1:

[1169] A user logs in to the system and enters information about their favorite art. For example, the user may specify through an input form that they like the color "blue," "Impressionism," and "Monet." The information entered includes favorite colors, art styles, favorite artists, and a history of artworks they have viewed in the past.

[1170] Input: User preferences (color, style, artist)

[1171] Output: User input is saved on the device

[1172] Step 2:

[1173] The device sends the received preference information to the server as an HTTP request. The server analyzes this request and stores the contents in a database. The stored data includes the preference information along with the user ID.

[1174] Input: User preference information

[1175] Output: Server-side preference storage

[1176] Step 3:

[1177] The server begins data analysis based on the stored preference information. Specifically, it uses generative artificial intelligence (generative AI) to analyze the preference information and extract the user's preferred features. The generative AI model used here is, for example, OpenAI GPT-3.

[1178] Input: Saved Preferences

[1179] Output: Identifying user preference patterns

[1180] Step 4:

[1181] Based on the identified preference patterns, the server activates a generative AI to generate or select from an existing database an artwork that matches the user's preferences. During this process, a prompt is input into the generative AI model. For example, a prompt such as "User A's preferences are 'blue,' 'Impressionism,' and 'Monet.' Please generate a new artwork based on these preferences" is used.

[1182] Input: User preference patterns

[1183] Output: Recommended artwork

[1184] Step 5:

[1185] The server sends the generated or selected artwork as an HTTP response to the terminal, which receives the response and displays the artwork to the user.

[1186] Input: Recommended Artwork

[1187] Output: Display of artwork on user device

[1188] Step 6:

[1189] By wearing the smart glasses, users can visually experience recommended artworks in real time. For example, when visiting a physical store, they can scan a specific area and artworks generated by the server will appear on the glasses' display.

[1190] Input: Recommended Artwork

[1191] Output: Artwork displayed on smart glasses

[1192] These are the processing steps of this system, which allows users to easily find artworks that suit their tastes and enjoy them visually in real time.

[1193] 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.

[1194] The system of the present invention recommends personalized art based on a user's preference information and emotional state, and analyzes the user's preferences and current emotional state to provide the most suitable artwork. The system includes a means for receiving and storing user preference information, a generative artificial intelligence for analyzing the data, an emotion engine, and a means for generating or selecting and providing artwork based on the analysis results.

[1195] User information acquisition

[1196] After logging in to the system, users enter their preferences. Specifically, they enter their favorite art style, favorite colors, names of artists they often watch, and so on into an input form. The system also activates an emotion engine to recognize the user's emotional state. The emotion engine obtains the user's current emotional state through facial expression analysis, voice analysis, and biometric information (such as heart rate).

[1197] User information transmission and storage

[1198] After the user inputs their preference information and the emotion engine collects their emotional data, the device compiles this data and sends it to the server. The server analyzes the received data and stores it in a database. By storing it, the user's preference information and emotional state can be referenced in future uses.

[1199] Data analysis

[1200] The server performs data analysis based on the preference information and emotional state stored in the database. This analysis uses a generative AI model to identify individual characteristics based on the user's preference patterns and current emotional state. For example, if a user likes "Impressionist" art and often likes the color "blue," but is currently feeling stressed, these factors will be taken into account when conducting the analysis.

[1201] Art recommendation generation

[1202] The server generates or selects from an existing database a suitable artwork for the user based on the preference patterns and emotional state identified by the generative AI model. The server can recommend a calming landscape painting with impressionist blue tones to help the user relax.

[1203] Return and provision of results

[1204] The server generates a list of recommended artworks and sends it to the device as an HTTP response. The device analyzes the received art recommendation list and displays it in a user-friendly format. The user can browse the recommended artworks and bookmark the ones they like. They can also click to view more detailed information.

[1205] Specific examples

[1206] As a specific example, suppose a user logs in and enters their preference information as "Impressionism," "blue color," and "frequently viewed artist: Monet." At the same time, the emotion engine analyzes the user's facial expressions and heart rate and recognizes that the user is feeling stressed. The server receives this information and generates artworks that match the user's preferences and current emotional state based on past records stored in the database and the generative AI model. For example, a recommendation list might include "serene landscapes with a Monet-esque blue theme." This list is sent to the device and displayed to the user. The user can view the recommended artworks and spend a pleasant time.

[1207] As described above, this system greatly enhances the art appreciation experience by personalizing artworks based on the user's preferences and emotional state, allowing users to easily find artworks that match their tastes and emotions and relieve daily stress.

[1208] The processing flow will be explained below.

[1209] Step 1:

[1210] A user logs into the system. The user enters their login information and, if authentication is successful, a user session begins.

[1211] Step 2:

[1212] The user enters their preferences, such as "favorite art style," "favorite color," and "frequently watched artists," into an input form.

[1213] Step 3:

[1214] The emotion engine is activated to recognize the user's emotional state in real time by analyzing the user's facial expressions, voice tone, and biometric information (e.g., heart rate).

[1215] Step 4:

[1216] The device compiles preference information and emotion data into a data structure in JSON format or similar, which is then formatted for easy analysis in subsequent processing.

[1217] Step 5:

[1218] The device sends the formatted data structure to the server as an HTTP request, which includes the user's preference information and emotion data.

[1219] Step 6:

[1220] The server analyzes the received HTTP request, extracts preference information and emotion data from the request body, and stores them in a database.

[1221] Step 7:

[1222] The server retrieves the user's preference information and emotional data stored in the database and begins analysis. Using a generative AI model, it identifies the user's preference patterns and current emotional state.

[1223] Step 8:

[1224] The generative AI model generates or selects the most suitable artwork for the user based on the identified preference patterns and emotional state. The server generates a new artwork or selects the most suitable artwork from an existing database.

[1225] Step 9:

[1226] The server compiles a list of generated or selected artworks into a recommendation list, which also includes the reason for the recommendation and related information.

[1227] Step 10:

[1228] The server sends the created recommendation list to the terminal as an HTTP response, which includes detailed information about the recommended artworks.

[1229] Step 11:

[1230] The device analyzes the HTTP response received and displays a list of recommendations in an easy-to-read format for the user.

[1231] Step 12:

[1232] Users can browse recommended artworks and bookmark their favorites. Users can also click on artworks to view additional information for more details.

[1233] Specific examples

[1234] Suppose a user logs in and enters their preferences, such as "Impressionism," "blue," and "Favorite Artist: Monet." At the same time, the emotion engine analyzes the user's facial expressions and heart rate and recognizes that the user is relaxed. The server receives this information and generates artworks that match the user's preferences and current emotional state based on past records stored in the database and the generative AI model. For example, a recommendation list might be generated that includes "serene landscapes with a Monet-esque blue theme." This list is sent to the device and displayed to the user. The user can browse these recommended artworks and spend a pleasant time.

[1235] As described above, this system greatly enhances the art appreciation experience by personalizing artworks based on the user's preferences and emotional state, allowing users to easily find artworks that match their tastes and emotions and relieve daily stress.

[1236] Example 2

[1237] 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."

[1238] Conventional art recommendation systems only consider user preference information and do not reflect the user's current emotional state, making it difficult to provide artworks that suit the user's psychological state. Furthermore, they are limited to static selection of artworks and lack the ability to generate new artworks. This makes it difficult to sufficiently increase user satisfaction.

[1239] 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.

[1240] In this invention, the server includes means for receiving user preference information, means for saving the received preference information, means for analyzing the saved preference information and the user's emotional state and identifying the preference pattern and the emotional state using a generative artificial intelligence to analyze the saved preference information and the user's emotional state, means for generating or selecting an artwork suited to the user based on the identified preference pattern and the emotional state, and means for providing the generated or selected artwork to the user, thereby making it possible to provide the optimal artwork based on the user's preferences and current emotional state.

[1241] "Preference information" refers to user-specified preferred art styles, colors, artist names, and past browsing history.

[1242] "Emotional state" is information that indicates the user's current emotional and psychological state, and is collected from facial expression analysis, voice analysis, and biometric information (heart rate, etc.).

[1243] "Generative AI" is a general term for AI technology that uses machine learning algorithms and AI models to analyze data and generate new information and objects.

[1244] "Data analysis means" refers to techniques and methods for analyzing stored preference information and emotional states to extract specific patterns and characteristics.

[1245] "Generative means" refers to the methods and techniques used to create new artworks based on the analyzed information.

[1246] "Selection method" refers to the method or technology used to select the most suitable artwork from the existing database based on the analyzed information.

[1247] "Delivery means" refers to the technology or method for visually displaying the generated or selected artwork to the user.

[1248] The system of the present invention recommends personalized art based on a user's preference information and emotional state, and provides the most suitable artwork by analyzing the user's preferences and current emotional state. The system includes a means for receiving and storing user preference information, a generative artificial intelligence for analyzing the data, an emotion engine, and a means for generating or selecting and providing artwork based on the analysis results.

[1249] Users log in to the system using their devices and enter their preferences. Specifically, they enter their art style, favorite colors, and names of artists they often visit into an input form. The system also uses an emotion engine to obtain the user's current emotional state through facial expression analysis, voice analysis, and biometric information (such as heart rate). The emotion engine includes facial expression analysis using the OpenCV library, voice analysis using the Librosa library, and real-time heart rate data collection.

[1250] The device combines the user's input preference information and the emotion data acquired by the emotion engine into a single packet and sends it to the server as an HTTP POST request. The server analyzes the received data and stores it in a database (MongoDB). The stored data is used for subsequent analysis and reference.

[1251] The server performs data analysis based on the stored preference information and emotional state. This analysis utilizes generative artificial intelligence, with a generative AI model (using TensorFlow) identifying individual characteristics based on the user's preference patterns and current emotional state. For example, if a user likes "Impressionist" art, has a history of using the color "blue," and is currently feeling stressed, these factors will be taken into account in the analysis.

[1252] Based on the analysis results, the server generates the most suitable artwork using a generative AI model or selects one from an existing database. An example of a generated prompt is, "User preference information: Impressionism, blue color, popular artists. Current emotional state: stress. Please recommend the most suitable artwork based on this."

[1253] The server generates a list of recommended artworks and sends it to the device as an HTTP response. The device analyzes the received art recommendation list and displays it on the screen in a format that is easy for the user to view. The user can view the recommended artworks and bookmark the ones they like. The user can also click to view more detailed information.

[1254] For example, suppose a user logs in and enters their preferences, such as "Impressionist," "blue," and "frequently viewed artists." At the same time, the emotion engine analyzes the user's facial expressions and heart rate and recognizes that the user is feeling stressed. The server receives this information and, based on past records stored in the database and the generative AI model, generates artworks that match the user's preferences and current emotional state. For example, a recommendation list might include "serene landscape paintings with blue Impressionist tones." This list is sent to the device and displayed to the user. The user can browse these recommended artworks and spend a pleasant time.

[1255] As described above, this system significantly improves the art appreciation experience by personalizing artworks based on the user's preferences and emotional state, allowing users to easily find artworks that match their tastes and emotions, helping to relieve everyday stress.

[1256] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1257] Step 1: Obtain user information

[1258] Users log in to the system and enter their preferences, such as their favorite art style, favorite colors, and the names of artists they often visit, into an input form. This input form is web-based, and the data entered by the user is sent to the device in JSON format. The device then uses its camera and microphone to activate the emotion engine. The emotion engine uses OpenCV to analyze the user's facial expressions and Librosa to analyze audio data. Biometric information, such as heart rate, is also collected in real time from the smartwatch. All of this data is compiled into emotional state data.

[1259] Input: User preference information (art style, color, artist name), facial expression data, voice data, biometric information

[1260] Output: Analyzed preference information and emotional state data

[1261] Step 2: Send and save user information

[1262] The device combines the user's input preferences and the emotional state data collected by the emotion engine into a single JSON packet. The combined data is then sent to the server as an HTTP POST request. The server receives the data and performs initial analysis using the Pandas library. The data is then stored in MongoDB, where it can be retained for future reference and analysis.

[1263] Input: A JSON packet containing preference information and emotional state data

[1264] Output: Parsed data stored in a database

[1265] Step 3: Data analysis

[1266] The server references the user's preference information and emotional state data stored in MongoDB and performs data analysis. A generative AI model is used for the analysis, using the TensorFlow library. The generative AI model uses this data to identify the user's preference patterns and current emotional state. For example, if a user likes "Impressionist" art, values ​​the color "blue," and is currently feeling stressed, the model combines these factors to perform an analysis.

[1267] Input: Preference information and emotional state data stored in a database

[1268] Output: Analysis results based on user preference patterns and emotional state

[1269] Step 4: Art recommendation generation

[1270] Based on the analysis results, the server uses a generative AI model to generate the most suitable artwork or select one from an existing database. An example of a generated prompt is, "User's preferences: Impressionism, blue, popular artists. Current emotional state: stress. Please recommend the most suitable artwork based on this." This generates or selects the artwork that best suits the user's preferences and emotional state.

[1271] Input: Analysis results of user preference patterns and emotional state

[1272] Output: A list of recommended artworks

[1273] Step 5: Return and provide results

[1274] The server generates a list of recommended artworks in JSON format and sends it to the device as an HTTP response. The device parses the received JSON data and displays it in a user-friendly format on the web browser. The user can browse the recommended artworks and bookmark their favorites. They can also click to view detailed information. This allows users to easily find artworks that match their tastes and emotional state.

[1275] Input: JSON data containing a list of recommended artworks

[1276] Output: A list of artworks visually displayed to the user

[1277] (Application example 2)

[1278] 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."

[1279] In modern society, it is difficult to select meals that match the individual preferences and emotional state of users, so methods to improve user satisfaction are required in food delivery services.In addition, because there are few personalized meal suggestions that reflect the user's preferences and emotional state, there is a lack of services that meet the needs of users, such as relaxation and health improvement, especially in stressful environments.

[1280] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving user preference information, means for saving the received preference information, data analysis means using generative artificial intelligence to analyze the saved preference information and emotional state and identify the user's preference pattern and emotional state, means for generating or selecting a meal suited to the user based on the identified preference pattern and emotional state, and means for providing the generated or selected meal to the user. This makes it possible to provide meals that suit the user's individual preferences and emotional state, which is expected to not only improve user satisfaction but also have effects such as maintaining health and reducing stress.

[1281] "Preference information" is information about the preferences of individual users, such as the user's favorite cuisine genres, specific ingredients, and the history of meals ordered in the past.

[1282] "Emotional state" refers to the user's current psychological or physiological state, and is information obtained through facial expression analysis, voice analysis, and biometric information (such as heart rate).

[1283] "Generative AI" is an AI that analyzes the user's preference patterns and emotional state based on the received data and generates new meal menus.

[1284] The "data analysis means" is a means for performing analysis based on the preference information and emotional state received from the user, and for suggesting the most suitable meal for the user.

[1285] A "meal generation or selection means" is a means for using artificial intelligence to generate a meal menu tailored to the user based on the identified preference patterns and emotional state, or for selecting from an existing menu.

[1286] "Means for storing" refers to means for storing the received user preference information and emotional state in a database for future use.

[1287] The "means for providing" is a means for transmitting the generated or selected meal menu to the user's terminal and displaying it.

[1288] The system of the present invention recommends personalized meals based on a user's preference information and emotional state. To provide optimal meal menus by analyzing a user's preferences and current emotional state, the system operates as follows: Specifically, the system includes the steps of acquiring user information, transmitting and saving data, analyzing the data, generating meal recommendations, and returning and providing the results.

[1289] User information acquisition

[1290] After logging in to the system, the user enters their preference information. Specifically, the user enters their preferred cuisine genre (e.g., Italian, Japanese, Chinese, etc.), specific ingredients, and past meal ordering history into an input form. The system also activates an emotion engine to recognize the user's emotional state. The emotion engine obtains the user's current emotional state through facial expression analysis using the smartphone camera, voice analysis using the microphone, and biometric information (heart rate, etc.) using a wearable device.

[1291] Data transmission and storage

[1292] After the user inputs their preference information and the emotion engine collects their emotional data, the device compiles this data and sends it to the server. The server analyzes the received data and stores it in a database. By storing it, the user's preference information and emotional state can be referenced in future uses.

[1293] Data analysis

[1294] The server performs data analysis based on the preference information and emotional state stored in the database. This analysis uses a generative AI model to identify individual characteristics based on the user's preference patterns and emotional state. For example, if a user likes Italian food, has a history of ordering a lot of pasta dishes in the past, and is currently feeling stressed, the analysis will take these factors into account.

[1295] Food recommendation generation

[1296] The server generates or selects from an existing database a meal plan tailored to the user based on the preference patterns and emotional state identified by the generative AI model. The server can recommend healthy Italian dishes or menus containing ingredients with stress-reducing properties to help the user relax.

[1297] Return and provision of results

[1298] The server generates a list of recommended food menus and sends it to the device as an HTTP response. The device analyzes the received food recommendation list and displays it in a user-friendly format. The user can browse the recommended menus and order the meals they like.

[1299] Examples and prompts

[1300] As a specific example, suppose a user logs in and enters their preference information as "Italian," "Pasta," and "Previously ordered menu: Carbonara." At the same time, the emotion engine analyzes the user's facial expressions and heart rate and recognizes that the user is feeling stressed. The server receives this information and generates a meal menu that matches the user's preferences and current emotional state based on past records stored in the database and the generative AI model. For example, a recommendation list of "Carbonara-style pasta served with relaxing herbal tea" is generated. This list is sent to the device and displayed to the user. The user can view the recommended menu and place an order.

[1301] Example prompt sentence:

[1302] "User's favorite dishes: pasta, salad. Current emotional state: stress. Generate a healthy and relaxing menu."

[1303] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1304] Step 1: Enter your user information

[1305] Input: A user logs into the application and enters their preferences (e.g., favorite cuisines, specific ingredients, past orders, etc.).

[1306] How it works: The device receives preference information through an input form and temporarily stores it.

[1307] Output: Preference information is saved on the device.

[1308] Step 2: Obtaining emotional states

[1309] Input: User's facial expressions, voice, and biometric information (heart rate, etc.).

[1310] How it works: The device captures facial expressions with a built-in camera and analyzes them using the emotion engine. It also records audio with a microphone and acquires biometric information from the wearable device.

[1311] Output: Emotional state data analyzed on the device.

[1312] Step 3: Sending data

[1313] Input: Stored preference information and retrieved emotional state data.

[1314] Operation: The device sends this data to the server.

[1315] Output: Preference information and emotional state data are sent to the server.

[1316] Step 4: Save your data

[1317] Input: Preference information and emotional state data sent to the server.

[1318] How it works: The server stores the received data persistently in a database.

[1319] Output: Preference information and emotional state data stored in a database.

[1320] Step 5: Analyze the data

[1321] Input: Preference information and emotional state data stored in a database.

[1322] How it works: The server uses a generative AI model to analyze preference patterns and emotional states. For example, if a user likes Italian food and is feeling stressed, it makes a calculation based on this information.

[1323] Output: Analysis results based on preference patterns and emotional states.

[1324] Step 6: Generate or select a meal menu

[1325] Input: Analysis of preference patterns and emotional states.

[1326] How it works: Based on the analysis results, the server uses a generative AI model to generate a new meal menu or select the best option from an existing menu.

[1327] Output: A list of recommended meals is generated.

[1328] Step 7: Returning the results

[1329] Input: A list of recommended meals.

[1330] Operation: The server sends the generated recommended menu list to the terminal as an HTTP response.

[1331] Output: A list of recommended meals is sent to the device.

[1332] Step 8: Viewing the results

[1333] Input: A list of recommended meals.

[1334] How it works: The device analyzes the received meal recommendation list and displays it in an easy-to-read format for the user.

[1335] Output: The user can view a list of recommended meals.

[1336] Step 9: Complete your order

[1337] Input: The meal selected by the user.

[1338] Operation: The user selects the menu item they like and completes the order. The terminal sends the order information to the server.

[1339] Output: The order information is sent to the server and the order is received.

[1340] These steps allow users to easily select and order the meal that best suits their tastes and emotional state.

[1341] 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.

[1342] 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.

[1343] 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.

[1344] 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.

[1345] 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.

[1346] 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.

[1347] 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).

[1348] 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.

[1349] 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."

[1350] 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.

[1351] 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).

[1352] 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.

[1353] 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.

[1354] 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.

[1355] 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.

[1356] 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.

[1357] 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.

[1358] 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.

[1359] 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.

[1360] 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.

[1361] 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.

[1362] The following is further disclosed regarding the above embodiment.

[1363] (Claim 1)

[1364] means for receiving user preference information;

[1365] means for storing the received preference information;

[1366] a data analysis means utilizing generative artificial intelligence to analyze the stored preference information and identify the user's preference patterns;

[1367] means for generating or selecting artwork tailored to the user based on the identified preference patterns;

[1368] means for providing a generated or selected artwork to a user;

[1369] A system including:

[1370] (Claim 2)

[1371] The system of claim 1 , wherein a generative artificial intelligence generates new artwork based on the analyzed preference information.

[1372] (Claim 3)

[1373] 10. The system of claim 1, wherein the user-entered preference information includes a favorite color, a favorite artist, and a history of artworks viewed in the past.

[1374] "Example 1"

[1375] (Claim 1)

[1376] means for receiving user preference information;

[1377] means for storing the received preference information;

[1378] a data analysis means utilizing generative artificial intelligence to analyze the stored preference information and identify the user's preference patterns;

[1379] means for generating or selecting artwork tailored to the user based on the identified preference patterns;

[1380] means for providing a generated or selected artwork to a user;

[1381] A system including:

[1382] (Claim 2)

[1383] The system of claim 1, wherein the generative artificial intelligence generates new artwork based on the analyzed preference information.

[1384] (Claim 3)

[1385] 2. The system of claim 1, wherein the preference information input by the user includes a favorite color, a favorite artist, and a history of artworks viewed in the past.

[1386] (Claim 4)

[1387] 2. The system according to claim 1, further comprising means for transmitting the generated art recommendation list to the terminal as an HTTP response, the terminal receiving the list and displaying it to the user.

[1388] "Application Example 1"

[1389] (Claim 1)

[1390] means for receiving user preference information;

[1391] means for storing the received preference information;

[1392] a data analysis means utilizing generative artificial intelligence to analyze the stored preference information and identify the user's preference patterns;

[1393] means for generating or selecting artwork tailored to the user based on the identified preference patterns;

[1394] means for providing a generated or selected artwork to a user;

[1395] means for visually presenting the artwork on a user-specific display device;

[1396] A system including:

[1397] (Claim 2)

[1398] The system of claim 1 , wherein a generative artificial intelligence generates new artwork based on the analyzed preference information.

[1399] (Claim 3)

[1400] 10. The system of claim 1, wherein the user-entered preference information includes a favorite color, a favorite artist, and a history of artworks viewed in the past.

[1401] (Claim 4)

[1402] 10. The system of claim 1, wherein the user-specific display device is a pair of smart glasses.

[1403] "Example 2: Combining Emotion Engines"

[1404] (Claim 1)

[1405] means for receiving user preference information;

[1406] means for storing the received preference information;

[1407] a data analysis means utilizing generative artificial intelligence to analyze the stored preference information and the user's emotional state and identify preference patterns and emotional states;

[1408] means for generating or selecting a piece of artwork tailored to the user based on the identified preference patterns and emotional state;

[1409] means for providing a generated or selected artwork to a user;

[1410] A system including:

[1411] (Claim 2)

[1412] The system of claim 1 , wherein the generative artificial intelligence generates new artwork based on the analyzed preference information and emotional state.

[1413] (Claim 3)

[1414] 10. The system of claim 1, wherein the user-entered preference information includes a favorite color, a favorite artist, and a history of artworks viewed in the past, and the emotional state includes facial expression analysis, voice analysis, and biometric information.

[1415] "Application example 2 when combining emotion engines"

[1416] (Claim 1)

[1417] means for receiving user preference information;

[1418] means for storing the received preference information;

[1419] a data analysis means utilizing generative artificial intelligence to analyze the stored preference information and emotional state and identify the user's preference patterns and emotional state;

[1420] means for generating or selecting a meal tailored to the user based on the identified preference patterns and emotional state;

[1421] means for providing the generated or selected meal to the user;

[1422] A system including:

[1423] (Claim 2)

[1424] The system of claim 1 , wherein the generative artificial intelligence generates new meal menus based on the analyzed preference information and emotional state.

[1425] (Claim 3)

[1426] 10. The system of claim 1, wherein the user-entered preference information includes a preferred cuisine genre, specific ingredients, a history of past meal orders, and an emotional state. [Explanation of symbols]

[1427] 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 user preference information; means for storing the received preference information; a data analysis means utilizing generative artificial intelligence to analyze the stored preference information and identify the user's preference patterns; means for generating or selecting artwork tailored to the user based on the identified preference patterns; means for providing a generated or selected artwork to a user; A system including:

2. The system of claim 1 , wherein a generative artificial intelligence generates new artwork based on the analyzed preference information.

3. The system of claim 1 , wherein the user-entered preference information includes a favorite color, a favorite artist, and a history of artworks viewed in the past.

Images