system

Abstract

We provide the system. [Solution] A means for collecting data on artworks and analyzing that data, A means for collecting user preference data and generating recommendation content based on said preference data, A means of presenting artworks to users using the analysis results and recommendations, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the art market, it is difficult to accurately capture the preferences of individual users and market trends, and human bias may be involved in the curation of artworks. Also, extracting relevant works efficiently from a vast number of artworks requires time and effort. In view of these problems, there is a need for a system that selects works from a new perspective and realizes an individualized exhibition experience.

Means for Solving the Problems

[0005] This invention provides a system that enables efficient and unbiased selection of artworks by including means for collecting and analyzing data on artworks, means for collecting user preference data and generating recommendations based on that preference data, and means for presenting artworks to users using the analysis results and recommendations. Furthermore, by adding means for analyzing past exhibition history and market trends, and means for collecting user feedback and improving the accuracy of recommendations, the invention provides a more personalized experience and solves various challenges in the art market.

[0006] "Works of art" are created as part of the visual or sculptural arts, and include paintings, sculptures, photographs, and other forms.

[0007] "Data collection methods" refer to technologies and methods for acquiring information from external databases or networks and storing it within a system.

[0008] "Data analysis methods" refer to analytical methods and techniques used to reveal specific patterns, trends, and characteristics based on acquired information.

[0009] "Preference data" refers to information that indicates a user's interests and concerns, and includes information based on past behavior, preferences, and browsing history.

[0010] "Recommendations" refer to a list of artworks and information selected and presented to the user by the system based on the user's preferences and analysis results.

[0011] "Feedback" refers to the evaluations and comments that users give to the information and services provided by a system, and is used to improve the system.

[0012] "Analysis results" refer to the results of analysis obtained through data analysis methods, and include characteristics of the artwork and market trends.

[0013] "Presentation methods" refer to methods and technologies for displaying generated information or selected content in an easily understandable way to the user.

[0014] "Exhibition history" refers to records of past public displays and exhibitions of artworks, including the method, timing, and location of the exhibition.

[0015] "Trend analysis methods" refer to analytical methods and techniques used to predict market and user trends. [Brief explanation of the drawing]

[0016] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12]It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0018] First, the language used in the following description will be explained.

[0019] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), etc.

[0020] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0036] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0037] This invention provides a system for selecting, recommending, and providing personalized displays of artworks for users. This system consists of a server, terminals, and users, which work together in coordination.

[0038] The server first collects data on artworks provided by various museums and galleries. This includes images of the artworks, artist information, and exhibition history. The server then analyzes the collected data and automatically extracts the characteristics of the artworks. This analysis includes extracting iconographic features using image recognition and text analysis using natural language processing.

[0039] Furthermore, the server collects user preference data. This data collection is done when users provide their interests and past browsing history through their devices. Based on this preference data, the server generates personalized recommendations and proposes a unique exhibition experience for each user.

[0040] The terminal displays analysis results and recommendation information provided by the server to the user. The user can then view the artworks and exhibition routes provided through their terminal and proceed with their art appreciation based on their interests.

[0041] As a concrete example, a user logs into the AI ​​art curator using their device and sets their preferences and interests. Based on these settings, the server suggests the most suitable exhibition content from a vast database of art works. For example, if a user is interested in Impressionism, the system will combine past trends and new works in the same genre to generate a unique exhibition route.

[0042] Furthermore, feedback provided by users after viewing a work is collected and analyzed by the server and used to improve the system. This feedback analysis improves the accuracy of recommendations for that user, resulting in a more enriching viewing experience next time.

[0043] In this way, the present invention makes it possible to provide visitors to museums and galleries with an efficient and personalized art appreciation experience.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The server accesses databases of partner museums and galleries to collect data including images of artworks, artist information, and exhibition history. After collection, this data is deduplicated and inaccurate information is removed, and it is formatted in a way that allows for analysis.

[0047] Step 2:

[0048] The server analyzes the collected art data. Image recognition technology is used to identify the color tone and style of the artworks, and text analysis technology is used to extract themes and background information from descriptions and reviews. This process allows the characteristics of each artwork to be stored in a database.

[0049] Step 3:

[0050] The device collects preference data from the user. This data includes information such as works the user has watched in the past and artists and genres the user is interested in. The device sends this information to the server.

[0051] Step 4:

[0052] The server combines accumulated artwork characteristic data with user preference data to generate a list of artworks best suited to the user. The generated list includes artworks related to the user's interests and artworks based on current trends.

[0053] Step 5:

[0054] The terminal displays a list of artworks and related information received from the server to the user. Through the interface, the user can view details of the artworks and select a recommended viewing route.

[0055] Step 6:

[0056] Users provide feedback on the works they have viewed through their devices, including their impressions and evaluations. This feedback is sent to the server and reflected in the database to improve the accuracy of future recommendations.

[0057] Step 7:

[0058] The server continuously improves the system using collected feedback and trend analysis results, and incorporates these improvements into future recommendations. This enhances the user experience and refines the recommendation system.

[0059] (Example 1)

[0060] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0061] In contemporary art appreciation, there is a need to quickly provide personalized recommendations tailored to the diverse preferences of users. However, traditional methods have struggled to accurately analyze the characteristics of artworks and generate recommendations that resonate with user preferences. Furthermore, effective recommendations that consider exhibition history and market trends have been limited. Designing systems that accurately reflect user feedback has also been challenging. Solving these challenges is essential.

[0062] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0063] In this invention, the server includes means for collecting information on artworks and extracting features from said information using image and text analysis; means for collecting information on the user's interests and generating personalized recommendation information based on said information; and means for providing artworks on a display device using said features and recommendation information. This makes it possible to recommend artworks that take into account the user's tastes and preferences. Furthermore, by analyzing exhibition history and market trends, more appropriate recommendations can be made, and a highly accurate recommendation system can be realized by accurately reflecting user feedback.

[0064] An "artwork" is a visual expression created to be appreciated through sight or other senses, and can take the form of painting, sculpture, photograph, or other similar media.

[0065] "Information" is a collection of data and knowledge that can be expressed in a form that computers and humans can understand, and includes forms such as text, images, and audio.

[0066] "Characteristics" refer to unique properties or attributes extracted from artworks or data, serving as criteria for identification and classification.

[0067] "Users" refers to individuals or groups who use the system or service, and in particular, those who are interested in art appreciation.

[0068] "Interest" refers to the degree of a user's interest in a particular subject or theme, and includes preferences that influence the selection of artworks.

[0069] "Recommendation information" refers to information provided as personalized suggestions or advice, generated based on the user's preferences and past behavior.

[0070] A "display device" refers to equipment or software used to provide information to users visually, and includes computer monitors and smartphone screens.

[0071] "Exhibition history" refers to a record of past exhibitions of artworks, including information such as the location and duration of the exhibition.

[0072] "Market trends" refer to specific tendencies and shifts in popularity observed over time within the art industry.

[0073] "Reactions" refer to the comments and evaluations that users provide after viewing an artwork, and these are used to improve the system.

[0074] "Accuracy" is a measure of how well the recommendation information generated by the system matches the user's expectations, and it serves as an indicator of reliability.

[0075] This invention relates to an information processing system for personalizing the appreciation of artworks and providing users with an optimal exhibition experience. In particular, it is realized through the collaboration of a server, a terminal, and the user, each playing their respective roles.

[0076] Server Role

[0077] The server first collects information about artworks from museums and galleries via APIs and data feeds. This information includes high-resolution images of the artworks, artist information, and past exhibition history. The HTTP protocol is used for this data collection. Next, machine learning libraries such as TENSORFLOW® or PyTorch are used to extract features such as color, composition, and style from the collected image data using image recognition models. Furthermore, NLTK or spaCy is used for natural language processing to analyze related text data and extract the artist's style and the theme of the artwork.

[0078] The server then uses collaborative filtering and content-based filtering to generate personalized recommendations tailored to the user's interests. At this stage, it takes into account the user's past browsing history and interests to calculate the optimal artwork and exhibition route.

[0079] Terminal role

[0080] The terminal visually presents the server-generated recommendation information to the user. The interface on the terminal allows users to customize their interests in detail using checkboxes and sliders. Artwork is displayed in a list with thumbnail images, and users can view detailed information by clicking on works of interest. This process utilizes databases such as SQLite and Realm, enabling rapid data access and display.

[0081] User roles

[0082] Users select works of art that interest them and check the exhibition route based on the information provided on their device. After viewing the art, they can use the feedback function to input their evaluation and impressions of the artwork. This feedback is sent to the server and contributes to improving the accuracy of the next event.

[0083] Specific example

[0084] For example, if a user enters a prompt such as, "Please create a recommended exhibition route for me, including new Impressionist works," the server interprets this and generates an optimal exhibition route that takes the user's interests into account. This route is displayed step-by-step on the terminal, and the user can use it as a guide for viewing the artworks.

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

[0086] Step 1:

[0087] The server collects information on artworks from museums and galleries using APIs and data feeds. As input, it receives data in JSON or XML format provided by each institution via HTTP requests. This data includes images of the artwork, artist information, and past exhibition history. As output, this data is integrated into the server's database and used in the next analysis step. Specifically, the server periodically accesses each data source to update new artwork information.

[0088] Step 2:

[0089] The server analyzes the collected image data using machine learning libraries such as TensorFlow and PyTorch to extract visual features. Image data of artworks stored in a database is used as input. For data processing, an image recognition model extracts features such as color, composition, and style from the images. As output, feature vectors for each artwork are generated and stored in a table. For example, Impressionist works are identified as having softer color tones and brushwork than usual.

[0090] Step 3:

[0091] The server analyzes collected artist information and exhibition history using natural language processing. Text data stored in a database is used as input. Tools such as NLTK and spaCy are used for data analysis to extract the artist's style and themes. Keywords and topics related to each artist and their works are generated as output. Specifically, frequently occurring phrases are extracted from the artist's biography and review articles, and their relevance is evaluated.

[0092] Step 4:

[0093] The device collects information about the user's interests and sends it to the server. The input includes the user's selected art genres and interests in specific artists. The device receives this information through UI elements such as forms and sends it to the server. The output is the user's interest data, which is stored on the server and used in the next recommendation generation step. A concrete example is when a user inputs that they are interested in "Impressionism."

[0094] Step 5:

[0095] The server generates recommendation information using collaborative filtering and content-based filtering based on user interest data. User preference data and artwork characteristic data are used as input. Data processing involves collaborative filtering based on the preference history of similar users and content-based filtering based on feature vectors. As output, a personalized list of recommended artworks is generated and sent to the terminal. Specifically, it analyzes patterns of users who have previously highly rated Impressionist works to determine new Impressionist recommendations.

[0096] Step 6:

[0097] The terminal displays recommendation information provided by the server to the user. The input is a list of recommendations from the server. The terminal displays this in the UI, presenting it in an interactive format. The output allows the user to view details of the recommended works and decide which one to view next. For example, the user can click on a thumbnail to view detailed information about the artwork and the artist's background.

[0098] Step 7:

[0099] After viewing a work, users enter feedback into their device and send it to the server. As input, user impressions and ratings are collected through the device. This information is sent to the server and used to refine the recommendation algorithm. As output, feedback data is stored on the server and used to improve the accuracy of future recommendations. Specifically, users may rate the work on a 5-point scale and add specific comments.

[0100] (Application Example 1)

[0101] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0102] Contemporary museums and galleries fail to adequately provide visitors with information on art pieces tailored to their individual interests and to personalize their viewing experience. As a result, users cannot easily find art pieces that suit their interests, limiting the quality of their viewing experience. Furthermore, providing real-time information and suggesting dynamic exhibition routes that incorporate user feedback is challenging.

[0103] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0104] In this invention, the server includes means for collecting and analyzing information on artworks, means for collecting user interest data and generating recommendations based on that interest data, means for presenting artwork information to the user via a visual device using the analysis results and recommendations, and means for acquiring user gaze information and displaying relevant information on the visual device's display in real time. This makes it possible to recommend artworks tailored to the user's individual interests and provide an immersive viewing experience through real-time information presentation.

[0105] "Information about artworks" refers to data such as image data related to the artwork, information about the creator, and exhibition history.

[0106] "Means of analysis" refers to a function that analyzes information on collected artworks and automatically extracts their characteristics.

[0107] "User interest data" refers to data that shows a user's interests, preferences, and past browsing history.

[0108] "Means for generating recommendations" refers to a function that recommends appropriate artworks and exhibition routes based on collected user interest data.

[0109] "Visual devices" refer to visual information presentation devices that users wear and use, such as smart glasses and head-mounted displays.

[0110] "Acquiring eye-tracking information" refers to sensing the user's eye movements and the direction they are focusing on, and acquiring this information as data.

[0111] "Means of displaying related information in real time" refers to a function that instantly presents related artworks and information based on the user's eye-tracking data and interest data.

[0112] An embodiment of this invention is a system that utilizes a visual device to optimize and personalize art appreciation for a user. This system consists of a server, a visual device worn by the user, and the user themselves.

[0113] The server first collects information about artworks from museums and galleries. This includes image data of the artworks, information about the artists, and past exhibition history. The server then uses image recognition technology (e.g., Google® Cloud Vision API) to analyze the features of the artworks and extract feature data. Furthermore, it collects interest data entered by users using visual devices, past browsing history, and feedback, and analyzes this information using natural language processing (e.g., Google Natural Language API) to generate recommendations.

[0114] Visual devices (e.g., smart glasses) use artwork information and recommendations received from a server to display relevant information in real time within the user's field of view. These devices are equipped with cameras and sensors to capture the user's gaze, and this data is sent to the server to help guide the user's interests.

[0115] For example, when a user visits a museum and looks at a nearby Impressionist painting, the device recognizes the painting, displays detailed information, and recommends other related works of art. This experience allows the user to make new discoveries and gain a deeper understanding and enjoyment on subsequent visits.

[0116] An example of a prompt might be, "How can I create a real-time art guide assistant that provides detailed information about Impressionist paintings in the art gallery I'm visiting?"

[0117] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0118] Step 1:

[0119] The server collects information on artworks from museums and galleries. It receives image data, artist information, and exhibition history as input. This information is stored in a database for later analysis.

[0120] Step 2:

[0121] The server analyzes the collected artwork information using image recognition technology. It takes image data as input and extracts characteristic data of the artworks as output. Specifically, it uses the Google Cloud Vision API to identify the color, shape, and style of each artwork and assign tags to them.

[0122] Step 3:

[0123] The server collects user interest data. It receives user interests and browsing history provided via visual devices as input. As output, it analyzes this data to generate a user profile, specifically revealing preferences based on user choices and feedback.

[0124] Step 4:

[0125] The server generates recommendations using an AI model based on user profiles. It takes user profiles and artwork characteristic data as input and generates recommended artworks and exhibition routes as output. Utilizing natural language processing, it precisely combines diverse artwork information to provide users with personalized recommendations.

[0126] Step 5:

[0127] The terminal, or visual device, displays recommendations provided by the server in real time within the user's field of view. It receives recommended artwork information as input and provides details of the artwork, partially overlaid. The output enhances user immersion and enriches the viewing experience.

[0128] Step 6:

[0129] When users view artwork through their visual devices, their gaze information is acquired by the terminal. As an initial input, this gaze data is sent to a server and used for analyzing works of interest. As an output, new preference data is generated from the user's gaze, contributing to the optimization of future exhibition recommendations.

[0130] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0131] This invention relates to a system that collects data on artworks and provides personalized recommendations using preference data and user emotions. The system includes a server, terminals, and an emotion engine, all of which work together.

[0132] The server first collects artwork data from various museums and galleries, storing images, artist information, exhibition history, and other information in a database. This makes it possible to manage large amounts of artwork information efficiently and systematically.

[0133] Next, the server analyzes the characteristics of the artwork based on the collected art data. It extracts the visual features of the artwork using image recognition technology and further analyzes related information using text analysis technology. This information is used as the basis for the recommendation algorithm.

[0134] The device collects preference and emotional data from the user. Users not only input their interests and past browsing history through the device, but also use a video camera and microphone equipped with an emotion engine to acquire visual and auditory emotional information. This emotional information is considered valuable data indicating how the user felt about different works.

[0135] The server combines preference and emotional data sent from the terminal to generate a list of the most suitable artworks for the user. In particular, the emotional state captured by the emotion engine is used to fine-tune the recommendations, prioritizing artworks that resonate more emotionally with the user.

[0136] As a concrete example, a user accesses an art curation application through their device and selects their favorite painting style. The emotion engine recognizes the emotions the user felt towards works they have viewed in the past and sends that data to the server. For example, if a user strongly expresses joy or curiosity when viewing Impressionist works, the system will focus on recommending works in that style.

[0137] In this way, the present invention, through the collaboration of a server, terminal, and emotion engine, can optimize a personalized art viewing experience based on the user's preferences and emotional state. This approach is expected to promote unique visits to museums and galleries and deeply resonate with the individual emotional experiences of the audience.

[0138] The following describes the processing flow.

[0139] Step 1:

[0140] The server collects artwork data from partner museums and galleries. This includes detailed information such as image files of the artwork, artist name, genre, year of creation, and past exhibition history. The collected data is converted to a standard format and stored in a database.

[0141] Step 2:

[0142] The server analyzes the stored art data and uses image recognition technology to extract the visual characteristics (color, composition, etc.) of each artwork. It also uses text mining technology to obtain themes and related information from artwork descriptions and reviews. The results of this analysis help understand the characteristics of each artwork and are used for future recommendations.

[0143] Step 3:

[0144] The device receives user preference data as input. This includes lists of works previously viewed, preferred art styles and artists, etc. The user sends this information to the server through the application interface.

[0145] Step 4:

[0146] The device activates an emotion engine to recognize the user's current emotional state. Using a video camera and microphone, it analyzes the user's facial expressions and voice tone to identify emotions such as joy, anger, sadness, and happiness. The identified emotion data is transmitted to the server in real time.

[0147] Step 5:

[0148] The server integrates the received preference and emotional data and runs an algorithm to select the most appropriate artwork for the user. Emotional data is used to fine-tune the artwork to match the user's preferred types of artwork and their current mood.

[0149] Step 6:

[0150] The terminal displays a list of recommended artworks generated from the server to the user. The user can select artworks of interest from this list and view detailed information and explanations. Selected artworks may also be presented as a recommended new exhibition route.

[0151] Step 7:

[0152] Users input feedback on their impressions and thoughts after viewing the content. This feedback is sent to the server and stored as data to improve the accuracy of recommendations for future viewings.

[0153] Step 8:

[0154] The server updates its recommendation algorithms based on feedback, continuously improving the overall accuracy of the system. This process enhances the quality and personalization of the art experience provided to users.

[0155] (Example 2)

[0156] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0157] Efficiently collecting information on diverse art works and providing personalized recommendations based on user preferences and emotions is challenging. Furthermore, to evoke emotional resonance and provide a deeper art experience, it is necessary to appropriately analyze emotional information and utilize it in art recommendations.

[0158] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0159] In this invention, the server includes means for collecting and analyzing information on artworks, means for collecting user preference and sentiment information and generating recommendation results based on the preference and sentiment information, and means for providing personalized artworks to the user using a generative model. This makes it possible for the user to receive more personalized recommendations for artworks.

[0160] "Artwork" refers to a visual art object that possesses artistic value, and includes paintings, sculptures, photographs, and other visual arts.

[0161] "Information" refers to data and knowledge about artworks and users, including image data, text information, history, and emotional states.

[0162] "Analysis" refers to the process of extracting useful features and patterns from collected information, and this includes data analysis using image analysis and natural language processing.

[0163] A "user" refers to an individual or organization that uses this system to receive recommendations for artworks.

[0164] "Preference information" refers to data that indicates a user's preferences and interests, and this is collected from past selection history and input data.

[0165] "Emotional information" refers to data that indicates the user's emotional state, and this is obtained by analyzing visual and auditory responses.

[0166] A "generative model" refers to a system that generates predictions and recommendations by analyzing data using machine learning algorithms.

[0167] "Personalized recommendations" refer to suggestions of artwork tailored to each user's preferences and emotional information.

[0168] This invention is a system that efficiently collects information on works of art and provides personalized recommendations based on user preferences and emotions. It is achieved through the collaboration of a server, terminals, and an emotion analysis engine.

[0169] The server first collects information on artworks from various museums and galleries via APIs. The software used here includes a database management system and a deep learning framework for image analysis (e.g., TensorFlow, PyTorch). Using deep learning technology, it extracts visual features such as color and shape from images of artworks, and analyzes exhibition history and descriptions using natural language processing technology. This generates characteristic data for each artwork.

[0170] The terminal is responsible for direct input from the user. Users can input their preferred art style and past viewing history through an art curation application installed on the terminal. Furthermore, the terminal is equipped with a camera and microphone, which are used to acquire emotional information from the user's facial expressions and voice. The emotion analysis engine determines the user's emotional state based on the acquired visual and audio data and sends that data to the server.

[0171] Upon receiving this information, the server uses a generative model to select the most suitable artwork for the user. The generative model analyzes the user's preference and emotional information and creates a personalized recommendation list using an algorithm. At this stage, the system prioritizes artwork that evokes positive emotions such as joy and interest.

[0172] As a concrete example, a user can access an art curation application using their device and, in response to a prompt such as "I'm interested in modern art," indicate their preferences. Furthermore, when viewing artwork at an exhibition venue, the device analyzes the user's emotional responses, and the server adjusts the next artwork recommended based on that data. Through this entire process, users can enjoy a more personalized art experience.

[0173] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0174] Step 1:

[0175] The server collects art information from museums and galleries. Inputs include image data, artist information, and exhibition history of artworks obtained through each facility's API. This information is stored in a database, and data cleaning and formatting are performed as needed. The output is detailed information about the artworks, stored in a unified format.

[0176] Step 2:

[0177] The server performs image and text analysis using the collected artwork information. The input consists of images and text data of the artworks saved in Step 1. A deep learning framework is used to extract visual features from the images, and natural language processing techniques are used to analyze the text data. The output is a dataset that quantifies the characteristics of each artwork.

[0178] Step 3:

[0179] The device collects preference information from the user. The user inputs their preferred art style and past viewing history as options through an application on the device. The input is in the user's chosen format and is then formatted by converting it to a standard data format. The output is data indicating the user's preferences.

[0180] Step 4:

[0181] The device collects user emotional information. This includes recording the user's facial expressions and voice using the device's built-in camera and microphone. The input is real-time visual and audio data, which is analyzed by an emotion analysis engine. The output is quantitative data indicating the user's emotional state.

[0182] Step 5:

[0183] The server combines user preference and emotional information and uses a generative AI model to generate a personalized list of recommended artworks. The input is the output data from steps 3 and 4, which the model uses to learn and generate recommendation results. The output is a list of artworks optimized for each user. This list is adjusted to prioritize the user's emotional resonance.

[0184] Step 6:

[0185] The terminal displays a personalized recommendation list sent from the server via a user interface. The input is the recommendation list received from the server, which is displayed in a visually easy-to-understand form. The output is a display showing the user's selected works. User feedback is collected and used for future recommendations.

[0186] (Application Example 2)

[0187] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0188] Traditional art appreciation systems, while capable of recommending artworks based on a user's specific preferences, have limitations in deeply engaging with users' emotions and optimizing individual emotional experiences. Furthermore, there is a growing demand for more personalized experiences that incorporate emotional elements into virtual art environments.

[0189] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0190] In this invention, the server includes means for collecting and analyzing data on artworks, means for collecting user preference data and emotional information and generating recommendations based on that data, and means for presenting artworks to the user that enhance emotional resonance using the analysis results and emotional data. This makes it possible to provide a more deeply resonant art experience that is tailored to the user's emotional state.

[0191] An "artwork" is a creative work, primarily a visual art, that is exhibited in museums or galleries.

[0192] "Data" is a logically organized form of information, and it is an element that is useful for analysis and interpretation.

[0193] "Preference data" refers to information that indicates a user's personal preferences and interests, and is used to provide personalized services.

[0194] "Emotional information" refers to data that indicates the user's emotional state and is collected through the emotion engine.

[0195] An "emotion engine" is a system that analyzes a user's emotions from their facial expressions and voice, and is used to optimize the user experience.

[0196] "Recommendations" refer to the selection of specific artworks based on user preference data and emotional information.

[0197] A "virtual environment" is a virtual space created using digital technology, offering an experience different from that of a real place.

[0198] A "virtual display device" is a device used to display digital content to a user, and includes smart glasses and head-mounted displays.

[0199] The system for realizing this invention includes a server, a terminal, and an emotion engine as its main components. The server collects data on artworks from museums and galleries and extracts the visual features of the artworks using image analysis techniques. It also integrates relevant information into a database using text analysis techniques. This utilizes software such as TensorFlow and OpenCV.

[0200] The device plays a role in collecting user preference and emotional data. This involves data input based on user preferences and past browsing history, as well as real-time analysis of user emotional information using the camera and microphone. Platforms such as Azure® Cognitive Services and Google Cloud Vision AI are used for analyzing emotional information.

[0201] The server comprehensively analyzes collected artwork data and user preference and emotional data to generate personalized recommendation content for each user. This result is presented on virtual display devices such as smartphones and smart glasses, allowing users to experience art that best suits their emotional state.

[0202] As a concrete example, suppose a user visits a virtual gallery and is viewing an Impressionist exhibition. The system detects the user's emotions of joy and prioritizes displaying works that evoke similar emotions. Using a generative AI model, the system performs the analysis according to a prompt such as, "Analyze how the artwork the user is viewing emotionally impacts them, and select the artwork that resonates most emotionally with the user."

[0203] A system configured in this way, through the coordination of servers, terminals, and an emotion engine, can provide users with a more engaging and personalized art viewing experience.

[0204] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0205] Step 1:

[0206] The server collects data on artworks from various museums and galleries. This process digitally acquires image data, artist information, and exhibition history of the artworks and stores them in a database. Input is data received from data provision APIs of museums and galleries, and output is organized database entries. This enables efficient data management.

[0207] Step 2:

[0208] The server analyzes the collected artwork data. For image data, TensorFlow and OpenCV are used to extract visual features. For text data, natural language processing techniques are used to analyze artist information and exhibition history. The input is artwork data stored in a database, and the output is feature-extracted data. This allows for the modeling of the artwork's characteristics.

[0209] Step 3:

[0210] The device collects user preference data. This is done by collecting past browsing history and selected art styles from the user's smart device. The input is user data from the smart device, and the output is the user's preference profile. This digitally represents the user's preferences.

[0211] Step 4:

[0212] The device collects user emotional information. It uses a camera and microphone equipped with an emotion engine to analyze the user's facial expressions and voice, collecting emotional data. The input is real-time data of the user's facial expressions and voice, while the output is analyzed emotional state data. This allows the device to understand the user's emotional state.

[0213] Step 5:

[0214] The server integrates preference data and emotional information, and uses a generative AI model to select artworks to recommend to the user. Based on prompts, it evaluates the emotional impact each artwork has on the user and lists the artworks that resonate most with them. The input is the user's preference profile and emotional state data, and the output is a list of emotionally resonant artworks.

[0215] Step 6:

[0216] The terminal displays the generated recommendation list on a virtual display device. Here, the user can view the presented artwork in a virtual space. The input is a list of artworks provided by the server, and the output is an art exhibition unfolded in the virtual space. This allows the user to have an emotionally rich art viewing experience.

[0217] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0218] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0219] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0220] [Second Embodiment]

[0221] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0222] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0223] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0224] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0225] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0226] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0227] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0228] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0229] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0230] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0231] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0232] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0233] This invention provides a system for selecting, recommending, and providing personalized displays of artworks for users. This system consists of a server, terminals, and users, which work together in coordination.

[0234] The server first collects data on artworks provided by various museums and galleries. This includes images of the artworks, artist information, and exhibition history. The server then analyzes the collected data and automatically extracts the characteristics of the artworks. This analysis includes extracting iconographic features using image recognition and text analysis using natural language processing.

[0235] Furthermore, the server collects user preference data. This data collection is done when users provide their interests and past browsing history through their devices. Based on this preference data, the server generates personalized recommendations and proposes a unique exhibition experience for each user.

[0236] The terminal displays analysis results and recommendation information provided by the server to the user. The user can then view the artworks and exhibition routes provided through their terminal and proceed with their art appreciation based on their interests.

[0237] As a concrete example, a user logs into the AI ​​art curator using their device and sets their preferences and interests. Based on these settings, the server suggests the most suitable exhibition content from a vast database of art works. For example, if a user is interested in Impressionism, the system will combine past trends and new works in the same genre to generate a unique exhibition route.

[0238] Furthermore, feedback provided by users after viewing a work is collected and analyzed by the server and used to improve the system. This feedback analysis improves the accuracy of recommendations for that user, resulting in a more enriching viewing experience next time.

[0239] In this way, the present invention makes it possible to provide visitors to museums and galleries with an efficient and personalized art appreciation experience.

[0240] The following describes the processing flow.

[0241] Step 1:

[0242] The server accesses databases of partner museums and galleries to collect data including images of artworks, artist information, and exhibition history. After collection, this data is deduplicated and inaccurate information is removed, and it is formatted in a way that allows for analysis.

[0243] Step 2:

[0244] The server analyzes the collected art data. Image recognition technology is used to identify the color tone and style of the artworks, and text analysis technology is used to extract themes and background information from descriptions and reviews. This process allows the characteristics of each artwork to be stored in a database.

[0245] Step 3:

[0246] The device collects preference data from the user. This data includes information such as works the user has watched in the past and artists and genres the user is interested in. The device sends this information to the server.

[0247] Step 4:

[0248] The server combines accumulated artwork characteristic data with user preference data to generate a list of artworks best suited to the user. The generated list includes artworks related to the user's interests and artworks based on current trends.

[0249] Step 5:

[0250] The terminal displays a list of artworks and related information received from the server to the user. Through the interface, the user can view details of the artworks and select a recommended viewing route.

[0251] Step 6:

[0252] Users provide feedback on the works they have viewed through their devices, including their impressions and evaluations. This feedback is sent to the server and reflected in the database to improve the accuracy of future recommendations.

[0253] Step 7:

[0254] The server continuously improves the system using collected feedback and trend analysis results, and incorporates these improvements into future recommendations. This enhances the user experience and refines the recommendation system.

[0255] (Example 1)

[0256] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0257] In contemporary art appreciation, there is a need to quickly provide personalized recommendations tailored to the diverse preferences of users. However, traditional methods have struggled to accurately analyze the characteristics of artworks and generate recommendations that resonate with user preferences. Furthermore, effective recommendations that consider exhibition history and market trends have been limited. Designing systems that accurately reflect user feedback has also been challenging. Solving these challenges is essential.

[0258] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0259] In this invention, the server includes means for collecting information on artworks and extracting features from said information using image and text analysis; means for collecting information on the user's interests and generating personalized recommendation information based on said information; and means for providing artworks on a display device using said features and recommendation information. This makes it possible to recommend artworks that take into account the user's tastes and preferences. Furthermore, by analyzing exhibition history and market trends, more appropriate recommendations can be made, and a highly accurate recommendation system can be realized by accurately reflecting user feedback.

[0260] An "artwork" is a visual expression created to be appreciated through sight or other senses, and can take the form of painting, sculpture, photograph, or other similar media.

[0261] "Information" is a collection of data and knowledge that can be expressed in a form that computers and humans can understand, and includes forms such as text, images, and audio.

[0262] "Characteristics" refer to unique properties or attributes extracted from artworks or data, serving as criteria for identification and classification.

[0263] "Users" refers to individuals or groups who use the system or service, and in particular, those who are interested in art appreciation.

[0264] "Interest" refers to the degree of a user's interest in a particular subject or theme, and includes preferences that influence the selection of artworks.

[0265] "Recommendation information" refers to information provided as personalized suggestions or advice, generated based on the user's preferences and past behavior.

[0266] A "display device" refers to equipment or software used to provide information to users visually, and includes computer monitors and smartphone screens.

[0267] "Exhibition history" refers to a record of past exhibitions of artworks, including information such as the location and duration of the exhibition.

[0268] "Market trends" refer to specific tendencies and shifts in popularity observed over time within the art industry.

[0269] "Reactions" refer to the comments and evaluations that users provide after viewing an artwork, and these are used to improve the system.

[0270] "Accuracy" is a measure of how well the recommendation information generated by the system matches the user's expectations, and it serves as an indicator of reliability.

[0271] This invention relates to an information processing system for personalizing the appreciation of artworks and providing users with an optimal exhibition experience. In particular, it is realized through the collaboration of a server, a terminal, and the user, each playing their respective roles.

[0272] Server Role

[0273] The server first collects information about artworks from museums and galleries via APIs and data feeds. This information includes high-resolution images of the artworks, artist information, and past exhibition history. The HTTP protocol is used for this data collection. Next, machine learning libraries such as TensorFlow or PyTorch are used on the collected image data to extract features such as color, composition, and style using image recognition models. Furthermore, NLTK or spaCy is used for natural language processing to analyze related text data and extract the artist's style and the theme of the artwork.

[0274] The server then uses collaborative filtering and content-based filtering to generate personalized recommendations tailored to the user's interests. At this stage, it takes into account the user's past browsing history and interests to calculate the optimal artwork and exhibition route.

[0275] Terminal role

[0276] The terminal visually presents the server-generated recommendation information to the user. The interface on the terminal allows users to customize their interests in detail using checkboxes and sliders. Artwork is displayed in a list with thumbnail images, and users can view detailed information by clicking on works of interest. This process utilizes databases such as SQLite and Realm, enabling rapid data access and display.

[0277] User roles

[0278] Based on the information provided on the terminal, the user selects works of interest or checks the exhibition route. After viewing, the user can use the feedback function to input evaluations and impressions of the art works. This feedback is sent to the server and contributes to the improvement of accuracy next time.

[0279] Specific example

[0280] For example, when the user inputs a prompt such as "Please create an exhibition route that I recommend, including new works of Impressionism.", the server interprets this and generates an optimal exhibition route considering the user's interests. This route is displayed step by step on the terminal and can be used by the user as a guide for viewing the works.

[0281] The flow of the specific process in Example 1 will be described using FIG. 11.

[0282] Step 1:

[0283] The server collects information on art works from art museums and galleries using APIs and data feeds. As input, it receives data in JSON or XML format provided from each facility via an HTTP request. This data includes images of the works, artist information, and past exhibition histories. As output, these data are integrated into the server's database and used in the next analysis step. As a specific operation, the server periodically accesses each data source and updates the new work information.

[0284] Step 2:

[0285] The server analyzes the collected image data using machine learning libraries such as TensorFlow and PyTorch to extract visual features. As input, it uses the image data of the works stored in the database. As data processing, the image recognition model extracts features such as color, composition, and style from the images. As output, the feature vectors of each work are generated and stored in a table. As a specific example, in Impressionist works, softer color tones and brushstrokes are usually identified.

[0286] Step 3:

[0287] The server analyzes the collected author information and exhibition history through natural language processing. As input, the text data stored in the database is used. Tools such as NLTK and spaCy are used for data analysis to extract the styles and themes of the authors. As output, keywords and topics related to each author and work are generated. As a specific operation, phrases frequently appearing in the author's history and review articles are extracted and their relevance is evaluated.

[0288] Step 4:

[0289] The terminal collects the information about the user's interests entered by the user and sends it to the server. As input, the art genre selected by the user and the interest in a specific author are input. The terminal receives this information through UI elements such as forms and sends it to the server. As output, the user's interest data is stored in the server and used in the next recommendation generation step. As a specific example, there is a case where the user inputs that they are interested in "Impressionism".

[0290] Step 5:

[0291] The server generates recommendation information using collaborative filtering and content-based filtering based on user interest data. User preference data and artwork characteristic data are used as input. Data processing involves collaborative filtering based on the preference history of similar users and content-based filtering based on feature vectors. As output, a personalized list of recommended artworks is generated and sent to the terminal. Specifically, it analyzes patterns of users who have previously highly rated Impressionist works to determine new Impressionist recommendations.

[0292] Step 6:

[0293] The terminal displays recommendation information provided by the server to the user. The input is a list of recommendations from the server. The terminal displays this in the UI, presenting it in an interactive format. The output allows the user to view details of the recommended works and decide which one to view next. For example, the user can click on a thumbnail to view detailed information about the artwork and the artist's background.

[0294] Step 7:

[0295] After viewing a work, users enter feedback into their device and send it to the server. As input, user impressions and ratings are collected through the device. This information is sent to the server and used to refine the recommendation algorithm. As output, feedback data is stored on the server and used to improve the accuracy of future recommendations. Specifically, users may rate the work on a 5-point scale and add specific comments.

[0296] (Application Example 1)

[0297] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0298] Contemporary museums and galleries fail to adequately provide visitors with information on art pieces tailored to their individual interests and to personalize their viewing experience. As a result, users cannot easily find art pieces that suit their interests, limiting the quality of their viewing experience. Furthermore, providing real-time information and suggesting dynamic exhibition routes that incorporate user feedback is challenging.

[0299] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0300] In this invention, the server includes means for collecting and analyzing information on artworks, means for collecting user interest data and generating recommendations based on that interest data, means for presenting artwork information to the user via a visual device using the analysis results and recommendations, and means for acquiring user gaze information and displaying relevant information on the visual device's display in real time. This makes it possible to recommend artworks tailored to the user's individual interests and provide an immersive viewing experience through real-time information presentation.

[0301] "Information about artworks" refers to data such as image data related to the artwork, information about the creator, and exhibition history.

[0302] "Means of analysis" refers to a function that analyzes information on collected artworks and automatically extracts their characteristics.

[0303] "User interest data" refers to data that shows a user's interests, preferences, and past browsing history.

[0304] "Means for generating recommendations" refers to a function that recommends appropriate artworks and exhibition routes based on collected user interest data.

[0305] "Visual devices" refer to visual information presentation devices that users wear and use, such as smart glasses and head-mounted displays.

[0306] "Obtaining gaze information" refers to sensing the movement of the user's eyes and the direction of attention and acquiring it as data.

[0307] "Means for displaying relevant information in real time" refers to the function of immediately presenting relevant artworks and their information based on the user's gaze information and interest data.

[0308] An embodiment of this invention is a system that utilizes a visual device to optimize and personalize art appreciation for the user. This system is composed of a server, a visual device worn by the user, and the user himself / herself.

[0309] First, the server collects information on artworks from museums and galleries. This includes image data of the works, information about the artists, and past exhibition histories. Then, the server analyzes the features of the works using image recognition technology (e.g., Google Cloud Vision API) and extracts feature data. Furthermore, the server collects interest data, past browsing histories, and feedback input by the user using the visual device, and analyzes them using natural language processing (e.g., Google Natural Language API) to generate recommended content.

[0310] The visual device (e.g., smart glasses) uses the artwork information and recommended content received from the server to display relevant information in real time within the user's field of vision. The visual device is equipped with a camera and sensors for obtaining the user's gaze information, and this data is transmitted to the server and used to guide the user's interests.

[0311] As a specific example, when the user visits a museum and stares at a nearby Impressionist painting, this device recognizes the painting and displays detailed information, as well as recommends other relevant artworks. Through this experience, the user can make new discoveries and gain a deeper understanding and enjoyment during their next visit.

[0312] An example of a prompt might be, "How can I create a real-time art guide assistant that provides detailed information about Impressionist paintings in the art gallery I'm visiting?"

[0313] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0314] Step 1:

[0315] The server collects information on artworks from museums and galleries. It receives image data, artist information, and exhibition history as input. This information is stored in a database for later analysis.

[0316] Step 2:

[0317] The server analyzes the collected artwork information using image recognition technology. It takes image data as input and extracts characteristic data of the artworks as output. Specifically, it uses the Google Cloud Vision API to identify the color, shape, and style of each artwork and assign tags to them.

[0318] Step 3:

[0319] The server collects user interest data. It receives user interests and browsing history provided via visual devices as input. As output, it analyzes this data to generate a user profile, specifically revealing preferences based on user choices and feedback.

[0320] Step 4:

[0321] The server generates recommendations using an AI model based on user profiles. It takes user profiles and artwork characteristic data as input and generates recommended artworks and exhibition routes as output. Utilizing natural language processing, it precisely combines diverse artwork information to provide users with personalized recommendations.

[0322] Step 5:

[0323] The terminal, or visual device, displays recommendations provided by the server in real time within the user's field of view. It receives recommended artwork information as input and provides details of the artwork, partially overlaid. The output enhances user immersion and enriches the viewing experience.

[0324] Step 6:

[0325] When users view artwork through their visual devices, their gaze information is acquired by the terminal. As an initial input, this gaze data is sent to a server and used for analyzing works of interest. As an output, new preference data is generated from the user's gaze, contributing to the optimization of future exhibition recommendations.

[0326] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0327] This invention relates to a system that collects data on artworks and provides personalized recommendations using preference data and user emotions. The system includes a server, terminals, and an emotion engine, all of which work together.

[0328] The server first collects artwork data from various museums and galleries, storing images, artist information, exhibition history, and other information in a database. This makes it possible to manage large amounts of artwork information efficiently and systematically.

[0329] Next, the server analyzes the characteristics of the artwork based on the collected art data. It extracts the visual features of the artwork using image recognition technology and further analyzes related information using text analysis technology. This information is used as the basis for the recommendation algorithm.

[0330] The device collects preference and emotional data from the user. Users not only input their interests and past browsing history through the device, but also use a video camera and microphone equipped with an emotion engine to acquire visual and auditory emotional information. This emotional information is considered valuable data indicating how the user felt about different works.

[0331] The server combines preference and emotional data sent from the terminal to generate a list of the most suitable artworks for the user. In particular, the emotional state captured by the emotion engine is used to fine-tune the recommendations, prioritizing artworks that resonate more emotionally with the user.

[0332] As a concrete example, a user accesses an art curation application through their device and selects their favorite painting style. The emotion engine recognizes the emotions the user felt towards works they have viewed in the past and sends that data to the server. For example, if a user strongly expresses joy or curiosity when viewing Impressionist works, the system will focus on recommending works in that style.

[0333] In this way, the present invention, through the collaboration of a server, terminal, and emotion engine, can optimize a personalized art viewing experience based on the user's preferences and emotional state. This approach is expected to promote unique visits to museums and galleries and deeply resonate with the individual emotional experiences of the audience.

[0334] The following describes the processing flow.

[0335] Step 1:

[0336] The server collects artwork data from partner museums and galleries. This includes detailed information such as image files of the artwork, artist name, genre, year of creation, and past exhibition history. The collected data is converted to a standard format and stored in a database.

[0337] Step 2:

[0338] The server analyzes the stored art data and uses image recognition technology to extract the visual characteristics (color, composition, etc.) of each artwork. It also uses text mining technology to obtain themes and related information from artwork descriptions and reviews. The results of this analysis help understand the characteristics of each artwork and are used for future recommendations.

[0339] Step 3:

[0340] The device receives user preference data as input. This includes lists of works previously viewed, preferred art styles and artists, etc. The user sends this information to the server through the application interface.

[0341] Step 4:

[0342] The device activates an emotion engine to recognize the user's current emotional state. Using a video camera and microphone, it analyzes the user's facial expressions and voice tone to identify emotions such as joy, anger, sadness, and happiness. The identified emotion data is transmitted to the server in real time.

[0343] Step 5:

[0344] The server integrates the received preference and emotional data and runs an algorithm to select the most appropriate artwork for the user. Emotional data is used to fine-tune the artwork to match the user's preferred types of artwork and their current mood.

[0345] Step 6:

[0346] The terminal displays a list of recommended artworks generated from the server to the user. The user can select artworks of interest from this list and view detailed information and explanations. Selected artworks may also be presented as a recommended new exhibition route.

[0347] Step 7:

[0348] Users input feedback on their impressions and thoughts after viewing the content. This feedback is sent to the server and stored as data to improve the accuracy of recommendations for future viewings.

[0349] Step 8:

[0350] The server updates its recommendation algorithms based on feedback, continuously improving the overall accuracy of the system. This process enhances the quality and personalization of the art experience provided to users.

[0351] (Example 2)

[0352] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0353] Efficiently collecting information on diverse art works and providing personalized recommendations based on user preferences and emotions is challenging. Furthermore, to evoke emotional resonance and provide a deeper art experience, it is necessary to appropriately analyze emotional information and utilize it in art recommendations.

[0354] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0355] In this invention, the server includes means for collecting and analyzing information on artworks, means for collecting user preference and sentiment information and generating recommendation results based on the preference and sentiment information, and means for providing personalized artworks to the user using a generative model. This makes it possible for the user to receive more personalized recommendations for artworks.

[0356] "Artwork" refers to a visual art object that possesses artistic value, and includes paintings, sculptures, photographs, and other visual arts.

[0357] "Information" refers to data and knowledge about artworks and users, including image data, text information, history, and emotional states.

[0358] "Analysis" refers to the process of extracting useful features and patterns from collected information, and this includes data analysis using image analysis and natural language processing.

[0359] A "user" refers to an individual or organization that uses this system to receive recommendations for artworks.

[0360] "Preference information" refers to data that indicates a user's preferences and interests, and this is collected from past selection history and input data.

[0361] "Emotional information" refers to data that indicates the user's emotional state, and this is obtained by analyzing visual and auditory responses.

[0362] A "generative model" refers to a system that generates predictions and recommendations by analyzing data using machine learning algorithms.

[0363] "Personalized recommendations" refer to suggestions of artwork tailored to each user's preferences and emotional information.

[0364] This invention is a system that efficiently collects information on works of art and provides personalized recommendations based on user preferences and emotions. It is achieved through the collaboration of a server, terminals, and an emotion analysis engine.

[0365] The server first collects information on artworks from various museums and galleries via APIs. The software used here includes a database management system and a deep learning framework for image analysis (e.g., TensorFlow, PyTorch). Using deep learning technology, it extracts visual features such as color and shape from images of artworks, and analyzes exhibition history and descriptions using natural language processing technology. This generates characteristic data for each artwork.

[0366] The terminal is responsible for direct input from the user. Users can input their preferred art style and past viewing history through an art curation application installed on the terminal. Furthermore, the terminal is equipped with a camera and microphone, which are used to acquire emotional information from the user's facial expressions and voice. The emotion analysis engine determines the user's emotional state based on the acquired visual and audio data and sends that data to the server.

[0367] Upon receiving this information, the server uses a generative model to select the most suitable artwork for the user. The generative model analyzes the user's preference and emotional information and creates a personalized recommendation list using an algorithm. At this stage, the system prioritizes artwork that evokes positive emotions such as joy and interest.

[0368] As a concrete example, a user can access an art curation application using their device and, in response to a prompt such as "I'm interested in modern art," indicate their preferences. Furthermore, when viewing artwork at an exhibition venue, the device analyzes the user's emotional responses, and the server adjusts the next artwork recommended based on that data. Through this entire process, users can enjoy a more personalized art experience.

[0369] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0370] Step 1:

[0371] The server collects art information from museums and galleries. Inputs include image data, artist information, and exhibition history of artworks obtained through each facility's API. This information is stored in a database, and data cleaning and formatting are performed as needed. The output is detailed information about the artworks, stored in a unified format.

[0372] Step 2:

[0373] The server performs image and text analysis using the collected artwork information. The input consists of images and text data of the artworks saved in Step 1. A deep learning framework is used to extract visual features from the images, and natural language processing techniques are used to analyze the text data. The output is a dataset that quantifies the characteristics of each artwork.

[0374] Step 3:

[0375] The device collects preference information from the user. The user inputs their preferred art style and past viewing history as options through an application on the device. The input is in the user's chosen format and is then formatted by converting it to a standard data format. The output is data indicating the user's preferences.

[0376] Step 4:

[0377] The device collects user emotional information. This includes recording the user's facial expressions and voice using the device's built-in camera and microphone. The input is real-time visual and audio data, which is analyzed by an emotion analysis engine. The output is quantitative data indicating the user's emotional state.

[0378] Step 5:

[0379] The server combines user preference and emotional information and uses a generative AI model to generate a personalized list of recommended artworks. The input is the output data from steps 3 and 4, which the model uses to learn and generate recommendation results. The output is a list of artworks optimized for each user. This list is adjusted to prioritize the user's emotional resonance.

[0380] Step 6:

[0381] The terminal displays a personalized recommendation list sent from the server via a user interface. The input is the recommendation list received from the server, which is displayed in a visually easy-to-understand form. The output is a display showing the user's selected works. User feedback is collected and used for future recommendations.

[0382] (Application Example 2)

[0383] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0384] Traditional art appreciation systems, while capable of recommending artworks based on a user's specific preferences, have limitations in deeply engaging with users' emotions and optimizing individual emotional experiences. Furthermore, there is a growing demand for more personalized experiences that incorporate emotional elements into virtual art environments.

[0385] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0386] In this invention, the server includes means for collecting and analyzing data on artworks, means for collecting user preference data and emotional information and generating recommendations based on that data, and means for presenting artworks to the user that enhance emotional resonance using the analysis results and emotional data. This makes it possible to provide a more deeply resonant art experience that is tailored to the user's emotional state.

[0387] An "artwork" is a creative work, primarily a visual art, that is exhibited in museums or galleries.

[0388] "Data" is a logically organized form of information, and it is an element that is useful for analysis and interpretation.

[0389] "Preference data" refers to information that indicates a user's personal preferences and interests, and is used to provide personalized services.

[0390] "Emotional information" refers to data that indicates the user's emotional state and is collected through the emotion engine.

[0391] An "emotion engine" is a system that analyzes a user's emotions from their facial expressions and voice, and is used to optimize the user experience.

[0392] "Recommendations" refer to the selection of specific artworks based on user preference data and emotional information.

[0393] A "virtual environment" is a virtual space created using digital technology, offering an experience different from that of a real place.

[0394] A "virtual display device" is a device used to display digital content to a user, and includes smart glasses and head-mounted displays.

[0395] The system for realizing this invention includes a server, a terminal, and an emotion engine as its main components. The server collects data on artworks from museums and galleries and extracts the visual features of the artworks using image analysis techniques. It also integrates relevant information into a database using text analysis techniques. This utilizes software such as TensorFlow and OpenCV.

[0396] The device plays a role in collecting user preference and sentiment data. This involves data input based on user preferences and past browsing history, as well as real-time analysis of user sentiment information using the camera and microphone. Platforms such as Azure Cognitive Services and Google Cloud Vision AI are used for analyzing sentiment information.

[0397] The server comprehensively analyzes collected artwork data and user preference and emotional data to generate personalized recommendation content for each user. This result is presented on virtual display devices such as smartphones and smart glasses, allowing users to experience art that best suits their emotional state.

[0398] As a concrete example, suppose a user visits a virtual gallery and is viewing an Impressionist exhibition. The system detects the user's emotions of joy and prioritizes displaying works that evoke similar emotions. Using a generative AI model, the system performs the analysis according to a prompt such as, "Analyze how the artwork the user is viewing emotionally impacts them, and select the artwork that resonates most emotionally with the user."

[0399] A system configured in this way, through the coordination of servers, terminals, and an emotion engine, can provide users with a more engaging and personalized art viewing experience.

[0400] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0401] Step 1:

[0402] The server collects data on artworks from various museums and galleries. This process digitally acquires image data, artist information, and exhibition history of the artworks and stores them in a database. Input is data received from data provision APIs of museums and galleries, and output is organized database entries. This enables efficient data management.

[0403] Step 2:

[0404] The server analyzes the collected artwork data. For image data, TensorFlow and OpenCV are used to extract visual features. For text data, natural language processing techniques are used to analyze artist information and exhibition history. The input is artwork data stored in a database, and the output is feature-extracted data. This allows for the modeling of the artwork's characteristics.

[0405] Step 3:

[0406] The device collects user preference data. This is done by collecting past browsing history and selected art styles from the user's smart device. The input is user data from the smart device, and the output is the user's preference profile. This digitally represents the user's preferences.

[0407] Step 4:

[0408] The device collects user emotional information. It uses a camera and microphone equipped with an emotion engine to analyze the user's facial expressions and voice, collecting emotional data. The input is real-time data of the user's facial expressions and voice, while the output is analyzed emotional state data. This allows the device to understand the user's emotional state.

[0409] Step 5:

[0410] The server integrates preference data and emotional information, and uses a generative AI model to select artworks to recommend to the user. Based on prompts, it evaluates the emotional impact each artwork has on the user and lists the artworks that resonate most with them. The input is the user's preference profile and emotional state data, and the output is a list of emotionally resonant artworks.

[0411] Step 6:

[0412] The terminal displays the generated recommendation list on a virtual display device. Here, the user can view the presented artwork in a virtual space. The input is a list of artworks provided by the server, and the output is an art exhibition unfolded in the virtual space. This allows the user to have an emotionally rich art viewing experience.

[0413] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0414] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0415] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0416] [Third Embodiment]

[0417] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0418] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0419] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0420] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0421] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0422] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0423] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0424] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0425] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0426] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0427] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0428] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0429] This invention provides a system for selecting, recommending, and providing personalized displays of artworks for users. This system consists of a server, terminals, and users, which work together in coordination.

[0430] The server first collects data on artworks provided by various museums and galleries. This includes images of the artworks, artist information, and exhibition history. The server then analyzes the collected data and automatically extracts the characteristics of the artworks. This analysis includes extracting iconographic features using image recognition and text analysis using natural language processing.

[0431] Furthermore, the server collects user preference data. This data collection is done when users provide their interests and past browsing history through their devices. Based on this preference data, the server generates personalized recommendations and proposes a unique exhibition experience for each user.

[0432] The terminal displays analysis results and recommendation information provided by the server to the user. The user can then view the artworks and exhibition routes provided through their terminal and proceed with their art appreciation based on their interests.

[0433] As a concrete example, a user logs into the AI ​​art curator using their device and sets their preferences and interests. Based on these settings, the server suggests the most suitable exhibition content from a vast database of art works. For example, if a user is interested in Impressionism, the system will combine past trends and new works in the same genre to generate a unique exhibition route.

[0434] Furthermore, feedback provided by users after viewing a work is collected and analyzed by the server and used to improve the system. This feedback analysis improves the accuracy of recommendations for that user, resulting in a more enriching viewing experience next time.

[0435] In this way, the present invention makes it possible to provide visitors to museums and galleries with an efficient and personalized art appreciation experience.

[0436] The following describes the processing flow.

[0437] Step 1:

[0438] The server accesses databases of partner museums and galleries to collect data including images of artworks, artist information, and exhibition history. After collection, this data is deduplicated and inaccurate information is removed, and it is formatted in a way that allows for analysis.

[0439] Step 2:

[0440] The server analyzes the collected art data. Image recognition technology is used to identify the color tone and style of the artworks, and text analysis technology is used to extract themes and background information from descriptions and reviews. This process allows the characteristics of each artwork to be stored in a database.

[0441] Step 3:

[0442] The device collects preference data from the user. This data includes information such as works the user has watched in the past and artists and genres the user is interested in. The device sends this information to the server.

[0443] Step 4:

[0444] The server combines accumulated artwork characteristic data with user preference data to generate a list of artworks best suited to the user. The generated list includes artworks related to the user's interests and artworks based on current trends.

[0445] Step 5:

[0446] The terminal displays a list of artworks and related information received from the server to the user. Through the interface, the user can view details of the artworks and select a recommended viewing route.

[0447] Step 6:

[0448] Users provide feedback on the works they have viewed through their devices, including their impressions and evaluations. This feedback is sent to the server and reflected in the database to improve the accuracy of future recommendations.

[0449] Step 7:

[0450] The server continuously improves the system using collected feedback and trend analysis results, and incorporates these improvements into future recommendations. This enhances the user experience and refines the recommendation system.

[0451] (Example 1)

[0452] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0453] In contemporary art appreciation, there is a need to quickly provide personalized recommendations tailored to the diverse preferences of users. However, traditional methods have struggled to accurately analyze the characteristics of artworks and generate recommendations that resonate with user preferences. Furthermore, effective recommendations that consider exhibition history and market trends have been limited. Designing systems that accurately reflect user feedback has also been challenging. Solving these challenges is essential.

[0454] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0455] In this invention, the server includes means for collecting information on artworks and extracting features from said information using image and text analysis; means for collecting information on the user's interests and generating personalized recommendation information based on said information; and means for providing artworks on a display device using said features and recommendation information. This makes it possible to recommend artworks that take into account the user's tastes and preferences. Furthermore, by analyzing exhibition history and market trends, more appropriate recommendations can be made, and a highly accurate recommendation system can be realized by accurately reflecting user feedback.

[0456] An "artwork" is a visual expression created to be appreciated through sight or other senses, and can take the form of painting, sculpture, photograph, or other similar media.

[0457] "Information" is a collection of data and knowledge that can be expressed in a form that computers and humans can understand, and includes forms such as text, images, and audio.

[0458] "Characteristics" refer to unique properties or attributes extracted from artworks or data, serving as criteria for identification and classification.

[0459] "Users" refers to individuals or groups who use the system or service, and in particular, those who are interested in art appreciation.

[0460] "Interest" refers to the degree of a user's interest in a particular subject or theme, and includes preferences that influence the selection of artworks.

[0461] "Recommendation information" refers to information provided as personalized suggestions or advice, generated based on the user's preferences and past behavior.

[0462] A "display device" refers to equipment or software used to provide information to users visually, and includes computer monitors and smartphone screens.

[0463] "Exhibition history" refers to a record of past exhibitions of artworks, including information such as the location and duration of the exhibition.

[0464] "Market trends" refer to specific tendencies and shifts in popularity observed over time within the art industry.

[0465] "Reactions" refer to the comments and evaluations that users provide after viewing an artwork, and these are used to improve the system.

[0466] "Accuracy" is a measure of how well the recommendation information generated by the system matches the user's expectations, and it serves as an indicator of reliability.

[0467] This invention relates to an information processing system for personalizing the appreciation of artworks and providing users with an optimal exhibition experience. In particular, it is realized through the collaboration of a server, a terminal, and the user, each playing their respective roles.

[0468] Server Role

[0469] The server first collects information about artworks from museums and galleries via APIs and data feeds. This information includes high-resolution images of the artworks, artist information, and past exhibition history. The HTTP protocol is used for this data collection. Next, machine learning libraries such as TensorFlow or PyTorch are used on the collected image data to extract features such as color, composition, and style using image recognition models. Furthermore, NLTK or spaCy is used for natural language processing to analyze related text data and extract the artist's style and the theme of the artwork.

[0470] The server then uses collaborative filtering and content-based filtering to generate personalized recommendations tailored to the user's interests. At this stage, it takes into account the user's past browsing history and interests to calculate the optimal artwork and exhibition route.

[0471] Terminal role

[0472] The terminal visually presents the server-generated recommendation information to the user. The interface on the terminal allows users to customize their interests in detail using checkboxes and sliders. Artwork is displayed in a list with thumbnail images, and users can view detailed information by clicking on works of interest. This process utilizes databases such as SQLite and Realm, enabling rapid data access and display.

[0473] User roles

[0474] Users select works of art that interest them and check the exhibition route based on the information provided on their device. After viewing the art, they can use the feedback function to input their evaluation and impressions of the artwork. This feedback is sent to the server and contributes to improving the accuracy of the next event.

[0475] Specific example

[0476] For example, if a user enters a prompt such as, "Please create a recommended exhibition route for me, including new Impressionist works," the server interprets this and generates an optimal exhibition route that takes the user's interests into account. This route is displayed step-by-step on the terminal, and the user can use it as a guide for viewing the artworks.

[0477] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0478] Step 1:

[0479] The server collects information on artworks from museums and galleries using APIs and data feeds. As input, it receives data in JSON or XML format provided by each institution via HTTP requests. This data includes images of the artwork, artist information, and past exhibition history. As output, this data is integrated into the server's database and used in the next analysis step. Specifically, the server periodically accesses each data source to update new artwork information.

[0480] Step 2:

[0481] The server analyzes the collected image data using machine learning libraries such as TensorFlow and PyTorch to extract visual features. Image data of artworks stored in a database is used as input. For data processing, an image recognition model extracts features such as color, composition, and style from the images. As output, feature vectors for each artwork are generated and stored in a table. For example, Impressionist works are identified as having softer color tones and brushwork than usual.

[0482] Step 3:

[0483] The server analyzes collected artist information and exhibition history using natural language processing. Text data stored in a database is used as input. Tools such as NLTK and spaCy are used for data analysis to extract the artist's style and themes. Keywords and topics related to each artist and their works are generated as output. Specifically, frequently occurring phrases are extracted from the artist's biography and review articles, and their relevance is evaluated.

[0484] Step 4:

[0485] The device collects information about the user's interests and sends it to the server. The input includes the user's selected art genres and interests in specific artists. The device receives this information through UI elements such as forms and sends it to the server. The output is the user's interest data, which is stored on the server and used in the next recommendation generation step. A concrete example is when a user inputs that they are interested in "Impressionism."

[0486] Step 5:

[0487] The server generates recommendation information using collaborative filtering and content-based filtering based on user interest data. User preference data and artwork characteristic data are used as input. Data processing involves collaborative filtering based on the preference history of similar users and content-based filtering based on feature vectors. As output, a personalized list of recommended artworks is generated and sent to the terminal. Specifically, it analyzes patterns of users who have previously highly rated Impressionist works to determine new Impressionist recommendations.

[0488] Step 6:

[0489] The terminal displays recommendation information provided by the server to the user. The input is a list of recommendations from the server. The terminal displays this in the UI, presenting it in an interactive format. The output allows the user to view details of the recommended works and decide which one to view next. For example, the user can click on a thumbnail to view detailed information about the artwork and the artist's background.

[0490] Step 7:

[0491] After viewing a work, users enter feedback into their device and send it to the server. As input, user impressions and ratings are collected through the device. This information is sent to the server and used to refine the recommendation algorithm. As output, feedback data is stored on the server and used to improve the accuracy of future recommendations. Specifically, users may rate the work on a 5-point scale and add specific comments.

[0492] (Application Example 1)

[0493] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0494] Contemporary museums and galleries fail to adequately provide visitors with information on art pieces tailored to their individual interests and to personalize their viewing experience. As a result, users cannot easily find art pieces that suit their interests, limiting the quality of their viewing experience. Furthermore, providing real-time information and suggesting dynamic exhibition routes that incorporate user feedback is challenging.

[0495] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0496] In this invention, the server includes means for collecting and analyzing information on artworks, means for collecting user interest data and generating recommendations based on that interest data, means for presenting artwork information to the user via a visual device using the analysis results and recommendations, and means for acquiring user gaze information and displaying relevant information on the visual device's display in real time. This makes it possible to recommend artworks tailored to the user's individual interests and provide an immersive viewing experience through real-time information presentation.

[0497] "Information about artworks" refers to data such as image data related to the artwork, information about the creator, and exhibition history.

[0498] "Means of analysis" refers to a function that analyzes information on collected artworks and automatically extracts their characteristics.

[0499] "User interest data" refers to data that shows a user's interests, preferences, and past browsing history.

[0500] "Means for generating recommendations" refers to a function that recommends appropriate artworks and exhibition routes based on collected user interest data.

[0501] "Visual devices" refer to visual information presentation devices that users wear and use, such as smart glasses and head-mounted displays.

[0502] "Acquiring eye-tracking information" refers to sensing the user's eye movements and the direction they are focusing on, and acquiring this information as data.

[0503] "Means of displaying related information in real time" refers to a function that instantly presents related artworks and information based on the user's eye-tracking data and interest data.

[0504] An embodiment of this invention is a system that utilizes a visual device to optimize and personalize art appreciation for a user. This system consists of a server, a visual device worn by the user, and the user themselves.

[0505] The server first collects information about artworks from museums and galleries. This includes image data of the artworks, information about the artists, and past exhibition history. The server then uses image recognition technology (e.g., Google Cloud Vision API) to analyze the features of the artworks and extract feature data. Furthermore, it collects interest data entered by users using visual devices, past browsing history, and feedback, and analyzes this data using natural language processing (e.g., Google Natural Language API) to generate recommendations.

[0506] Visual devices (e.g., smart glasses) use artwork information and recommendations received from a server to display relevant information in real time within the user's field of view. These devices are equipped with cameras and sensors to capture the user's gaze, and this data is sent to the server to help guide the user's interests.

[0507] For example, when a user visits a museum and looks at a nearby Impressionist painting, the device recognizes the painting, displays detailed information, and recommends other related works of art. This experience allows the user to make new discoveries and gain a deeper understanding and enjoyment on subsequent visits.

[0508] An example of a prompt might be, "How can I create a real-time art guide assistant that provides detailed information about Impressionist paintings in the art gallery I'm visiting?"

[0509] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0510] Step 1:

[0511] The server collects information on artworks from museums and galleries. It receives image data, artist information, and exhibition history as input. This information is stored in a database for later analysis.

[0512] Step 2:

[0513] The server analyzes the collected artwork information using image recognition technology. It takes image data as input and extracts characteristic data of the artworks as output. Specifically, it uses the Google Cloud Vision API to identify the color, shape, and style of each artwork and assign tags to them.

[0514] Step 3:

[0515] The server collects user interest data. It receives user interests and browsing history provided via visual devices as input. As output, it analyzes this data to generate a user profile, specifically revealing preferences based on user choices and feedback.

[0516] Step 4:

[0517] The server generates recommendations using an AI model based on user profiles. It takes user profiles and artwork characteristic data as input and generates recommended artworks and exhibition routes as output. Utilizing natural language processing, it precisely combines diverse artwork information to provide users with personalized recommendations.

[0518] Step 5:

[0519] The terminal, or visual device, displays recommendations provided by the server in real time within the user's field of view. It receives recommended artwork information as input and provides details of the artwork, partially overlaid. The output enhances user immersion and enriches the viewing experience.

[0520] Step 6:

[0521] When users view artwork through their visual devices, their gaze information is acquired by the terminal. As an initial input, this gaze data is sent to a server and used for analyzing works of interest. As an output, new preference data is generated from the user's gaze, contributing to the optimization of future exhibition recommendations.

[0522] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0523] This invention relates to a system that collects data on artworks and provides personalized recommendations using preference data and user emotions. The system includes a server, terminals, and an emotion engine, all of which work together.

[0524] The server first collects artwork data from various museums and galleries, storing images, artist information, exhibition history, and other information in a database. This makes it possible to manage large amounts of artwork information efficiently and systematically.

[0525] Next, the server analyzes the characteristics of the artwork based on the collected art data. It extracts the visual features of the artwork using image recognition technology and further analyzes related information using text analysis technology. This information is used as the basis for the recommendation algorithm.

[0526] The device collects preference and emotional data from the user. Users not only input their interests and past browsing history through the device, but also use a video camera and microphone equipped with an emotion engine to acquire visual and auditory emotional information. This emotional information is considered valuable data indicating how the user felt about different works.

[0527] The server combines preference and emotional data sent from the terminal to generate a list of the most suitable artworks for the user. In particular, the emotional state captured by the emotion engine is used to fine-tune the recommendations, prioritizing artworks that resonate more emotionally with the user.

[0528] As a concrete example, a user accesses an art curation application through their device and selects their favorite painting style. The emotion engine recognizes the emotions the user felt towards works they have viewed in the past and sends that data to the server. For example, if a user strongly expresses joy or curiosity when viewing Impressionist works, the system will focus on recommending works in that style.

[0529] In this way, the present invention, through the collaboration of a server, terminal, and emotion engine, can optimize a personalized art viewing experience based on the user's preferences and emotional state. This approach is expected to promote unique visits to museums and galleries and deeply resonate with the individual emotional experiences of the audience.

[0530] The following describes the processing flow.

[0531] Step 1:

[0532] The server collects artwork data from partner museums and galleries. This includes detailed information such as image files of the artwork, artist name, genre, year of creation, and past exhibition history. The collected data is converted to a standard format and stored in a database.

[0533] Step 2:

[0534] The server analyzes the stored art data and uses image recognition technology to extract the visual characteristics (color, composition, etc.) of each artwork. It also uses text mining technology to obtain themes and related information from artwork descriptions and reviews. The results of this analysis help understand the characteristics of each artwork and are used for future recommendations.

[0535] Step 3:

[0536] The device receives user preference data as input. This includes lists of works previously viewed, preferred art styles and artists, etc. The user sends this information to the server through the application interface.

[0537] Step 4:

[0538] The device activates an emotion engine to recognize the user's current emotional state. Using a video camera and microphone, it analyzes the user's facial expressions and voice tone to identify emotions such as joy, anger, sadness, and happiness. The identified emotion data is transmitted to the server in real time.

[0539] Step 5:

[0540] The server integrates the received preference and emotional data and runs an algorithm to select the most appropriate artwork for the user. Emotional data is used to fine-tune the artwork to match the user's preferred types of artwork and their current mood.

[0541] Step 6:

[0542] The terminal displays a list of recommended artworks generated from the server to the user. The user can select artworks of interest from this list and view detailed information and explanations. Selected artworks may also be presented as a recommended new exhibition route.

[0543] Step 7:

[0544] Users input feedback on their impressions and thoughts after viewing the content. This feedback is sent to the server and stored as data to improve the accuracy of recommendations for future viewings.

[0545] Step 8:

[0546] The server updates its recommendation algorithms based on feedback, continuously improving the overall accuracy of the system. This process enhances the quality and personalization of the art experience provided to users.

[0547] (Example 2)

[0548] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0549] Efficiently collecting information on diverse art works and providing personalized recommendations based on user preferences and emotions is challenging. Furthermore, to evoke emotional resonance and provide a deeper art experience, it is necessary to appropriately analyze emotional information and utilize it in art recommendations.

[0550] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0551] In this invention, the server includes means for collecting and analyzing information on artworks, means for collecting user preference and sentiment information and generating recommendation results based on the preference and sentiment information, and means for providing personalized artworks to the user using a generative model. This makes it possible for the user to receive more personalized recommendations for artworks.

[0552] "Artwork" refers to a visual art object that possesses artistic value, and includes paintings, sculptures, photographs, and other visual arts.

[0553] "Information" refers to data and knowledge about artworks and users, including image data, text information, history, and emotional states.

[0554] "Analysis" refers to the process of extracting useful features and patterns from collected information, and this includes data analysis using image analysis and natural language processing.

[0555] A "user" refers to an individual or organization that uses this system to receive recommendations for artworks.

[0556] "Preference information" refers to data that indicates a user's preferences and interests, and this is collected from past selection history and input data.

[0557] "Emotional information" refers to data that indicates the user's emotional state, and this is obtained by analyzing visual and auditory responses.

[0558] A "generative model" refers to a system that generates predictions and recommendations by analyzing data using machine learning algorithms.

[0559] "Personalized recommendations" refer to suggestions of artwork tailored to each user's preferences and emotional information.

[0560] This invention is a system that efficiently collects information on works of art and provides personalized recommendations based on user preferences and emotions. It is achieved through the collaboration of a server, terminals, and an emotion analysis engine.

[0561] The server first collects information on artworks from various museums and galleries via APIs. The software used here includes a database management system and a deep learning framework for image analysis (e.g., TensorFlow, PyTorch). Using deep learning technology, it extracts visual features such as color and shape from images of artworks, and analyzes exhibition history and descriptions using natural language processing technology. This generates characteristic data for each artwork.

[0562] The terminal is responsible for direct input from the user. Users can input their preferred art style and past viewing history through an art curation application installed on the terminal. Furthermore, the terminal is equipped with a camera and microphone, which are used to acquire emotional information from the user's facial expressions and voice. The emotion analysis engine determines the user's emotional state based on the acquired visual and audio data and sends that data to the server.

[0563] Upon receiving this information, the server uses a generative model to select the most suitable artwork for the user. The generative model analyzes the user's preference and emotional information and creates a personalized recommendation list using an algorithm. At this stage, the system prioritizes artwork that evokes positive emotions such as joy and interest.

[0564] As a concrete example, a user can access an art curation application using their device and, in response to a prompt such as "I'm interested in modern art," indicate their preferences. Furthermore, when viewing artwork at an exhibition venue, the device analyzes the user's emotional responses, and the server adjusts the next artwork recommended based on that data. Through this entire process, users can enjoy a more personalized art experience.

[0565] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0566] Step 1:

[0567] The server collects art information from museums and galleries. Inputs include image data, artist information, and exhibition history of artworks obtained through each facility's API. This information is stored in a database, and data cleaning and formatting are performed as needed. The output is detailed information about the artworks, stored in a unified format.

[0568] Step 2:

[0569] The server performs image and text analysis using the collected artwork information. The input consists of images and text data of the artworks saved in Step 1. A deep learning framework is used to extract visual features from the images, and natural language processing techniques are used to analyze the text data. The output is a dataset that quantifies the characteristics of each artwork.

[0570] Step 3:

[0571] The device collects preference information from the user. The user inputs their preferred art style and past viewing history as options through an application on the device. The input is in the user's chosen format and is then formatted by converting it to a standard data format. The output is data indicating the user's preferences.

[0572] Step 4:

[0573] The device collects user emotional information. This includes recording the user's facial expressions and voice using the device's built-in camera and microphone. The input is real-time visual and audio data, which is analyzed by an emotion analysis engine. The output is quantitative data indicating the user's emotional state.

[0574] Step 5:

[0575] The server combines user preference and emotional information and uses a generative AI model to generate a personalized list of recommended artworks. The input is the output data from steps 3 and 4, which the model uses to learn and generate recommendation results. The output is a list of artworks optimized for each user. This list is adjusted to prioritize the user's emotional resonance.

[0576] Step 6:

[0577] The terminal displays a personalized recommendation list sent from the server via a user interface. The input is the recommendation list received from the server, which is displayed in a visually easy-to-understand form. The output is a display showing the user's selected works. User feedback is collected and used for future recommendations.

[0578] (Application Example 2)

[0579] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0580] Traditional art appreciation systems, while capable of recommending artworks based on a user's specific preferences, have limitations in deeply engaging with users' emotions and optimizing individual emotional experiences. Furthermore, there is a growing demand for more personalized experiences that incorporate emotional elements into virtual art environments.

[0581] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0582] In this invention, the server includes means for collecting and analyzing data on artworks, means for collecting user preference data and emotional information and generating recommendations based on that data, and means for presenting artworks to the user that enhance emotional resonance using the analysis results and emotional data. This makes it possible to provide a more deeply resonant art experience that is tailored to the user's emotional state.

[0583] An "artwork" is a creative work, primarily a visual art, that is exhibited in museums or galleries.

[0584] "Data" is a logically organized form of information, and it is an element that is useful for analysis and interpretation.

[0585] "Preference data" refers to information that indicates a user's personal preferences and interests, and is used to provide personalized services.

[0586] "Emotional information" refers to data that indicates the user's emotional state and is collected through the emotion engine.

[0587] An "emotion engine" is a system that analyzes a user's emotions from their facial expressions and voice, and is used to optimize the user experience.

[0588] "Recommendations" refer to the selection of specific artworks based on user preference data and emotional information.

[0589] A "virtual environment" is a virtual space created using digital technology, offering an experience different from that of a real place.

[0590] A "virtual display device" is a device used to display digital content to a user, and includes smart glasses and head-mounted displays.

[0591] The system for realizing this invention includes a server, a terminal, and an emotion engine as its main components. The server collects data on artworks from museums and galleries and extracts the visual features of the artworks using image analysis techniques. It also integrates relevant information into a database using text analysis techniques. This utilizes software such as TensorFlow and OpenCV.

[0592] The device plays a role in collecting user preference and sentiment data. This involves data input based on user preferences and past browsing history, as well as real-time analysis of user sentiment information using the camera and microphone. Platforms such as Azure Cognitive Services and Google Cloud Vision AI are used for analyzing sentiment information.

[0593] The server comprehensively analyzes collected artwork data and user preference and emotional data to generate personalized recommendation content for each user. This result is presented on virtual display devices such as smartphones and smart glasses, allowing users to experience art that best suits their emotional state.

[0594] As a concrete example, suppose a user visits a virtual gallery and is viewing an Impressionist exhibition. The system detects the user's emotions of joy and prioritizes displaying works that evoke similar emotions. Using a generative AI model, the system performs the analysis according to a prompt such as, "Analyze how the artwork the user is viewing emotionally impacts them, and select the artwork that resonates most emotionally with the user."

[0595] A system configured in this way, through the coordination of servers, terminals, and an emotion engine, can provide users with a more engaging and personalized art viewing experience.

[0596] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0597] Step 1:

[0598] The server collects data on artworks from various museums and galleries. This process digitally acquires image data, artist information, and exhibition history of the artworks and stores them in a database. Input is data received from data provision APIs of museums and galleries, and output is organized database entries. This enables efficient data management.

[0599] Step 2:

[0600] The server analyzes the collected artwork data. For image data, TensorFlow and OpenCV are used to extract visual features. For text data, natural language processing techniques are used to analyze artist information and exhibition history. The input is artwork data stored in a database, and the output is feature-extracted data. This allows for the modeling of the artwork's characteristics.

[0601] Step 3:

[0602] The device collects user preference data. This is done by collecting past browsing history and selected art styles from the user's smart device. The input is user data from the smart device, and the output is the user's preference profile. This digitally represents the user's preferences.

[0603] Step 4:

[0604] The device collects user emotional information. It uses a camera and microphone equipped with an emotion engine to analyze the user's facial expressions and voice, collecting emotional data. The input is real-time data of the user's facial expressions and voice, while the output is analyzed emotional state data. This allows the device to understand the user's emotional state.

[0605] Step 5:

[0606] The server integrates preference data and emotional information, and uses a generative AI model to select artworks to recommend to the user. Based on prompts, it evaluates the emotional impact each artwork has on the user and lists the artworks that resonate most with them. The input is the user's preference profile and emotional state data, and the output is a list of emotionally resonant artworks.

[0607] Step 6:

[0608] The terminal displays the generated recommendation list on a virtual display device. Here, the user can view the presented artwork in a virtual space. The input is a list of artworks provided by the server, and the output is an art exhibition unfolded in the virtual space. This allows the user to have an emotionally rich art viewing experience.

[0609] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0610] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0611] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0612] [Fourth Embodiment]

[0613] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0614] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0615] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0616] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0617] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0618] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0619] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0620] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0621] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0622] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0623] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0624] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0625] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0626] This invention provides a system for selecting, recommending, and providing personalized displays of artworks for users. This system consists of a server, terminals, and users, which work together in coordination.

[0627] The server first collects data on artworks provided by various museums and galleries. This includes images of the artworks, artist information, and exhibition history. The server then analyzes the collected data and automatically extracts the characteristics of the artworks. This analysis includes extracting iconographic features using image recognition and text analysis using natural language processing.

[0628] Furthermore, the server collects user preference data. This data collection is done when users provide their interests and past browsing history through their devices. Based on this preference data, the server generates personalized recommendations and proposes a unique exhibition experience for each user.

[0629] The terminal displays analysis results and recommendation information provided by the server to the user. The user can then view the artworks and exhibition routes provided through their terminal and proceed with their art appreciation based on their interests.

[0630] As a concrete example, a user logs into the AI ​​art curator using their device and sets their preferences and interests. Based on these settings, the server suggests the most suitable exhibition content from a vast database of art works. For example, if a user is interested in Impressionism, the system will combine past trends and new works in the same genre to generate a unique exhibition route.

[0631] Furthermore, feedback provided by users after viewing a work is collected and analyzed by the server and used to improve the system. This feedback analysis improves the accuracy of recommendations for that user, resulting in a more enriching viewing experience next time.

[0632] In this way, the present invention makes it possible to provide visitors to museums and galleries with an efficient and personalized art appreciation experience.

[0633] The following describes the processing flow.

[0634] Step 1:

[0635] The server accesses databases of partner museums and galleries to collect data including images of artworks, artist information, and exhibition history. After collection, this data is deduplicated and inaccurate information is removed, and it is formatted in a way that allows for analysis.

[0636] Step 2:

[0637] The server analyzes the collected art data. Image recognition technology is used to identify the color tone and style of the artworks, and text analysis technology is used to extract themes and background information from descriptions and reviews. This process allows the characteristics of each artwork to be stored in a database.

[0638] Step 3:

[0639] The device collects preference data from the user. This data includes information such as works the user has watched in the past and artists and genres the user is interested in. The device sends this information to the server.

[0640] Step 4:

[0641] The server combines accumulated artwork characteristic data with user preference data to generate a list of artworks best suited to the user. The generated list includes artworks related to the user's interests and artworks based on current trends.

[0642] Step 5:

[0643] The terminal displays a list of artworks and related information received from the server to the user. Through the interface, the user can view details of the artworks and select a recommended viewing route.

[0644] Step 6:

[0645] Users provide feedback on the works they have viewed through their devices, including their impressions and evaluations. This feedback is sent to the server and reflected in the database to improve the accuracy of future recommendations.

[0646] Step 7:

[0647] The server continuously improves the system using collected feedback and trend analysis results, and incorporates these improvements into future recommendations. This enhances the user experience and refines the recommendation system.

[0648] (Example 1)

[0649] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0650] In contemporary art appreciation, there is a need to quickly provide personalized recommendations tailored to the diverse preferences of users. However, traditional methods have struggled to accurately analyze the characteristics of artworks and generate recommendations that resonate with user preferences. Furthermore, effective recommendations that consider exhibition history and market trends have been limited. Designing systems that accurately reflect user feedback has also been challenging. Solving these challenges is essential.

[0651] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0652] In this invention, the server includes means for collecting information on artworks and extracting features from said information using image and text analysis; means for collecting information on the user's interests and generating personalized recommendation information based on said information; and means for providing artworks on a display device using said features and recommendation information. This makes it possible to recommend artworks that take into account the user's tastes and preferences. Furthermore, by analyzing exhibition history and market trends, more appropriate recommendations can be made, and a highly accurate recommendation system can be realized by accurately reflecting user feedback.

[0653] An "artwork" is a visual expression created to be appreciated through sight or other senses, and can take the form of painting, sculpture, photograph, or other similar media.

[0654] "Information" is a collection of data and knowledge that can be expressed in a form that computers and humans can understand, and includes forms such as text, images, and audio.

[0655] "Characteristics" refer to unique properties or attributes extracted from artworks or data, serving as criteria for identification and classification.

[0656] "Users" refers to individuals or groups who use the system or service, and in particular, those who are interested in art appreciation.

[0657] "Interest" refers to the degree of a user's interest in a particular subject or theme, and includes preferences that influence the selection of artworks.

[0658] "Recommendation information" refers to information provided as personalized suggestions or advice, generated based on the user's preferences and past behavior.

[0659] A "display device" refers to equipment or software used to provide information to users visually, and includes computer monitors and smartphone screens.

[0660] "Exhibition history" refers to a record of past exhibitions of artworks, including information such as the location and duration of the exhibition.

[0661] "Market trends" refer to specific tendencies and shifts in popularity observed over time within the art industry.

[0662] "Reactions" refer to the comments and evaluations that users provide after viewing an artwork, and these are used to improve the system.

[0663] "Accuracy" is a measure of how well the recommendation information generated by the system matches the user's expectations, and it serves as an indicator of reliability.

[0664] This invention relates to an information processing system for personalizing the appreciation of artworks and providing users with an optimal exhibition experience. In particular, it is realized through the collaboration of a server, a terminal, and the user, each playing their respective roles.

[0665] Server Role

[0666] The server first collects information about artworks from museums and galleries via APIs and data feeds. This information includes high-resolution images of the artworks, artist information, and past exhibition history. The HTTP protocol is used for this data collection. Next, machine learning libraries such as TensorFlow or PyTorch are used on the collected image data to extract features such as color, composition, and style using image recognition models. Furthermore, NLTK or spaCy is used for natural language processing to analyze related text data and extract the artist's style and the theme of the artwork.

[0667] The server then uses collaborative filtering and content-based filtering to generate personalized recommendations tailored to the user's interests. At this stage, it takes into account the user's past browsing history and interests to calculate the optimal artwork and exhibition route.

[0668] Terminal role

[0669] The terminal visually presents the server-generated recommendation information to the user. The interface on the terminal allows users to customize their interests in detail using checkboxes and sliders. Artwork is displayed in a list with thumbnail images, and users can view detailed information by clicking on works of interest. This process utilizes databases such as SQLite and Realm, enabling rapid data access and display.

[0670] User roles

[0671] Users select works of art that interest them and check the exhibition route based on the information provided on their device. After viewing the art, they can use the feedback function to input their evaluation and impressions of the artwork. This feedback is sent to the server and contributes to improving the accuracy of the next event.

[0672] Specific example

[0673] For example, if a user enters a prompt such as, "Please create a recommended exhibition route for me, including new Impressionist works," the server interprets this and generates an optimal exhibition route that takes the user's interests into account. This route is displayed step-by-step on the terminal, and the user can use it as a guide for viewing the artworks.

[0674] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0675] Step 1:

[0676] The server collects information on artworks from museums and galleries using APIs and data feeds. As input, it receives data in JSON or XML format provided by each institution via HTTP requests. This data includes images of the artwork, artist information, and past exhibition history. As output, this data is integrated into the server's database and used in the next analysis step. Specifically, the server periodically accesses each data source to update new artwork information.

[0677] Step 2:

[0678] The server analyzes the collected image data using machine learning libraries such as TensorFlow and PyTorch to extract visual features. Image data of artworks stored in a database is used as input. For data processing, an image recognition model extracts features such as color, composition, and style from the images. As output, feature vectors for each artwork are generated and stored in a table. For example, Impressionist works are identified as having softer color tones and brushwork than usual.

[0679] Step 3:

[0680] The server analyzes collected artist information and exhibition history using natural language processing. Text data stored in a database is used as input. Tools such as NLTK and spaCy are used for data analysis to extract the artist's style and themes. Keywords and topics related to each artist and their works are generated as output. Specifically, frequently occurring phrases are extracted from the artist's biography and review articles, and their relevance is evaluated.

[0681] Step 4:

[0682] The device collects information about the user's interests and sends it to the server. The input includes the user's selected art genres and interests in specific artists. The device receives this information through UI elements such as forms and sends it to the server. The output is the user's interest data, which is stored on the server and used in the next recommendation generation step. A concrete example is when a user inputs that they are interested in "Impressionism."

[0683] Step 5:

[0684] The server generates recommendation information using collaborative filtering and content-based filtering based on user interest data. User preference data and artwork characteristic data are used as input. Data processing involves collaborative filtering based on the preference history of similar users and content-based filtering based on feature vectors. As output, a personalized list of recommended artworks is generated and sent to the terminal. Specifically, it analyzes patterns of users who have previously highly rated Impressionist works to determine new Impressionist recommendations.

[0685] Step 6:

[0686] The terminal displays recommendation information provided by the server to the user. The input is a list of recommendations from the server. The terminal displays this in the UI, presenting it in an interactive format. The output allows the user to view details of the recommended works and decide which one to view next. For example, the user can click on a thumbnail to view detailed information about the artwork and the artist's background.

[0687] Step 7:

[0688] After viewing a work, users enter feedback into their device and send it to the server. As input, user impressions and ratings are collected through the device. This information is sent to the server and used to refine the recommendation algorithm. As output, feedback data is stored on the server and used to improve the accuracy of future recommendations. Specifically, users may rate the work on a 5-point scale and add specific comments.

[0689] (Application Example 1)

[0690] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0691] Contemporary museums and galleries fail to adequately provide visitors with information on art pieces tailored to their individual interests and to personalize their viewing experience. As a result, users cannot easily find art pieces that suit their interests, limiting the quality of their viewing experience. Furthermore, providing real-time information and suggesting dynamic exhibition routes that incorporate user feedback is challenging.

[0692] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0693] In this invention, the server includes means for collecting and analyzing information on artworks, means for collecting user interest data and generating recommendations based on that interest data, means for presenting artwork information to the user via a visual device using the analysis results and recommendations, and means for acquiring user gaze information and displaying relevant information on the visual device's display in real time. This makes it possible to recommend artworks tailored to the user's individual interests and provide an immersive viewing experience through real-time information presentation.

[0694] "Information about artworks" refers to data such as image data related to the artwork, information about the creator, and exhibition history.

[0695] "Means of analysis" refers to a function that analyzes information on collected artworks and automatically extracts their characteristics.

[0696] "User interest data" refers to data that shows a user's interests, preferences, and past browsing history.

[0697] "Means for generating recommendations" refers to a function that recommends appropriate artworks and exhibition routes based on collected user interest data.

[0698] "Visual devices" refer to visual information presentation devices that users wear and use, such as smart glasses and head-mounted displays.

[0699] "Acquiring eye-tracking information" refers to sensing the user's eye movements and the direction they are focusing on, and acquiring this information as data.

[0700] "Means of displaying related information in real time" refers to a function that instantly presents related artworks and information based on the user's eye-tracking data and interest data.

[0701] An embodiment of this invention is a system that utilizes a visual device to optimize and personalize art appreciation for a user. This system consists of a server, a visual device worn by the user, and the user themselves.

[0702] The server first collects information about artworks from museums and galleries. This includes image data of the artworks, information about the artists, and past exhibition history. The server then uses image recognition technology (e.g., Google Cloud Vision API) to analyze the features of the artworks and extract feature data. Furthermore, it collects interest data entered by users using visual devices, past browsing history, and feedback, and analyzes this data using natural language processing (e.g., Google Natural Language API) to generate recommendations.

[0703] Visual devices (e.g., smart glasses) use artwork information and recommendations received from a server to display relevant information in real time within the user's field of view. These devices are equipped with cameras and sensors to capture the user's gaze, and this data is sent to the server to help guide the user's interests.

[0704] For example, when a user visits a museum and looks at a nearby Impressionist painting, the device recognizes the painting, displays detailed information, and recommends other related works of art. This experience allows the user to make new discoveries and gain a deeper understanding and enjoyment on subsequent visits.

[0705] An example of a prompt might be, "How can I create a real-time art guide assistant that provides detailed information about Impressionist paintings in the art gallery I'm visiting?"

[0706] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0707] Step 1:

[0708] The server collects information on artworks from museums and galleries. It receives image data, artist information, and exhibition history as input. This information is stored in a database for later analysis.

[0709] Step 2:

[0710] The server analyzes the collected artwork information using image recognition technology. It takes image data as input and extracts characteristic data of the artworks as output. Specifically, it uses the Google Cloud Vision API to identify the color, shape, and style of each artwork and assign tags to them.

[0711] Step 3:

[0712] The server collects user interest data. It receives user interests and browsing history provided via visual devices as input. As output, it analyzes this data to generate a user profile, specifically revealing preferences based on user choices and feedback.

[0713] Step 4:

[0714] The server generates recommendations using an AI model based on user profiles. It takes user profiles and artwork characteristic data as input and generates recommended artworks and exhibition routes as output. Utilizing natural language processing, it precisely combines diverse artwork information to provide users with personalized recommendations.

[0715] Step 5:

[0716] The terminal, or visual device, displays recommendations provided by the server in real time within the user's field of view. It receives recommended artwork information as input and provides details of the artwork, partially overlaid. The output enhances user immersion and enriches the viewing experience.

[0717] Step 6:

[0718] When users view artwork through their visual devices, their gaze information is acquired by the terminal. As an initial input, this gaze data is sent to a server and used for analyzing works of interest. As an output, new preference data is generated from the user's gaze, contributing to the optimization of future exhibition recommendations.

[0719] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0720] This invention relates to a system that collects data on artworks and provides personalized recommendations using preference data and user emotions. The system includes a server, terminals, and an emotion engine, all of which work together.

[0721] The server first collects artwork data from various museums and galleries, storing images, artist information, exhibition history, and other information in a database. This makes it possible to manage large amounts of artwork information efficiently and systematically.

[0722] Next, the server analyzes the characteristics of the artwork based on the collected art data. It extracts the visual features of the artwork using image recognition technology and further analyzes related information using text analysis technology. This information is used as the basis for the recommendation algorithm.

[0723] The device collects preference and emotional data from the user. Users not only input their interests and past browsing history through the device, but also use a video camera and microphone equipped with an emotion engine to acquire visual and auditory emotional information. This emotional information is considered valuable data indicating how the user felt about different works.

[0724] The server combines preference and emotional data sent from the terminal to generate a list of the most suitable artworks for the user. In particular, the emotional state captured by the emotion engine is used to fine-tune the recommendations, prioritizing artworks that resonate more emotionally with the user.

[0725] As a concrete example, a user accesses an art curation application through their device and selects their favorite painting style. The emotion engine recognizes the emotions the user felt towards works they have viewed in the past and sends that data to the server. For example, if a user strongly expresses joy or curiosity when viewing Impressionist works, the system will focus on recommending works in that style.

[0726] In this way, the present invention, through the collaboration of a server, terminal, and emotion engine, can optimize a personalized art viewing experience based on the user's preferences and emotional state. This approach is expected to promote unique visits to museums and galleries and deeply resonate with the individual emotional experiences of the audience.

[0727] The following describes the processing flow.

[0728] Step 1:

[0729] The server collects artwork data from partner museums and galleries. This includes detailed information such as image files of the artwork, artist name, genre, year of creation, and past exhibition history. The collected data is converted to a standard format and stored in a database.

[0730] Step 2:

[0731] The server analyzes the stored art data and uses image recognition technology to extract the visual characteristics (color, composition, etc.) of each artwork. It also uses text mining technology to obtain themes and related information from artwork descriptions and reviews. The results of this analysis help understand the characteristics of each artwork and are used for future recommendations.

[0732] Step 3:

[0733] The device receives user preference data as input. This includes lists of works previously viewed, preferred art styles and artists, etc. The user sends this information to the server through the application interface.

[0734] Step 4:

[0735] The device activates an emotion engine to recognize the user's current emotional state. Using a video camera and microphone, it analyzes the user's facial expressions and voice tone to identify emotions such as joy, anger, sadness, and happiness. The identified emotion data is transmitted to the server in real time.

[0736] Step 5:

[0737] The server integrates the received preference and emotional data and runs an algorithm to select the most appropriate artwork for the user. Emotional data is used to fine-tune the artwork to match the user's preferred types of artwork and their current mood.

[0738] Step 6:

[0739] The terminal displays a list of recommended artworks generated from the server to the user. The user can select artworks of interest from this list and view detailed information and explanations. Selected artworks may also be presented as a recommended new exhibition route.

[0740] Step 7:

[0741] Users input feedback on their impressions and thoughts after viewing the content. This feedback is sent to the server and stored as data to improve the accuracy of recommendations for future viewings.

[0742] Step 8:

[0743] The server updates its recommendation algorithms based on feedback, continuously improving the overall accuracy of the system. This process enhances the quality and personalization of the art experience provided to users.

[0744] (Example 2)

[0745] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0746] Efficiently collecting information on diverse art works and providing personalized recommendations based on user preferences and emotions is challenging. Furthermore, to evoke emotional resonance and provide a deeper art experience, it is necessary to appropriately analyze emotional information and utilize it in art recommendations.

[0747] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0748] In this invention, the server includes means for collecting and analyzing information on artworks, means for collecting user preference and sentiment information and generating recommendation results based on the preference and sentiment information, and means for providing personalized artworks to the user using a generative model. This makes it possible for the user to receive more personalized recommendations for artworks.

[0749] "Artwork" refers to a visual art object that possesses artistic value, and includes paintings, sculptures, photographs, and other visual arts.

[0750] "Information" refers to data and knowledge about artworks and users, including image data, text information, history, and emotional states.

[0751] "Analysis" refers to the process of extracting useful features and patterns from collected information, and this includes data analysis using image analysis and natural language processing.

[0752] A "user" refers to an individual or organization that uses this system to receive recommendations for artworks.

[0753] "Preference information" refers to data that indicates a user's preferences and interests, and this is collected from past selection history and input data.

[0754] "Emotional information" refers to data that indicates the user's emotional state, and this is obtained by analyzing visual and auditory responses.

[0755] A "generative model" refers to a system that generates predictions and recommendations by analyzing data using machine learning algorithms.

[0756] "Personalized recommendations" refer to suggestions of artwork tailored to each user's preferences and emotional information.

[0757] This invention is a system that efficiently collects information on works of art and provides personalized recommendations based on user preferences and emotions. It is achieved through the collaboration of a server, terminals, and an emotion analysis engine.

[0758] The server first collects information on artworks from various museums and galleries via APIs. The software used here includes a database management system and a deep learning framework for image analysis (e.g., TensorFlow, PyTorch). Using deep learning technology, it extracts visual features such as color and shape from images of artworks, and analyzes exhibition history and descriptions using natural language processing technology. This generates characteristic data for each artwork.

[0759] The terminal is responsible for direct input from the user. Users can input their preferred art style and past viewing history through an art curation application installed on the terminal. Furthermore, the terminal is equipped with a camera and microphone, which are used to acquire emotional information from the user's facial expressions and voice. The emotion analysis engine determines the user's emotional state based on the acquired visual and audio data and sends that data to the server.

[0760] Upon receiving this information, the server uses a generative model to select the most suitable artwork for the user. The generative model analyzes the user's preference and emotional information and creates a personalized recommendation list using an algorithm. At this stage, the system prioritizes artwork that evokes positive emotions such as joy and interest.

[0761] As a concrete example, a user can access an art curation application using their device and, in response to a prompt such as "I'm interested in modern art," indicate their preferences. Furthermore, when viewing artwork at an exhibition venue, the device analyzes the user's emotional responses, and the server adjusts the next artwork recommended based on that data. Through this entire process, users can enjoy a more personalized art experience.

[0762] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0763] Step 1:

[0764] The server collects art information from museums and galleries. Inputs include image data, artist information, and exhibition history of artworks obtained through each facility's API. This information is stored in a database, and data cleaning and formatting are performed as needed. The output is detailed information about the artworks, stored in a unified format.

[0765] Step 2:

[0766] The server performs image and text analysis using the collected artwork information. The input consists of images and text data of the artworks saved in Step 1. A deep learning framework is used to extract visual features from the images, and natural language processing techniques are used to analyze the text data. The output is a dataset that quantifies the characteristics of each artwork.

[0767] Step 3:

[0768] The device collects preference information from the user. The user inputs their preferred art style and past viewing history as options through an application on the device. The input is in the user's chosen format and is then formatted by converting it to a standard data format. The output is data indicating the user's preferences.

[0769] Step 4:

[0770] The device collects user emotional information. This includes recording the user's facial expressions and voice using the device's built-in camera and microphone. The input is real-time visual and audio data, which is analyzed by an emotion analysis engine. The output is quantitative data indicating the user's emotional state.

[0771] Step 5:

[0772] The server combines user preference and emotional information and uses a generative AI model to generate a personalized list of recommended artworks. The input is the output data from steps 3 and 4, which the model uses to learn and generate recommendation results. The output is a list of artworks optimized for each user. This list is adjusted to prioritize the user's emotional resonance.

[0773] Step 6:

[0774] The terminal displays a personalized recommendation list sent from the server via a user interface. The input is the recommendation list received from the server, which is displayed in a visually easy-to-understand form. The output is a display showing the user's selected works. User feedback is collected and used for future recommendations.

[0775] (Application Example 2)

[0776] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0777] Traditional art appreciation systems, while capable of recommending artworks based on a user's specific preferences, have limitations in deeply engaging with users' emotions and optimizing individual emotional experiences. Furthermore, there is a growing demand for more personalized experiences that incorporate emotional elements into virtual art environments.

[0778] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0779] In this invention, the server includes means for collecting and analyzing data on artworks, means for collecting user preference data and emotional information and generating recommendations based on that data, and means for presenting artworks to the user that enhance emotional resonance using the analysis results and emotional data. This makes it possible to provide a more deeply resonant art experience that is tailored to the user's emotional state.

[0780] An "artwork" is a creative work, primarily a visual art, that is exhibited in museums or galleries.

[0781] "Data" is a logically organized form of information, and it is an element that is useful for analysis and interpretation.

[0782] "Preference data" refers to information that indicates a user's personal preferences and interests, and is used to provide personalized services.

[0783] "Emotional information" refers to data that indicates the user's emotional state and is collected through the emotion engine.

[0784] An "emotion engine" is a system that analyzes a user's emotions from their facial expressions and voice, and is used to optimize the user experience.

[0785] "Recommendations" refer to the selection of specific artworks based on user preference data and emotional information.

[0786] A "virtual environment" is a virtual space created using digital technology, offering an experience different from that of a real place.

[0787] A "virtual display device" is a device used to display digital content to a user, and includes smart glasses and head-mounted displays.

[0788] The system for realizing this invention includes a server, a terminal, and an emotion engine as its main components. The server collects data on artworks from museums and galleries and extracts the visual features of the artworks using image analysis techniques. It also integrates relevant information into a database using text analysis techniques. This utilizes software such as TensorFlow and OpenCV.

[0789] The device plays a role in collecting user preference and sentiment data. This involves data input based on user preferences and past browsing history, as well as real-time analysis of user sentiment information using the camera and microphone. Platforms such as Azure Cognitive Services and Google Cloud Vision AI are used for analyzing sentiment information.

[0790] The server comprehensively analyzes collected artwork data and user preference and emotional data to generate personalized recommendation content for each user. This result is presented on virtual display devices such as smartphones and smart glasses, allowing users to experience art that best suits their emotional state.

[0791] As a concrete example, suppose a user visits a virtual gallery and is viewing an Impressionist exhibition. The system detects the user's emotions of joy and prioritizes displaying works that evoke similar emotions. Using a generative AI model, the system performs the analysis according to a prompt such as, "Analyze how the artwork the user is viewing emotionally impacts them, and select the artwork that resonates most emotionally with the user."

[0792] A system configured in this way, through the coordination of servers, terminals, and an emotion engine, can provide users with a more engaging and personalized art viewing experience.

[0793] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0794] Step 1:

[0795] The server collects data on artworks from various museums and galleries. This process digitally acquires image data, artist information, and exhibition history of the artworks and stores them in a database. Input is data received from data provision APIs of museums and galleries, and output is organized database entries. This enables efficient data management.

[0796] Step 2:

[0797] The server analyzes the collected artwork data. For image data, TensorFlow and OpenCV are used to extract visual features. For text data, natural language processing techniques are used to analyze artist information and exhibition history. The input is artwork data stored in a database, and the output is feature-extracted data. This allows for the modeling of the artwork's characteristics.

[0798] Step 3:

[0799] The device collects user preference data. This is done by collecting past browsing history and selected art styles from the user's smart device. The input is user data from the smart device, and the output is the user's preference profile. This digitally represents the user's preferences.

[0800] Step 4:

[0801] The device collects user emotional information. It uses a camera and microphone equipped with an emotion engine to analyze the user's facial expressions and voice, collecting emotional data. The input is real-time data of the user's facial expressions and voice, while the output is analyzed emotional state data. This allows the device to understand the user's emotional state.

[0802] Step 5:

[0803] The server integrates preference data and emotional information, and uses a generative AI model to select artworks to recommend to the user. Based on prompts, it evaluates the emotional impact each artwork has on the user and lists the artworks that resonate most with them. The input is the user's preference profile and emotional state data, and the output is a list of emotionally resonant artworks.

[0804] Step 6:

[0805] The terminal displays the generated recommendation list on a virtual display device. Here, the user can view the presented artwork in a virtual space. The input is a list of artworks provided by the server, and the output is an art exhibition unfolded in the virtual space. This allows the user to have an emotionally rich art viewing experience.

[0806] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0807] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0808] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0809] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0810] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0811] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0812] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0813] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0814] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0815] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0816] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0817] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0818] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0819] 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.

[0820] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0821] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0822] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0823] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0824] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0825] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0826] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0827] The following is further disclosed regarding the embodiments described above.

[0828] (Claim 1)

[0829] A means for collecting data on artworks and analyzing that data,

[0830] A means for collecting user preference data and generating recommendation content based on said preference data,

[0831] A means of presenting artworks to users using the analysis results and recommendations,

[0832] A system that includes this.

[0833] (Claim 2)

[0834] The system according to claim 1, further comprising means for analyzing past exhibition history and analyzing market trends.

[0835] (Claim 3)

[0836] The system according to claim 1, further comprising means for collecting user feedback and improving the accuracy of the recommendations.

[0837] "Example 1"

[0838] (Claim 1)

[0839] A means for collecting information on artworks and extracting features from that information using image and text analysis,

[0840] A means for collecting information about users' interests and generating personalized recommendation information based on that information,

[0841] A means for providing artworks on a display device using the aforementioned features and recommendation information,

[0842] A system that includes this.

[0843] (Claim 2)

[0844] The system according to claim 1, further comprising means for analyzing exhibition history and analyzing trends in cultural activities.

[0845] (Claim 3)

[0846] The system according to claim 1, further comprising means for collecting user feedback and improving the accuracy of the recommendation information.

[0847] "Application Example 1"

[0848] (Claim 1)

[0849] A means for collecting information on works of art and analyzing that information,

[0850] A means for collecting user interest data and generating recommendations based on said interest data,

[0851] A means of presenting art information to a user via a visual device using the analysis results and recommendations,

[0852] A means for acquiring user eye-tracking information and displaying related information in real time on the display of a visual device,

[0853] A system that includes this.

[0854] (Claim 2)

[0855] The system according to claim 1, further comprising means for analyzing past exhibition history and analyzing market trends.

[0856] (Claim 3)

[0857] The system according to claim 1, further comprising means for collecting user feedback and improving the reliability of the recommendations.

[0858] "Example 2 of combining an emotion engine"

[0859] (Claim 1)

[0860] A means for collecting information on works of art and analyzing that information,

[0861] A means for collecting user preference information and sentiment information, and for generating recommendation results based on said preference information and sentiment information,

[0862] A means of providing personalized artwork to users using a generative model,

[0863] A means for analyzing emotional states acquired through visual and voice input,

[0864] A system that includes this.

[0865] (Claim 2)

[0866] The system according to claim 1, further comprising means for analyzing past exhibition borrowings and analyzing market trends.

[0867] (Claim 3)

[0868] The system according to claim 1, further comprising means for collecting user evaluations and improving the accuracy of the recommendation results.

[0869] "Application example 2 when combining with an emotional engine"

[0870] (Claim 1)

[0871] A means for collecting data on artworks and analyzing that data,

[0872] A means for collecting user preference data and sentiment information, and generating recommendation content based on said data,

[0873] A means of presenting art works that enhance emotional resonance to users using the aforementioned analysis results and emotional data,

[0874] A means of tracking user behavior in a virtual environment and presenting artworks via a virtual display device,

[0875] A system that includes this.

[0876] (Claim 2)

[0877] The system according to claim 1, further comprising means for analyzing past exhibition history and user emotional responses to analyze cultural trends.

[0878] (Claim 3)

[0879] The system according to claim 1, further comprising means for collecting emotional feedback from users and improving the emotional impact of the recommendations. [Explanation of symbols]

[0880] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for collecting data on artworks and analyzing that data, A means for collecting user preference data and generating recommendation content based on said preference data, A means of presenting artworks to users using the analysis results and recommendations, A system that includes this.

2. The system according to claim 1, further comprising means for analyzing past exhibition history and analyzing market trends.

3. The system according to claim 1, further comprising means for collecting user feedback and improving the accuracy of the recommendations.

Images