system

Abstract

We provide the system. [Solution] A means for integrating and managing preference data collected from users, A means for fusing multiple generative models based on the preference data to generate optimized information suggestions, A means for dynamically adjusting and displaying the generated information on the user's terminal, 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 persona chatbot control method 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] ​​​​​​​​​​​​​​​​​​​​​[This invention provides a system that integrates preference data collected from users and, based on that data, fuses multiple generative models to provide optimized information suggestions. This system includes a function to dynamically adjust and display the generated information on the user's terminal, and improves the performance of the generative models by aggregating user feedback. Furthermore, it includes an algorithm that extracts common hobbies and preferences among multiple users to support group decision-making. This enables efficient and effective information provision in various scenarios, thereby improving user satisfaction.]

[0006] "Users" refer to individuals or organizations that use the system and are the entities that receive information.

[0007] "Preference data" refers to information that specifically indicates a user's interests, concerns, and preferences, and is collected and analyzed by the system.

[0008] A "generative model" refers to an algorithm or program that generates information and suggestions based on user preference data and other external data.

[0009] "Fusion" is the process of combining multiple generative models and information to produce a newly integrated output.

[0010] "Information suggestions" refer to customized information and recommendations provided by the system in a way that responds to the user's preferences and needs.

[0011] A "terminal" is a device used by users to receive information and perform operations, and includes smartphones and computers.

[0012] "Feedback" refers to the evaluations and opinions of users regarding the information and services provided, and is data used to improve the system.

[0013] An "algorithm" refers to a series of procedures or processing steps set up to achieve a specific purpose, and is used in computation and data processing. [Brief explanation of the drawing]

[0014] [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] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0015] 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.

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

[0017] In the following embodiments, a labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0020] 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).

[0021] 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."

[0022] [First Embodiment]

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

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0029] 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.

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

[0031] As shown in Figure 2, in the data processing device 12, 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] This invention provides a system that collects and analyzes user preference data and integrates multiple generative models to offer optimal information suggestions. The system mainly consists of a server, terminals, and users, which work together in coordination with each other.

[0036] The server receives preference data from users and stores it in a database. This data includes content that individual users have previously accessed and items they have shown interest in. The server integrates and analyzes this data to extract common characteristics across all users or groups.

[0037] Next, the server uses a generative model to create information suggestions based on the analysis results. The generative model combines different algorithms and AI technologies, which are dynamically merged to produce suggestions optimized for specific scenarios. For example, a user in a zoo can be provided with detailed descriptions of specific animals and related event information.

[0038] The server sends the generated information to the terminal. The terminal receives this information and dynamically adjusts the interface to present it to the user intuitively and effectively. This allows the user to quickly obtain the necessary information, improving convenience.

[0039] Furthermore, users can send feedback about the information provided from their devices. The server analyzes this feedback and uses it to improve the generative model. By continuously accumulating and analyzing feedback, the overall system performance improves, enabling more precise information suggestions.

[0040] Specific example:

[0041] For example, when this system is used in a zoo, users can search for information about their favorite animals on their devices. The server generates detailed information about the animal's ecology, characteristics, and where it is kept, and sends it to the device. Users can then view the presented information to plan their visit or learn about specific animals. In this way, users can explore the zoo efficiently and have a more fulfilling experience.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] Users operate a device and input data about their individual hobbies and preferences. This includes their favorite animals, activities of interest, and past visit history. The device collects this data and sends it to the server.

[0045] Step 2:

[0046] The server stores the received user data in a database. The database integrates preference data obtained from multiple users and updates each user's profile.

[0047] Step 3:

[0048] The server analyzes the data and runs algorithms to extract common interests and trends. This process utilizes machine learning techniques to identify group-specific features and patterns.

[0049] Step 4:

[0050] The server applies a generative model to generate information suggestions based on extracted features. The generative model utilizes pre-trained AI technology to construct information optimized for each user or user group.

[0051] Step 5:

[0052] The server sends the generated information to the terminal. Based on the received information, the terminal adjusts the user interface as needed to display the information in a visually easy-to-understand manner.

[0053] Step 6:

[0054] Users review the presented information and view details about specific animals, event information, and more. Any feedback or additional requests from the user are sent from the device to the server.

[0055] Step 7:

[0056] The server receives user feedback and reflects it in the database. This allows the system to use the feedback to improve the accuracy of generative models and information suggestions.

[0057] (Example 1)

[0058] 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."

[0059] In modern information systems, there is a challenge in accurately understanding the diverse preferences of users and efficiently providing personalized information suggestions based on those preferences. Furthermore, while it is necessary to further optimize systems by effectively incorporating user feedback, existing methods have limitations. Moreover, there is a need to leverage common preferences among multiple users to provide even greater value.

[0060] 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.

[0061] In this invention, the server includes means for integrating and storing preference data collected from users, means for analyzing collective preference patterns based on the preference data, and means for dynamically fusing multiple generation algorithms based on the analysis results to generate optimized information suggestions. This enables highly accurate information suggestions based on individual user preferences, and further enables multi-layered value provision through the analysis of collective preferences.

[0062] "Preference data" refers to a collection of information that shows a user's past behavior and interests.

[0063] A "generative algorithm" is a process that integrates multiple algorithms to generate optimal information based on data.

[0064] "Feedback" refers to the evaluations and opinions that users give regarding the information provided by the system.

[0065] A "common preference pattern" refers to characteristics that indicate shared interests and concerns among multiple users.

[0066] "Information suggestions" refer to customized information provided to users by a generation algorithm based on analysis results.

[0067] An "analytical algorithm to support group decision-making" is a computational process that analyzes the preferences and opinions of multiple users to help make optimal decisions.

[0068] A description of embodiments for carrying out this invention will be given.

[0069] The server serves as a means of receiving, integrating, and storing preference data sent by users in a database. This preference data includes content that users have previously accessed and interests they have shown. The server uses this data to run algorithms to analyze collective preference patterns. Machine learning techniques and AI methods are utilized in the analysis.

[0070] Next, based on the analysis results, the server dynamically merges multiple generation algorithms and executes the process to propose the most suitable information. This generation algorithm fusion involves combining different AI models to generate data that adapts to specific conditions.

[0071] The terminal receives information provided by the server and dynamically adjusts the interface presented to the user. This allows the user to obtain information intuitively and effectively. The information presented may take various forms, including text, images, and videos.

[0072] Furthermore, users can send feedback on the provided information from their devices. This feedback is collected on the server and used to further improve the performance of the generation algorithm. Through this process, the system is continuously improved, and the accuracy of suggestions to users becomes practically better.

[0073] For example, a user visiting a zoo might send a prompt message from their device such as, "Tell me the latest panda event information." In this case, the server generates and provides optimal information suggestions that reflect the user's interests. This allows the user to efficiently plan their visit.

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] The server receives user preference data sent from the terminal and stores it in a database. Input data includes the user's access history and items they are interested in. The server then processes this data to normalize it and store it in a consistent format. This process yields a dataset that reflects the user's preferences.

[0077] Step 2:

[0078] The server analyzes preference data stored in the database and extracts collective preference patterns. Previously stored preference data is used as input. The data is subjected to data calculations that apply machine learning algorithms to find common patterns, and the output is preference patterns and trends as analysis results. This result provides foundational data that enables information suggestions tailored to users and user groups.

[0079] Step 3:

[0080] The server generates information suggestions by fusing multiple generative AI models based on the analysis results of preference patterns. The input consists of the analysis results and available generative AI models. The server performs data calculations to integrate different AI models and generate optimal information, with the output being personalized information suggestions presented to the user. This process creates recommendations tailored to the user's preferences.

[0081] Step 4:

[0082] The server sends the generated information suggestions to the terminal. The input is the information suggestion data. The terminal receives this and dynamically constructs an interface to display the information appropriately for the user. The output is a display optimized for the user's screen. This makes the information easier for the user to understand intuitively.

[0083] Step 5:

[0084] Users submit feedback from their devices based on the information provided. Inputs include user satisfaction levels and requests for additional information. The server receives the feedback and performs an analysis. The output is feedback data used to improve the generated AI model. As a result, the system improves accuracy over time, enabling more effective information suggestions.

[0085] (Application Example 1)

[0086] 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."

[0087] There is a need to improve the accuracy of information provision based on users' interests and preferences, and to realize more personalized content suggestions. However, current systems struggle to efficiently provide information suitable for individual users, and the presentation of related product information is limited. The challenge is to solve this problem and provide a system that allows users to easily and intuitively search for and display information.

[0088] 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.

[0089] In this invention, the server includes means for integrating and managing interest information collected from users, means for fusing multiple generation algorithms based on the interest information to generate optimized information, and means for dynamically adjusting and displaying the generated information on the user's information processing device. This enables more personalized content suggestions for users by providing relevant data based on viewing history and displaying relevant product information.

[0090] "User" refers to an individual person who uses or consumes a particular system or content.

[0091] "Interest information" refers to data that indicates a user's interest in specific content or topics.

[0092] "Integrating and managing" refers to gathering data from different sources, organizing and storing it centrally, and making it usable efficiently.

[0093] A "generative algorithm" refers to a set of computational procedures or methods used to process data according to a specific purpose and generate new information.

[0094] "Dynamically adjusting and displaying information" means changing the way information is presented in real time according to the user's situation and requests.

[0095] An "information processing device" refers to a machine or device that has the function of collecting and analyzing data and displaying or saving the results.

[0096] "Related data" refers to information that is associated with the presented information and provides additional value.

[0097] "Product information" refers to data that describes details about a specific product, such as its specifications, features, price, and usage instructions.

[0098] "Personalized content suggestions" refers to providing information optimized for each individual user based on their interests and preferences.

[0099] This invention is based on a system centered around a server, a terminal, and a user, in order to provide personalized information to users.

[0100] First, the server collects and integrates user interest information. This interest information is gathered from the user's past interests and accessed content, and stored in a database. This creates a dataset that reflects the individual preferences of each user.

[0101] Next, the server uses a generative AI model based on the interest information. Here, multiple generative algorithms are dynamically merged to generate optimized information. The generated information is adapted to provide appropriate content suggestions for the user in a specific usage scenario.

[0102] The generated information is then transmitted to the user's information processing device, the terminal. The terminal receives this information, dynamically adjusts it according to the user's situation and device characteristics, and then displays it. This allows the user to receive information in a visually optimized format.

[0103] In addition, the server receives feedback from users and uses that feedback to improve the performance of the generation algorithm. This feedback loop gradually improves the overall recommendation accuracy of the system.

[0104] For example, if a movie enthusiast wants information on new releases, the server analyzes their movie viewing history and suggests relevant data, including related titles and trailers for new releases. Furthermore, it can also provide related product information, such as purchase information for DVDs and soundtracks.

[0105] An example of a prompt message is, "Generate the latest movie release information for action movies that this user likes, and also list recommended related merchandise." This is how instructions can be given to the generative AI model. The main hardware in this system is Amazon Web Services (AWS®), and the software used to build the AI ​​model includes PyTorch and TENSORFLOW®.

[0106] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0107] Step 1: The server collects user interest information.

[0108] The server retrieves users' past access history and content evaluation data from a database and integrates this as interest information. The collected information indicates users' interests and behavioral patterns.

[0109] Step 2: The server performs data analysis using interest information.

[0110] Based on the input interest information, the server uses a collaborative filtering algorithm to analyze the data and identify highly relevant content. The output is the analysis results, which form the basis for providing users with the most relevant information.

[0111] Step 3: The server generates information suggestions using the generated AI model.

[0112] The server inputs the analysis results into a generative AI model, which then creates optimal information suggestions based on this input. In this process, different algorithms are combined, and a content list tailored to the user's interests is output according to the prompts.

[0113] Step 4: The server sends the generated information to the terminal.

[0114] The server sends the generated information suggestions as data packets to the user's terminal, which the terminal receives. This prepares the terminal to display information in response to the user's actions.

[0115] Step 5: The device dynamically displays information.

[0116] The device dynamically adjusts the layout, taking into account screen size and device specifications, to display received information in the most optimal format for the user. As a result, the user sees visually effective information on the screen.

[0117] Step 6: Evaluate the user's information and submit feedback.

[0118] Users provide ratings and comments on the displayed information and send this feedback from their device to the server. This accumulates data that helps improve the generated AI model.

[0119] 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.

[0120] This invention constructs a system that combines user preference data and emotional data to provide optimized information. The system consists of a server, terminals, an emotional engine, and the user. This makes it possible to provide a more personalized experience.

[0121] First, users register their hobbies and interests via a device. The device is equipped with a camera and microphone, and these devices are used to collect real-time emotional data from the user's facial expressions and tone of voice. The emotion engine analyzes this data to identify the user's emotional state.

[0122] The emotional data analyzed by the emotion engine, along with user preference data, is sent from the device to the server. Upon receiving this data, the server stores it in a database for centralized management.

[0123] The server then fuses and analyzes the received preference and emotion data. This utilizes a generative model that takes emotional tendencies into account. This model has the ability to select and generate appropriate information according to a specific emotional state. Specifically, it adjusts the content soothing if the user is relaxed, and provides stress-reducing information if they are tense.

[0124] The generated information is sent from the server to the terminal, which then presents this information to the user in an easy-to-understand manner. The interface is dynamically adjusted to provide a presentation that matches the user's current emotional state. This allows users to receive a service that fits their emotions, leading to increased satisfaction.

[0125] Specific example:

[0126] For example, when a user visiting a museum uses this system, the terminal detects their emotions from their facial expressions and voice. If they are relaxed, it suggests exhibition information, including soothing music that matches their current mood. If the user is excited, it can enhance their visit by providing more interactive and participatory activity information. By combining this emotion-driven information suggestion, users can have the most optimal experience at that moment.

[0127] The following describes the processing flow.

[0128] Step 1:

[0129] The device collects data on the user's hobbies and interests, and uses its camera and microphone to recognize the user's facial expressions and voice tone in real time as emotions. This data is then converted into emotional states through an emotion engine.

[0130] Step 2:

[0131] The device sends the collected preference and emotional data to the server. During this process, the data is appropriately formatted and encrypted to protect privacy.

[0132] Step 3:

[0133] The server stores received preference and emotion data in a database and updates individual user profiles. The database also includes records of each user's different emotional states, enabling dynamic data management.

[0134] Step 4:

[0135] The server analyzes the received data and generates optimized information suggestions at that point using a generative model that takes emotional data into account. For example, if the user is feeling stressed, the generative model might generate suggestions related to relaxation.

[0136] Step 5:

[0137] The server sends the generated suggestions to the terminal. Based on the received information, the terminal adjusts and displays the interface in a way that suits the user's emotions.

[0138] Step 6:

[0139] Users receive the presented information and can send feedback from their device to the server as needed. This feedback reflects the user's satisfaction level and newly identified preferences.

[0140] Step 7:

[0141] The server analyzes the feedback it receives and uses it to improve the generative model. The feedback data continuously improves the accuracy of user sentiment-based suggestions, thereby enhancing the overall system performance.

[0142] (Example 2)

[0143] 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".

[0144] In modern information processing systems, providing information suggestions that consider not only user preferences but also their real-time emotional state is crucial for delivering a highly satisfying experience. However, conventional systems have limitations in analyzing emotional data and providing appropriate information based on it, failing to achieve complete personalization that fully responds to user emotions. Furthermore, the technology for efficiently utilizing user feedback to improve information suggestions is insufficient.

[0145] 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.

[0146] In this invention, the server includes means for integrating and managing preference data and emotional data collected from users; means for fusing multiple generative models based on the preference data and emotional data to generate optimized information suggestions according to the user's emotional state; and means for dynamically adjusting and displaying the generated information on the user's terminal, and presenting it in a way that is appropriate to the user's current emotional state. This enables advanced personalization tailored to the user's emotions and continuous improvement of the system's performance through feedback.

[0147] "Preference data" refers to data that shows information about the areas and activities that users are interested in.

[0148] "Emotional data" refers to information that indicates the user's emotional state, and is acquired through facial recognition and voice analysis.

[0149] A "generative model" is an algorithm used to generate new content or information based on input data.

[0150] "Feedback" refers to information that users provide, expressing their evaluations and reactions to the information and services offered, and is used to improve the system.

[0151] Personalization is the process of optimizing services and content according to the individual preferences and needs of each user.

[0152] A "server" is a computer system that processes information, stores and manages data, and transmits information to terminals as needed.

[0153] A "terminal" is a device that allows users to access a system and receive information through its interface.

[0154] This invention constructs a system that combines user preference data and real-time sentiment data to provide personalized information. This system consists of a server, a terminal, a sentiment analysis engine, and the user, and each element works in cooperation with the others.

[0155] Users first register their hobbies and interests via a device. The device is equipped with a camera and microphone, and these devices are used to capture the user's facial expressions and voice tone, collecting real-time emotional data.

[0156] In this system, the terminal sends collected data to the sentiment analysis engine, which analyzes this data to identify the user's emotional state. The analysis results and preference data are then sent from the terminal to the server.

[0157] The server stores the received preference and emotion data in a database and then uses it for analysis. It uses a generative AI model to select and generate the most appropriate information based on a specific emotional state. For example, when the user is relaxed, it provides calming music information, and when they are stressed, it suggests information to reduce stress.

[0158] The generated information is sent from the server to the terminal and presented to the user in a dynamically adjusted form on the terminal. The user interface is optimized to adapt to the user's emotions, allowing the user to receive information that resonates with their feelings. As a result, a highly satisfying experience is provided.

[0159] As a concrete example, when a user visits a museum, the device detects a relaxed state from their facial expressions and voice and suggests calm exhibit information appropriate for the situation. On the other hand, if an excited state is detected, it presents more interactive activity information. This system allows users to enjoy the best possible experience according to their emotions at that moment.

[0160] An example of a prompt message used in a generative AI model would be an instruction such as, "Suggest optimal content for a relaxed user, and engage both their visual and auditory senses."

[0161] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0162] Step 1: The user registers their hobbies and interests through the device. The input is the user's own information about their hobbies and interests, and the output is saved on the device as preference data. Specifically, registration is performed by selecting items on the device's interface or filling in data in input forms.

[0163] Step 2: The device uses its built-in camera and microphone to collect real-time emotional data from the user. The input is the user's facial expressions and voice tone, and the output is emotional data obtained by analyzing these. Specifically, this involves capturing facial expressions with the camera and processing voice input.

[0164] Step 3: The device sends the collected emotional data to the emotion analysis engine. The input is the emotional data obtained in Step 2, and the output is the detailed emotional state analyzed by the emotion analysis engine. Specifically, the emotion analysis algorithm runs and the data is analyzed.

[0165] Step 4: The terminal sends the analyzed sentiment and preference data to the server. The input is the analyzed sentiment and preference data, and the output is the server that receives this data. Operationally, the data is encoded and securely transmitted over the network.

[0166] Step 5: The server stores the received preference and emotion data in a database and then integrates and analyzes this data. The input is the received preference and emotion data, and the output is the analysis results based on this data. Specifically, the process involves writing to the database and analyzing the data using a generative AI model.

[0167] Step 6: The server uses a generative AI model to select and generate information that matches the user's emotional state. The input is the analysis results obtained in Step 5, and the output is the optimized information provided to the user. The operation includes an information generation process by the AI ​​model based on prompt statements.

[0168] Step 7: The server sends the generated information to the terminal. The input is the generated information data, and the output is the terminal that received the information. Specifically, the information is sent based on the data transmission protocol from the server.

[0169] Step 8: The terminal dynamically adjusts the received information on the user interface and presents it to the user. The input is the information received from the server, and the output is the content displayed on the screen shown to the user. In operation, the interface dynamically changes according to the user's current emotional state, presenting the information in the most optimal way.

[0170] (Application Example 2)

[0171] 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".

[0172] This invention aims to address the challenge of personalizing digital content delivery in accordance with the user's emotional state. Existing content distribution systems generally provide information based solely on user preference data, and do not adequately provide flexible content recommendations that take into account the user's instantaneous emotional state. As a result, users often receive content that does not match their emotions or mood, leading to decreased satisfaction.

[0173] 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.

[0174] In this invention, the server includes means for integrating and managing preference data and emotional data collected from users; means for fusing multiple generative models based on the preference data and emotional data to generate information suggestions adapted to the user's emotional state; and means for dynamically adjusting the generated information on the user's terminal and presenting it in visual and auditory representations corresponding to the user's emotional state. This makes it possible to provide content that is appropriate to the user's emotions in a timely manner, thereby improving the user experience.

[0175] "Preference data" refers to information about the genres and content that users prefer, and is used for selecting and recommending content.

[0176] "Emotional data" refers to data that represents a user's current emotions and mood, and is information obtained from facial expressions, tone of voice, and other biosignals.

[0177] A "generative model" is an algorithm or program that generates or selects content that matches the user's needs and circumstances based on collected data.

[0178] "Information recommendations" are recommendations regarding content and services provided to users, and are determined based on preference data and sentiment data.

[0179] "Visual and auditory representations" refer to the format in which information is presented to the user, including on-screen visual and audio feedback.

[0180] Based on this invention, the system that implements the application example consists of a server, a terminal, an emotion engine, and a user. Specifically, it is implemented as follows:

[0181] First, the device is a smartphone equipped with a camera and microphone. This hardware captures the user's facial expressions and voice tone in real time and collects the data. The device sends this data to the emotion engine. The emotion engine uses Google® Cloud Vision API and IBM Watson® Tone Analyzer to analyze the facial expressions and voice tone and identify the user's emotional state.

[0182] The analyzed sentiment data and preference data previously registered by the user via their device are sent to the server. The server stores and integrates this collected data in a database. Next, the server utilizes generative AI models, including OpenAI's GPT-3, to select appropriate content based on a specific sentiment state. In this selection process, the generative AI model uses prompt statements to generate content that matches the sentiment.

[0183] The generated information is sent from the server to the terminal, which then displays the content in a format that matches the user's emotional state. This display utilizes both visual and auditory representations, enabling a more personalized experience for the user.

[0184] As a concrete example, when a user is using the application in a relaxed state in the evening, classical music and sunset scenery videos selected based on their past preference data will be automatically presented. An example of a prompt message used in this case might be, "Please recommend music and videos that the user should watch when they are in a relaxed emotional state. They have a history of enjoying classical music."

[0185] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0186] Step 1:

[0187] The device uses a camera and microphone to capture the user's facial expressions and voice tone in real time. The input is the user's facial image and voice signal, and the output is the recording of them as digital data.

[0188] Step 2:

[0189] The terminal transmits the collected facial and audio data to the emotion engine. The input is the digital data obtained in step 1, which is then converted into a data format for analysis and used as the output.

[0190] Step 3:

[0191] The emotion engine uses the Google Cloud Vision API to analyze facial expressions and IBM Watson Tone Analyzer to analyze voice tone. The input is the analysis data format obtained in step 2, and the output is the analysis result indicating the user's emotional state. In this step, facial feature points and voice frequencies are analyzed to identify the emotional state.

[0192] Step 4:

[0193] The server integrates and manages emotional data received from terminals with preference data pre-registered by the user. Input consists of emotional data and preference data, which are combined, stored in a database, and output as basic data for information selection.

[0194] Step 5:

[0195] The server utilizes a generative AI model to generate information suggestions using prompt sentences based on preference and emotion data. The input is the data integrated in step 4, and the output is content information appropriate to the user's emotional state. In this process, the generative AI model plays the role of combining and generating the most suitable content.

[0196] Step 6:

[0197] The generated information is sent from the server to the terminal. The input is the content information obtained in step 5, and the output is converted into a data format for display in visual and auditory formats and sent to the terminal.

[0198] Step 7:

[0199] The device presents the received content using visual and auditory representations that match the user's emotional state. The input is the data received in step 6, and the output is the specific content display for the user. This display performs specific actions, such as playing classical music and soothing images if the user is relaxed.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] [Second Embodiment]

[0204] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0205] 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.

[0206] 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).

[0207] 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.

[0208] 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.

[0209] 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).

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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".

[0216] This invention provides a system that collects and analyzes user preference data and integrates multiple generative models to offer optimal information suggestions. The system mainly consists of a server, terminals, and users, which work together in coordination with each other.

[0217] The server receives preference data from users and stores it in a database. This data includes content that individual users have previously accessed and items they have shown interest in. The server integrates and analyzes this data to extract common characteristics across all users or groups.

[0218] Next, the server uses a generative model to create information suggestions based on the analysis results. The generative model combines different algorithms and AI technologies, which are dynamically merged to produce suggestions optimized for specific scenarios. For example, a user in a zoo can be provided with detailed descriptions of specific animals and related event information.

[0219] The server sends the generated information to the terminal. The terminal receives this information and dynamically adjusts the interface to present it to the user intuitively and effectively. This allows the user to quickly obtain the necessary information, improving convenience.

[0220] Furthermore, users can send feedback about the information provided from their devices. The server analyzes this feedback and uses it to improve the generative model. By continuously accumulating and analyzing feedback, the overall system performance improves, enabling more precise information suggestions.

[0221] Specific example:

[0222] For example, when this system is used in a zoo, users can search for information about their favorite animals on their devices. The server generates detailed information about the animal's ecology, characteristics, and where it is kept, and sends it to the device. Users can then view the presented information to plan their visit or learn about specific animals. In this way, users can explore the zoo efficiently and have a more fulfilling experience.

[0223] The following describes the processing flow.

[0224] Step 1:

[0225] Users operate a device and input data about their individual hobbies and preferences. This includes their favorite animals, activities of interest, and past visit history. The device collects this data and sends it to the server.

[0226] Step 2:

[0227] The server stores the received user data in a database. The database integrates preference data obtained from multiple users and updates each user's profile.

[0228] Step 3:

[0229] The server analyzes the data and runs algorithms to extract common interests and trends. This process utilizes machine learning techniques to identify group-specific features and patterns.

[0230] Step 4:

[0231] The server applies a generative model to generate information suggestions based on extracted features. The generative model utilizes pre-trained AI technology to construct information optimized for each user or user group.

[0232] Step 5:

[0233] The server sends the generated information to the terminal. Based on the received information, the terminal adjusts the user interface as needed to display the information in a visually easy-to-understand manner.

[0234] Step 6:

[0235] Users review the presented information and view details about specific animals, event information, and more. Any feedback or additional requests from the user are sent from the device to the server.

[0236] Step 7:

[0237] The server receives user feedback and reflects it in the database. This allows the system to use the feedback to improve the accuracy of generative models and information suggestions.

[0238] (Example 1)

[0239] 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."

[0240] In modern information systems, there is a challenge in accurately understanding the diverse preferences of users and efficiently providing personalized information suggestions based on those preferences. Furthermore, while it is necessary to further optimize systems by effectively incorporating user feedback, existing methods have limitations. Moreover, there is a need to leverage common preferences among multiple users to provide even greater value.

[0241] 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.

[0242] In this invention, the server includes means for integrating and storing preference data collected from users, means for analyzing collective preference patterns based on the preference data, and means for dynamically fusing multiple generation algorithms based on the analysis results to generate optimized information suggestions. This enables highly accurate information suggestions based on individual user preferences, and further enables multi-layered value provision through the analysis of collective preferences.

[0243] "Preference data" refers to a collection of information that shows a user's past behavior and interests.

[0244] A "generative algorithm" is a process that integrates multiple algorithms to generate optimal information based on data.

[0245] "Feedback" refers to the evaluations and opinions that users give regarding the information provided by the system.

[0246] A "common preference pattern" refers to characteristics that indicate shared interests and concerns among multiple users.

[0247] "Information suggestions" refer to customized information provided to users by a generation algorithm based on analysis results.

[0248] An "analytical algorithm to support group decision-making" is a computational process that analyzes the preferences and opinions of multiple users to help make optimal decisions.

[0249] A description of embodiments for carrying out this invention will be given.

[0250] The server serves as a means of receiving, integrating, and storing preference data sent by users in a database. This preference data includes content that users have previously accessed and interests they have shown. The server uses this data to run algorithms to analyze collective preference patterns. Machine learning techniques and AI methods are utilized in the analysis.

[0251] Next, based on the analysis results, the server dynamically merges multiple generation algorithms and executes the process to propose the most suitable information. This generation algorithm fusion involves combining different AI models to generate data that adapts to specific conditions.

[0252] The terminal receives information provided by the server and dynamically adjusts the interface presented to the user. This allows the user to obtain information intuitively and effectively. The information presented may take various forms, including text, images, and videos.

[0253] Furthermore, users can send feedback on the provided information from their devices. This feedback is collected on the server and used to further improve the performance of the generation algorithm. Through this process, the system is continuously improved, and the accuracy of suggestions to users becomes practically better.

[0254] For example, a user visiting a zoo might send a prompt message from their device such as, "Tell me the latest panda event information." In this case, the server generates and provides optimal information suggestions that reflect the user's interests. This allows the user to efficiently plan their visit.

[0255] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0256] Step 1:

[0257] The server receives user preference data sent from the terminal and stores it in a database. Input data includes the user's access history and items they are interested in. The server then processes this data to normalize it and store it in a consistent format. This process yields a dataset that reflects the user's preferences.

[0258] Step 2:

[0259] The server analyzes preference data stored in the database and extracts collective preference patterns. Previously stored preference data is used as input. The data is subjected to data calculations that apply machine learning algorithms to find common patterns, and the output is preference patterns and trends as analysis results. This result provides foundational data that enables information suggestions tailored to users and user groups.

[0260] Step 3:

[0261] The server generates information suggestions by fusing multiple generative AI models based on the analysis results of preference patterns. The input consists of the analysis results and available generative AI models. The server performs data calculations to integrate different AI models and generate optimal information, with the output being personalized information suggestions presented to the user. This process creates recommendations tailored to the user's preferences.

[0262] Step 4:

[0263] The server sends the generated information suggestions to the terminal. The input is the information suggestion data. The terminal receives this and dynamically constructs an interface to display the information appropriately for the user. The output is a display optimized for the user's screen. This makes the information easier for the user to understand intuitively.

[0264] Step 5:

[0265] Users submit feedback from their devices based on the information provided. Inputs include user satisfaction levels and requests for additional information. The server receives the feedback and performs an analysis. The output is feedback data used to improve the generated AI model. As a result, the system improves accuracy over time, enabling more effective information suggestions.

[0266] (Application Example 1)

[0267] 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."

[0268] There is a need to improve the accuracy of information provision based on users' interests and preferences, and to realize more personalized content suggestions. However, current systems struggle to efficiently provide information suitable for individual users, and the presentation of related product information is limited. The challenge is to solve this problem and provide a system that allows users to easily and intuitively search for and display information.

[0269] 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.

[0270] In this invention, the server includes means for integrating and managing interest information collected from users, means for fusing multiple generation algorithms based on the interest information to generate optimized information, and means for dynamically adjusting and displaying the generated information on the user's information processing device. This enables more personalized content suggestions for users by providing relevant data based on viewing history and displaying relevant product information.

[0271] "User" refers to an individual person who uses or consumes a particular system or content.

[0272] "Interest information" refers to data that indicates a user's interest in specific content or topics.

[0273] "Integrating and managing" refers to gathering data from different sources, organizing and storing it centrally, and making it usable efficiently.

[0274] A "generative algorithm" refers to a set of computational procedures or methods used to process data according to a specific purpose and generate new information.

[0275] "Dynamically adjusting and displaying information" means changing the way information is presented in real time according to the user's situation and requests.

[0276] An "information processing device" refers to a machine or device that has the function of collecting and analyzing data and displaying or saving the results.

[0277] "Related data" refers to information that is associated with the presented information and provides additional value.

[0278] "Product information" refers to data that describes details about a specific product, such as its specifications, features, price, and usage instructions.

[0279] "Personalized content recommendation" refers to providing information optimized for an individual user based on their interests and preferences.

[0280] This invention is based on a system centered around a server, a terminal, and a user in order to realize personalized information provision to users.

[0281] First, the server collects the interest information of users, integrates it, and manages it. The interest information is collected from the interests and accessed content that users have shown in the past and stored in a database. As a result, a dataset reflecting the preferences of individual users is formed.

[0282] Next, the server uses a generation AI model based on the interest information. Here, multiple generation algorithms are dynamically fused to generate optimized information provision. The generated information is adapted to make a content recommendation appropriate for the user in a specific usage scenario.

[0283] The generated information is then sent to the terminal, which is the user's information processing device. The terminal receives this information, dynamically adjusts it according to the user's situation and device characteristics, and then displays it. As a result, the user can receive the information in a visually optimized form.

[0284] [[ID=十九]] In addition, the server receives feedback from the user and improves the performance of the generation algorithm based on this feedback. Through this feedback loop, the recommendation accuracy of the entire system is gradually improved.

[0285] As a specific example, when a movie enthusiast wants information about a new movie, the server analyzes the viewing history related to movies and proposes related data including related works and trailers for new movies. Furthermore, related product information, such as purchase information for DVDs and soundtracks, can also be provided simultaneously.

[0286] As an example of a prompt sentence, it is possible to give instructions to the generative AI model in the form of "Generate the latest movie release information about action movies preferred by this user and list recommended products of related goods." In this system, the main hardware is Amazon Web Services (AWS), and as software, PyTorch or TensorFlow is used for building the AI model.

[0287] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0288] Step 1: The server collects the user's interest information.

[0289] The server obtains the user's past access history and evaluation data for content from the database and integrates this as interest information. The collected information indicates the user's interests and behavioral patterns.

[0290] Step 2: The server performs data analysis using the interest information.

[0291] Based on the input interest information, the server uses a collaborative filtering algorithm to analyze the data and identify highly relevant content. As an output, analysis results serving as a basis for optimal information recommendation to the user are obtained.

[0292] Step 3: The server generates an information recommendation using the generative AI model.

[0293] The server inputs the analysis results into the generative AI model, and the generative model creates an optimal information recommendation based on this. In this process, different algorithms are integrated, and according to the prompt sentence, a content list corresponding to the user's interests is output.

[0294] Step 4: The server transmits the generated information to the terminal.

[0295] The server sends the generated information suggestions as data packets to the user's terminal, which the terminal receives. This prepares the terminal to display information in response to the user's actions.

[0296] Step 5: The device dynamically displays information.

[0297] The device dynamically adjusts the layout, taking into account screen size and device specifications, to display received information in the most optimal format for the user. As a result, the user sees visually effective information on the screen.

[0298] Step 6: Evaluate the user's information and submit feedback.

[0299] Users provide ratings and comments on the displayed information and send this feedback from their device to the server. This accumulates data that helps improve the generated AI model.

[0300] 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.

[0301] This invention constructs a system that combines user preference data and emotional data to provide optimized information. The system consists of a server, terminals, an emotional engine, and the user. This makes it possible to provide a more personalized experience.

[0302] First, users register their hobbies and interests via a device. The device is equipped with a camera and microphone, and these devices are used to collect real-time emotional data from the user's facial expressions and tone of voice. The emotion engine analyzes this data to identify the user's emotional state.

[0303] The emotional data analyzed by the emotion engine and the user's preference data are transmitted from the terminal to the server. When the server receives these data, it stores them in a database and manages them centrally.

[0304] Next, the server fuses and analyzes the received preference data and emotional data. A generation model that takes into account the emotional trend is used for this. This model has a function of selecting and generating appropriate information according to a specific emotional state. Specifically, adjustments are made such that if the user is in a relaxed emotion, gentle content is provided, and if the user is tense, information that reduces stress is provided.

[0305] The generated information is transmitted from the server to the terminal, and the terminal presents this information to the user in an easy-to-understand manner. The interface is dynamically adjusted, and a presentation suitable for the user's current emotional state is made. As a result, the user can receive a service that fits their emotions, and the satisfaction is improved.

[0306] Specific example:

[0307] For example, when a user who visits a museum uses this system, the terminal detects the emotion from the user's expression and voice, and when the user is relaxed, proposes exhibition information including leisurely music that matches the emotion at that time. If the user is excited, the visit can be made more fulfilling by providing more interactive and participatory activity information. By proposing information that combines the emotion engine in this way, the user can obtain an optimal experience at that moment.

[0308] The following describes the processing flow.

[0309] Step 1:

[0310] The device collects data on the user's hobbies and interests, and uses its camera and microphone to recognize the user's facial expressions and voice tone in real time as emotions. This data is then converted into emotional states through an emotion engine.

[0311] Step 2:

[0312] The device sends the collected preference and emotional data to the server. During this process, the data is appropriately formatted and encrypted to protect privacy.

[0313] Step 3:

[0314] The server stores received preference and emotion data in a database and updates individual user profiles. The database also includes records of each user's different emotional states, enabling dynamic data management.

[0315] Step 4:

[0316] The server analyzes the received data and generates optimized information suggestions at that point using a generative model that takes emotional data into account. For example, if the user is feeling stressed, the generative model might generate suggestions related to relaxation.

[0317] Step 5:

[0318] The server sends the generated suggestions to the terminal. Based on the received information, the terminal adjusts and displays the interface in a way that suits the user's emotions.

[0319] Step 6:

[0320] Users receive the presented information and can send feedback from their device to the server as needed. This feedback reflects the user's satisfaction level and newly identified preferences.

[0321] Step 7:

[0322] The server analyzes the feedback it receives and uses it to improve the generative model. The feedback data continuously improves the accuracy of user sentiment-based suggestions, thereby enhancing the overall system performance.

[0323] (Example 2)

[0324] 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".

[0325] In modern information processing systems, providing information suggestions that consider not only user preferences but also their real-time emotional state is crucial for delivering a highly satisfying experience. However, conventional systems have limitations in analyzing emotional data and providing appropriate information based on it, failing to achieve complete personalization that fully responds to user emotions. Furthermore, the technology for efficiently utilizing user feedback to improve information suggestions is insufficient.

[0326] 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.

[0327] In this invention, the server includes means for integrating and managing preference data and emotional data collected from users; means for fusing multiple generative models based on the preference data and emotional data to generate optimized information suggestions according to the user's emotional state; and means for dynamically adjusting and displaying the generated information on the user's terminal, and presenting it in a way that is appropriate to the user's current emotional state. This enables advanced personalization tailored to the user's emotions and continuous improvement of the system's performance through feedback.

[0328] "Preference data" refers to data that shows information about the areas and activities that users are interested in.

[0329] "Emotional data" refers to information that indicates the user's emotional state, and is acquired through facial recognition and voice analysis.

[0330] A "generative model" is an algorithm used to generate new content or information based on input data.

[0331] "Feedback" refers to information that users provide, expressing their evaluations and reactions to the information and services offered, and is used to improve the system.

[0332] Personalization is the process of optimizing services and content according to the individual preferences and needs of each user.

[0333] A "server" is a computer system that processes information, stores and manages data, and transmits information to terminals as needed.

[0334] A "terminal" is a device that allows users to access a system and receive information through its interface.

[0335] This invention constructs a system that combines user preference data and real-time sentiment data to provide personalized information. This system consists of a server, a terminal, a sentiment analysis engine, and the user, and each element works in cooperation with the others.

[0336] Users first register their hobbies and interests via a device. The device is equipped with a camera and microphone, and these devices are used to capture the user's facial expressions and voice tone, collecting real-time emotional data.

[0337] In this system, the terminal sends collected data to the sentiment analysis engine, which analyzes this data to identify the user's emotional state. The analysis results and preference data are then sent from the terminal to the server.

[0338] The server stores the received preference and emotion data in a database and then uses it for analysis. It uses a generative AI model to select and generate the most appropriate information based on a specific emotional state. For example, when the user is relaxed, it provides calming music information, and when they are stressed, it suggests information to reduce stress.

[0339] The generated information is sent from the server to the terminal and presented to the user in a dynamically adjusted form on the terminal. The user interface is optimized to adapt to the user's emotions, allowing the user to receive information that resonates with their feelings. As a result, a highly satisfying experience is provided.

[0340] As a concrete example, when a user visits a museum, the device detects a relaxed state from their facial expressions and voice and suggests calm exhibit information appropriate for the situation. On the other hand, if an excited state is detected, it presents more interactive activity information. This system allows users to enjoy the best possible experience according to their emotions at that moment.

[0341] An example of a prompt message used in a generative AI model would be an instruction such as, "Suggest optimal content for a relaxed user, and engage both their visual and auditory senses."

[0342] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0343] Step 1: The user registers their hobbies and interests through the device. The input is the user's own information about their hobbies and interests, and the output is saved on the device as preference data. Specifically, registration is performed by selecting items on the device's interface or filling in data in input forms.

[0344] Step 2: The device uses its built-in camera and microphone to collect real-time emotional data from the user. The input is the user's facial expressions and voice tone, and the output is emotional data obtained by analyzing these. Specifically, this involves capturing facial expressions with the camera and processing voice input.

[0345] Step 3: The device sends the collected emotional data to the emotion analysis engine. The input is the emotional data obtained in Step 2, and the output is the detailed emotional state analyzed by the emotion analysis engine. Specifically, the emotion analysis algorithm runs and the data is analyzed.

[0346] Step 4: The terminal sends the analyzed sentiment and preference data to the server. The input is the analyzed sentiment and preference data, and the output is the server that receives this data. Operationally, the data is encoded and securely transmitted over the network.

[0347] Step 5: The server stores the received preference and emotion data in a database and then integrates and analyzes this data. The input is the received preference and emotion data, and the output is the analysis results based on this data. Specifically, the process involves writing to the database and analyzing the data using a generative AI model.

[0348] Step 6: The server uses a generative AI model to select and generate information that matches the user's emotional state. The input is the analysis results obtained in Step 5, and the output is the optimized information provided to the user. The operation includes an information generation process by the AI ​​model based on prompt statements.

[0349] Step 7: The server sends the generated information to the terminal. The input is the generated information data, and the output is the terminal that received the information. Specifically, the information is sent based on the data transmission protocol from the server.

[0350] Step 8: The terminal dynamically adjusts the received information on the user interface and presents it to the user. The input is the information received from the server, and the output is the content displayed on the screen shown to the user. In operation, the interface dynamically changes according to the user's current emotional state, presenting the information in the most optimal way.

[0351] (Application Example 2)

[0352] 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."

[0353] This invention aims to address the challenge of personalizing digital content delivery in accordance with the user's emotional state. Existing content distribution systems generally provide information based solely on user preference data, and do not adequately provide flexible content recommendations that take into account the user's instantaneous emotional state. As a result, users often receive content that does not match their emotions or mood, leading to decreased satisfaction.

[0354] 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.

[0355] In this invention, the server includes means for integrating and managing preference data and emotional data collected from users; means for fusing multiple generative models based on the preference data and emotional data to generate information suggestions adapted to the user's emotional state; and means for dynamically adjusting the generated information on the user's terminal and presenting it in visual and auditory representations corresponding to the user's emotional state. This makes it possible to provide content that is appropriate to the user's emotions in a timely manner, thereby improving the user experience.

[0356] "Preference data" refers to information about the genres and content that users prefer, and is used for selecting and recommending content.

[0357] "Emotional data" refers to data that represents a user's current emotions and mood, and is information obtained from facial expressions, tone of voice, and other biosignals.

[0358] A "generative model" is an algorithm or program that generates or selects content that matches the user's needs and circumstances based on collected data.

[0359] "Information recommendations" are recommendations regarding content and services provided to users, and are determined based on preference data and sentiment data.

[0360] "Visual and auditory representations" refer to the format in which information is presented to the user, including on-screen visual and audio feedback.

[0361] Based on this invention, the system that implements the application example consists of a server, a terminal, an emotion engine, and a user. Specifically, it is implemented as follows:

[0362] First, the device is a smartphone equipped with a camera and microphone. This hardware captures the user's facial expressions and voice tone in real time and collects the data. The device sends this data to the emotion engine. The emotion engine uses the Google Cloud Vision API and IBM Watson Tone Analyzer to analyze the facial expressions and voice tone and identify the user's emotional state.

[0363] The analyzed sentiment data and preference data previously registered by the user via the device are sent to the server. The server stores and integrates this collected data in a database. Next, the server utilizes generative AI models, including OpenAI's GPT-3, to select appropriate content based on a specific sentiment state. In this selection process, the generative AI model uses prompt statements to generate content that matches the sentiment.

[0364] The generated information is sent from the server to the terminal, which then displays the content in a format that matches the user's emotional state. This display utilizes both visual and auditory representations, enabling a more personalized experience for the user.

[0365] As a concrete example, when a user is using the application in a relaxed state in the evening, classical music and sunset scenery videos selected based on their past preference data will be automatically presented. An example of a prompt message used in this case might be, "Please recommend music and videos that the user should watch when they are in a relaxed emotional state. They have a history of enjoying classical music."

[0366] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0367] Step 1:

[0368] The device uses a camera and microphone to capture the user's facial expressions and voice tone in real time. The input is the user's facial image and voice signal, and the output is the recording of them as digital data.

[0369] Step 2:

[0370] The terminal transmits the collected facial and audio data to the emotion engine. The input is the digital data obtained in step 1, which is then converted into a data format for analysis and used as the output.

[0371] Step 3:

[0372] The emotion engine uses the Google Cloud Vision API to analyze facial expressions and IBM Watson Tone Analyzer to analyze voice tone. The input is the analysis data format obtained in step 2, and the output is the analysis result indicating the user's emotional state. In this step, facial feature points and voice frequencies are analyzed to identify the emotional state.

[0373] Step 4:

[0374] The server integrates and manages emotional data received from terminals with preference data pre-registered by the user. Input consists of emotional data and preference data, which are combined, stored in a database, and output as basic data for information selection.

[0375] Step 5:

[0376] The server utilizes a generative AI model to generate information suggestions using prompt sentences based on preference and emotion data. The input is the data integrated in step 4, and the output is content information appropriate to the user's emotional state. In this process, the generative AI model plays the role of combining and generating the most suitable content.

[0377] Step 6:

[0378] The generated information is sent from the server to the terminal. The input is the content information obtained in step 5, and the output is converted into a data format for display in visual and auditory formats and sent to the terminal.

[0379] Step 7:

[0380] The device presents the received content using visual and auditory representations that match the user's emotional state. The input is the data received in step 6, and the output is the specific content display for the user. This display performs specific actions, such as playing classical music and soothing images if the user is relaxed.

[0381] 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.

[0382] 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.

[0383] 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.

[0384] [Third Embodiment]

[0385] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0386] 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.

[0387] 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).

[0388] 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.

[0389] 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.

[0390] 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).

[0391] 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.

[0392] 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.

[0393] 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.

[0394] 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.

[0395] 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.

[0396] 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".

[0397] This invention provides a system that collects and analyzes user preference data and integrates multiple generative models to offer optimal information suggestions. The system mainly consists of a server, terminals, and users, which work together in coordination with each other.

[0398] The server receives preference data from users and stores it in a database. This data includes content that individual users have previously accessed and items they have shown interest in. The server integrates and analyzes this data to extract common characteristics across all users or groups.

[0399] Next, the server uses a generative model to create information suggestions based on the analysis results. The generative model combines different algorithms and AI technologies, which are dynamically merged to produce suggestions optimized for specific scenarios. For example, a user in a zoo can be provided with detailed descriptions of specific animals and related event information.

[0400] The server sends the generated information to the terminal. The terminal receives this information and dynamically adjusts the interface to present it to the user intuitively and effectively. This allows the user to quickly obtain the necessary information, improving convenience.

[0401] Furthermore, users can send feedback about the information provided from their devices. The server analyzes this feedback and uses it to improve the generative model. By continuously accumulating and analyzing feedback, the overall system performance improves, enabling more precise information suggestions.

[0402] Specific example:

[0403] For example, when this system is used in a zoo, users can search for information about their favorite animals on their devices. The server generates detailed information about the animal's ecology, characteristics, and where it is kept, and sends it to the device. Users can then view the presented information to plan their visit or learn about specific animals. In this way, users can explore the zoo efficiently and have a more fulfilling experience.

[0404] The following describes the processing flow.

[0405] Step 1:

[0406] Users operate a device and input data about their individual hobbies and preferences. This includes their favorite animals, activities of interest, and past visit history. The device collects this data and sends it to the server.

[0407] Step 2:

[0408] The server stores the received user data in a database. The database integrates preference data obtained from multiple users and updates each user's profile.

[0409] Step 3:

[0410] The server analyzes the data and runs algorithms to extract common interests and trends. This process utilizes machine learning techniques to identify group-specific features and patterns.

[0411] Step 4:

[0412] The server applies a generative model to generate information suggestions based on extracted features. The generative model utilizes pre-trained AI technology to construct information optimized for each user or user group.

[0413] Step 5:

[0414] The server sends the generated information to the terminal. Based on the received information, the terminal adjusts the user interface as needed to display the information in a visually easy-to-understand manner.

[0415] Step 6:

[0416] Users review the presented information and view details about specific animals, event information, and more. Any feedback or additional requests from the user are sent from the device to the server.

[0417] Step 7:

[0418] The server receives user feedback and reflects it in the database. This allows the system to use the feedback to improve the accuracy of generative models and information suggestions.

[0419] (Example 1)

[0420] 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."

[0421] In modern information systems, there is a challenge in accurately understanding the diverse preferences of users and efficiently providing personalized information suggestions based on those preferences. Furthermore, while it is necessary to further optimize systems by effectively incorporating user feedback, existing methods have limitations. Moreover, there is a need to leverage common preferences among multiple users to provide even greater value.

[0422] 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.

[0423] In this invention, the server includes means for integrating and storing preference data collected from users, means for analyzing collective preference patterns based on the preference data, and means for dynamically fusing multiple generation algorithms based on the analysis results to generate optimized information suggestions. This enables highly accurate information suggestions based on individual user preferences, and further enables multi-layered value provision through the analysis of collective preferences.

[0424] "Preference data" refers to a collection of information that shows a user's past behavior and interests.

[0425] A "generative algorithm" is a process that integrates multiple algorithms to generate optimal information based on data.

[0426] "Feedback" refers to the evaluations and opinions that users give regarding the information provided by the system.

[0427] A "common preference pattern" refers to characteristics that indicate shared interests and concerns among multiple users.

[0428] "Information suggestions" refer to customized information provided to users by a generation algorithm based on analysis results.

[0429] An "analytical algorithm to support group decision-making" is a computational process that analyzes the preferences and opinions of multiple users to help make optimal decisions.

[0430] A description of embodiments for carrying out this invention will be given.

[0431] The server serves as a means of receiving, integrating, and storing preference data sent by users in a database. This preference data includes content that users have previously accessed and interests they have shown. The server uses this data to run algorithms to analyze collective preference patterns. Machine learning techniques and AI methods are utilized in the analysis.

[0432] Next, based on the analysis results, the server dynamically merges multiple generation algorithms and executes the process to propose the most suitable information. This generation algorithm fusion involves combining different AI models to generate data that adapts to specific conditions.

[0433] The terminal receives information provided by the server and dynamically adjusts the interface presented to the user. This allows the user to obtain information intuitively and effectively. The information presented may take various forms, including text, images, and videos.

[0434] Furthermore, users can send feedback on the provided information from their devices. This feedback is collected on the server and used to further improve the performance of the generation algorithm. Through this process, the system is continuously improved, and the accuracy of suggestions to users becomes practically better.

[0435] For example, a user visiting a zoo might send a prompt message from their device such as, "Tell me the latest panda event information." In this case, the server generates and provides optimal information suggestions that reflect the user's interests. This allows the user to efficiently plan their visit.

[0436] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0437] Step 1:

[0438] The server receives user preference data sent from the terminal and stores it in a database. Input data includes the user's access history and items they are interested in. The server then processes this data to normalize it and store it in a consistent format. This process yields a dataset that reflects the user's preferences.

[0439] Step 2:

[0440] The server analyzes preference data stored in the database and extracts collective preference patterns. Previously stored preference data is used as input. The data is subjected to data calculations that apply machine learning algorithms to find common patterns, and the output is preference patterns and trends as analysis results. This result provides foundational data that enables information suggestions tailored to users and user groups.

[0441] Step 3:

[0442] The server generates information suggestions by fusing multiple generative AI models based on the analysis results of preference patterns. The input consists of the analysis results and available generative AI models. The server performs data calculations to integrate different AI models and generate optimal information, with the output being personalized information suggestions presented to the user. This process creates recommendations tailored to the user's preferences.

[0443] Step 4:

[0444] The server sends the generated information suggestions to the terminal. The input is the information suggestion data. The terminal receives this and dynamically constructs an interface to display the information appropriately for the user. The output is a display optimized for the user's screen. This makes the information easier for the user to understand intuitively.

[0445] Step 5:

[0446] Users submit feedback from their devices based on the information provided. Inputs include user satisfaction levels and requests for additional information. The server receives the feedback and performs an analysis. The output is feedback data used to improve the generated AI model. As a result, the system improves accuracy over time, enabling more effective information suggestions.

[0447] (Application Example 1)

[0448] 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."

[0449] There is a need to improve the accuracy of information provision based on users' interests and preferences, and to realize more personalized content suggestions. However, current systems struggle to efficiently provide information suitable for individual users, and the presentation of related product information is limited. The challenge is to solve this problem and provide a system that allows users to easily and intuitively search for and display information.

[0450] 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.

[0451] In this invention, the server includes means for integrating and managing interest information collected from users, means for fusing multiple generation algorithms based on the interest information to generate optimized information, and means for dynamically adjusting and displaying the generated information on the user's information processing device. This enables more personalized content suggestions for users by providing relevant data based on viewing history and displaying relevant product information.

[0452] "User" refers to an individual person who uses or consumes a particular system or content.

[0453] "Interest information" refers to data that indicates a user's interest in specific content or topics.

[0454] "Integrating and managing" refers to gathering data from different sources, organizing and storing it centrally, and making it usable efficiently.

[0455] A "generative algorithm" refers to a set of computational procedures or methods used to process data according to a specific purpose and generate new information.

[0456] "Dynamically adjusting and displaying information" means changing the way information is presented in real time according to the user's situation and requests.

[0457] An "information processing device" refers to a machine or device that has the function of collecting and analyzing data and displaying or saving the results.

[0458] "Related data" refers to information that is associated with the presented information and provides additional value.

[0459] "Product information" refers to data that describes details about a specific product, such as its specifications, features, price, and usage instructions.

[0460] "Personalized content suggestions" refers to providing information optimized for each individual user based on their interests and preferences.

[0461] This invention is based on a system centered around a server, a terminal, and a user, in order to provide personalized information to users.

[0462] First, the server collects and integrates user interest information. This interest information is gathered from the user's past interests and accessed content, and stored in a database. This creates a dataset that reflects the individual preferences of each user.

[0463] Next, the server uses a generative AI model based on the interest information. Here, multiple generative algorithms are dynamically merged to generate optimized information. The generated information is adapted to provide appropriate content suggestions for the user in a specific usage scenario.

[0464] The generated information is then transmitted to the user's information processing device, the terminal. The terminal receives this information, dynamically adjusts it according to the user's situation and device characteristics, and then displays it. This allows the user to receive information in a visually optimized format.

[0465] In addition, the server receives feedback from users and uses that feedback to improve the performance of the generation algorithm. This feedback loop gradually improves the overall recommendation accuracy of the system.

[0466] For example, if a movie enthusiast wants information on new releases, the server analyzes their movie viewing history and suggests relevant data, including related titles and trailers for new releases. Furthermore, it can also provide related product information, such as purchase information for DVDs and soundtracks.

[0467] An example of a prompt message is, "Generate the latest movie release information for action movies that this user likes, and also list recommended related merchandise." This is how instructions can be given to the generative AI model. The main hardware in this system is Amazon Web Services (AWS), and the software used to build the AI ​​model is PyTorch and TensorFlow.

[0468] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0469] Step 1: The server collects user interest information.

[0470] The server retrieves users' past access history and content evaluation data from a database and integrates this as interest information. The collected information indicates users' interests and behavioral patterns.

[0471] Step 2: The server performs data analysis using interest information.

[0472] Based on the input interest information, the server uses a collaborative filtering algorithm to analyze the data and identify highly relevant content. The output is the analysis results, which form the basis for providing users with the most relevant information.

[0473] Step 3: The server generates information suggestions using the generated AI model.

[0474] The server inputs the analysis results into a generative AI model, which then creates optimal information suggestions based on this input. In this process, different algorithms are combined, and a content list tailored to the user's interests is output according to the prompts.

[0475] Step 4: The server sends the generated information to the terminal.

[0476] The server sends the generated information suggestions as data packets to the user's terminal, which the terminal receives. This prepares the terminal to display information in response to the user's actions.

[0477] Step 5: The device dynamically displays information.

[0478] The device dynamically adjusts the layout, taking into account screen size and device specifications, to display received information in the most optimal format for the user. As a result, the user sees visually effective information on the screen.

[0479] Step 6: Evaluate the user's information and submit feedback.

[0480] Users provide ratings and comments on the displayed information and send this feedback from their device to the server. This accumulates data that helps improve the generated AI model.

[0481] 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.

[0482] This invention constructs a system that combines user preference data and emotional data to provide optimized information. The system consists of a server, terminals, an emotional engine, and the user. This makes it possible to provide a more personalized experience.

[0483] First, users register their hobbies and interests via a device. The device is equipped with a camera and microphone, and these devices are used to collect real-time emotional data from the user's facial expressions and tone of voice. The emotion engine analyzes this data to identify the user's emotional state.

[0484] The emotional data analyzed by the emotion engine, along with user preference data, is sent from the device to the server. Upon receiving this data, the server stores it in a database for centralized management.

[0485] The server then fuses and analyzes the received preference and emotion data. This utilizes a generative model that takes emotional tendencies into account. This model has the ability to select and generate appropriate information according to a specific emotional state. Specifically, it adjusts the content soothing if the user is relaxed, and provides stress-reducing information if they are tense.

[0486] The generated information is sent from the server to the terminal, which then presents this information to the user in an easy-to-understand manner. The interface is dynamically adjusted to provide a presentation that matches the user's current emotional state. This allows users to receive a service that fits their emotions, leading to increased satisfaction.

[0487] Specific example:

[0488] For example, when a user visiting a museum uses this system, the terminal detects their emotions from their facial expressions and voice. If they are relaxed, it suggests exhibition information, including soothing music that matches their current mood. If the user is excited, it can enhance their visit by providing more interactive and participatory activity information. By combining this emotion-driven information suggestion, users can have the most optimal experience at that moment.

[0489] The following describes the processing flow.

[0490] Step 1:

[0491] The device collects data on the user's hobbies and interests, and uses its camera and microphone to recognize the user's facial expressions and voice tone in real time as emotions. This data is then converted into emotional states through an emotion engine.

[0492] Step 2:

[0493] The device sends the collected preference and emotional data to the server. During this process, the data is appropriately formatted and encrypted to protect privacy.

[0494] Step 3:

[0495] The server stores received preference and emotion data in a database and updates individual user profiles. The database also includes records of each user's different emotional states, enabling dynamic data management.

[0496] Step 4:

[0497] The server analyzes the received data and generates optimized information suggestions at that point using a generative model that takes emotional data into account. For example, if the user is feeling stressed, the generative model might generate suggestions related to relaxation.

[0498] Step 5:

[0499] The server sends the generated suggestions to the terminal. Based on the received information, the terminal adjusts and displays the interface in a way that suits the user's emotions.

[0500] Step 6:

[0501] Users receive the presented information and can send feedback from their device to the server as needed. This feedback reflects the user's satisfaction level and newly identified preferences.

[0502] Step 7:

[0503] The server analyzes the feedback it receives and uses it to improve the generative model. The feedback data continuously improves the accuracy of user sentiment-based suggestions, thereby enhancing the overall system performance.

[0504] (Example 2)

[0505] 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."

[0506] In modern information processing systems, providing information suggestions that consider not only user preferences but also their real-time emotional state is crucial for delivering a highly satisfying experience. However, conventional systems have limitations in analyzing emotional data and providing appropriate information based on it, failing to achieve complete personalization that fully responds to user emotions. Furthermore, the technology for efficiently utilizing user feedback to improve information suggestions is insufficient.

[0507] 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.

[0508] In this invention, the server includes means for integrating and managing preference data and emotional data collected from users; means for fusing multiple generative models based on the preference data and emotional data to generate optimized information suggestions according to the user's emotional state; and means for dynamically adjusting and displaying the generated information on the user's terminal, and presenting it in a way that is appropriate to the user's current emotional state. This enables advanced personalization tailored to the user's emotions and continuous improvement of the system's performance through feedback.

[0509] "Preference data" refers to data that shows information about the areas and activities that users are interested in.

[0510] "Emotional data" refers to information that indicates the user's emotional state, and is acquired through facial recognition and voice analysis.

[0511] A "generative model" is an algorithm used to generate new content or information based on input data.

[0512] "Feedback" refers to information that users provide, expressing their evaluations and reactions to the information and services offered, and is used to improve the system.

[0513] Personalization is the process of optimizing services and content according to the individual preferences and needs of each user.

[0514] A "server" is a computer system that processes information, stores and manages data, and transmits information to terminals as needed.

[0515] A "terminal" is a device that allows users to access a system and receive information through its interface.

[0516] This invention constructs a system that combines user preference data and real-time sentiment data to provide personalized information. This system consists of a server, a terminal, a sentiment analysis engine, and the user, and each element works in cooperation with the others.

[0517] Users first register their hobbies and interests via a device. The device is equipped with a camera and microphone, and these devices are used to capture the user's facial expressions and voice tone, collecting real-time emotional data.

[0518] In this system, the terminal sends collected data to the sentiment analysis engine, which analyzes this data to identify the user's emotional state. The analysis results and preference data are then sent from the terminal to the server.

[0519] The server stores the received preference and emotion data in a database and then uses it for analysis. It uses a generative AI model to select and generate the most appropriate information based on a specific emotional state. For example, when the user is relaxed, it provides calming music information, and when they are stressed, it suggests information to reduce stress.

[0520] The generated information is sent from the server to the terminal and presented to the user in a dynamically adjusted form on the terminal. The user interface is optimized to adapt to the user's emotions, allowing the user to receive information that resonates with their feelings. As a result, a highly satisfying experience is provided.

[0521] As a concrete example, when a user visits a museum, the device detects a relaxed state from their facial expressions and voice and suggests calm exhibit information appropriate for the situation. On the other hand, if an excited state is detected, it presents more interactive activity information. This system allows users to enjoy the best possible experience according to their emotions at that moment.

[0522] An example of a prompt message used in a generative AI model would be an instruction such as, "Suggest optimal content for a relaxed user, and engage both their visual and auditory senses."

[0523] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0524] Step 1: The user registers their hobbies and interests through the device. The input is the user's own information about their hobbies and interests, and the output is saved on the device as preference data. Specifically, registration is performed by selecting items on the device's interface or filling in data in input forms.

[0525] Step 2: The device uses its built-in camera and microphone to collect real-time emotional data from the user. The input is the user's facial expressions and voice tone, and the output is emotional data obtained by analyzing these. Specifically, this involves capturing facial expressions with the camera and processing voice input.

[0526] Step 3: The device sends the collected emotional data to the emotion analysis engine. The input is the emotional data obtained in Step 2, and the output is the detailed emotional state analyzed by the emotion analysis engine. Specifically, the emotion analysis algorithm runs and the data is analyzed.

[0527] Step 4: The terminal sends the analyzed sentiment and preference data to the server. The input is the analyzed sentiment and preference data, and the output is the server that receives this data. Operationally, the data is encoded and securely transmitted over the network.

[0528] Step 5: The server stores the received preference and emotion data in a database and then integrates and analyzes this data. The input is the received preference and emotion data, and the output is the analysis results based on this data. Specifically, the process involves writing to the database and analyzing the data using a generative AI model.

[0529] Step 6: The server uses a generative AI model to select and generate information that matches the user's emotional state. The input is the analysis results obtained in Step 5, and the output is the optimized information provided to the user. The operation includes an information generation process by the AI ​​model based on prompt statements.

[0530] Step 7: The server sends the generated information to the terminal. The input is the generated information data, and the output is the terminal that received the information. Specifically, the information is sent based on the data transmission protocol from the server.

[0531] Step 8: The terminal dynamically adjusts the received information on the user interface and presents it to the user. The input is the information received from the server, and the output is the content displayed on the screen shown to the user. In operation, the interface dynamically changes according to the user's current emotional state, presenting the information in the most optimal way.

[0532] (Application Example 2)

[0533] 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."

[0534] This invention aims to address the challenge of personalizing digital content delivery in accordance with the user's emotional state. Existing content distribution systems generally provide information based solely on user preference data, and do not adequately provide flexible content recommendations that take into account the user's instantaneous emotional state. As a result, users often receive content that does not match their emotions or mood, leading to decreased satisfaction.

[0535] 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.

[0536] In this invention, the server includes means for integrating and managing preference data and emotional data collected from users; means for fusing multiple generative models based on the preference data and emotional data to generate information suggestions adapted to the user's emotional state; and means for dynamically adjusting the generated information on the user's terminal and presenting it in visual and auditory representations corresponding to the user's emotional state. This makes it possible to provide content that is appropriate to the user's emotions in a timely manner, thereby improving the user experience.

[0537] "Preference data" refers to information about the genres and content that users prefer, and is used for selecting and recommending content.

[0538] "Emotional data" refers to data that represents a user's current emotions and mood, and is information obtained from facial expressions, tone of voice, and other biosignals.

[0539] A "generative model" is an algorithm or program that generates or selects content that matches the user's needs and circumstances based on collected data.

[0540] "Information recommendations" are recommendations regarding content and services provided to users, and are determined based on preference data and sentiment data.

[0541] "Visual and auditory representations" refer to the format in which information is presented to the user, including on-screen visual and audio feedback.

[0542] Based on this invention, the system that implements the application example consists of a server, a terminal, an emotion engine, and a user. Specifically, it is implemented as follows:

[0543] First, the device is a smartphone equipped with a camera and microphone. This hardware captures the user's facial expressions and voice tone in real time and collects the data. The device sends this data to the emotion engine. The emotion engine uses the Google Cloud Vision API and IBM Watson Tone Analyzer to analyze the facial expressions and voice tone and identify the user's emotional state.

[0544] The analyzed sentiment data and preference data previously registered by the user via the device are sent to the server. The server stores and integrates this collected data in a database. Next, the server utilizes generative AI models, including OpenAI's GPT-3, to select appropriate content based on a specific sentiment state. In this selection process, the generative AI model uses prompt statements to generate content that matches the sentiment.

[0545] The generated information is sent from the server to the terminal, which then displays the content in a format that matches the user's emotional state. This display utilizes both visual and auditory representations, enabling a more personalized experience for the user.

[0546] As a concrete example, when a user is using the application in a relaxed state in the evening, classical music and sunset scenery videos selected based on their past preference data will be automatically presented. An example of a prompt message used in this case might be, "Please recommend music and videos that the user should watch when they are in a relaxed emotional state. They have a history of enjoying classical music."

[0547] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0548] Step 1:

[0549] The device uses a camera and microphone to capture the user's facial expressions and voice tone in real time. The input is the user's facial image and voice signal, and the output is the recording of them as digital data.

[0550] Step 2:

[0551] The terminal transmits the collected facial and audio data to the emotion engine. The input is the digital data obtained in step 1, which is then converted into a data format for analysis and used as the output.

[0552] Step 3:

[0553] The emotion engine uses the Google Cloud Vision API to analyze facial expressions and IBM Watson Tone Analyzer to analyze voice tone. The input is the analysis data format obtained in step 2, and the output is the analysis result indicating the user's emotional state. In this step, facial feature points and voice frequencies are analyzed to identify the emotional state.

[0554] Step 4:

[0555] The server integrates and manages emotional data received from terminals with preference data pre-registered by the user. Input consists of emotional data and preference data, which are combined, stored in a database, and output as basic data for information selection.

[0556] Step 5:

[0557] The server utilizes a generative AI model to generate information suggestions using prompt sentences based on preference and emotion data. The input is the data integrated in step 4, and the output is content information appropriate to the user's emotional state. In this process, the generative AI model plays the role of combining and generating the most suitable content.

[0558] Step 6:

[0559] The generated information is sent from the server to the terminal. The input is the content information obtained in step 5, and the output is converted into a data format for display in visual and auditory formats and sent to the terminal.

[0560] Step 7:

[0561] The device presents the received content using visual and auditory representations that match the user's emotional state. The input is the data received in step 6, and the output is the specific content display for the user. This display performs specific actions, such as playing classical music and soothing images if the user is relaxed.

[0562] 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.

[0563] 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.

[0564] 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.

[0565] [Fourth Embodiment]

[0566] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0567] 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.

[0568] 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).

[0569] 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.

[0570] 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.

[0571] 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).

[0572] 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.

[0573] 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.

[0574] 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.

[0575] 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.

[0576] 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.

[0577] 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.

[0578] 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".

[0579] This invention provides a system that collects and analyzes user preference data and integrates multiple generative models to offer optimal information suggestions. The system mainly consists of a server, terminals, and users, which work together in coordination with each other.

[0580] The server receives preference data from users and stores it in a database. This data includes content that individual users have previously accessed and items they have shown interest in. The server integrates and analyzes this data to extract common characteristics across all users or groups.

[0581] Next, the server uses a generative model to create information suggestions based on the analysis results. The generative model combines different algorithms and AI technologies, which are dynamically merged to produce suggestions optimized for specific scenarios. For example, a user in a zoo can be provided with detailed descriptions of specific animals and related event information.

[0582] The server sends the generated information to the terminal. The terminal receives this information and dynamically adjusts the interface to present it to the user intuitively and effectively. This allows the user to quickly obtain the necessary information, improving convenience.

[0583] Furthermore, users can send feedback about the information provided from their devices. The server analyzes this feedback and uses it to improve the generative model. By continuously accumulating and analyzing feedback, the overall system performance improves, enabling more precise information suggestions.

[0584] Specific example:

[0585] For example, when this system is used in a zoo, users can search for information about their favorite animals on their devices. The server generates detailed information about the animal's ecology, characteristics, and where it is kept, and sends it to the device. Users can then view the presented information to plan their visit or learn about specific animals. In this way, users can explore the zoo efficiently and have a more fulfilling experience.

[0586] The following describes the processing flow.

[0587] Step 1:

[0588] Users operate a device and input data about their individual hobbies and preferences. This includes their favorite animals, activities of interest, and past visit history. The device collects this data and sends it to the server.

[0589] Step 2:

[0590] The server stores the received user data in a database. The database integrates preference data obtained from multiple users and updates each user's profile.

[0591] Step 3:

[0592] The server analyzes the data and runs algorithms to extract common interests and trends. This process utilizes machine learning techniques to identify group-specific features and patterns.

[0593] Step 4:

[0594] The server applies a generative model to generate information suggestions based on extracted features. The generative model utilizes pre-trained AI technology to construct information optimized for each user or user group.

[0595] Step 5:

[0596] The server sends the generated information to the terminal. Based on the received information, the terminal adjusts the user interface as needed to display the information in a visually easy-to-understand manner.

[0597] Step 6:

[0598] Users review the presented information and view details about specific animals, event information, and more. Any feedback or additional requests from the user are sent from the device to the server.

[0599] Step 7:

[0600] The server receives user feedback and reflects it in the database. This allows the system to use the feedback to improve the accuracy of generative models and information suggestions.

[0601] (Example 1)

[0602] 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".

[0603] In modern information systems, there is a challenge in accurately understanding the diverse preferences of users and efficiently providing personalized information suggestions based on those preferences. Furthermore, while it is necessary to further optimize systems by effectively incorporating user feedback, existing methods have limitations. Moreover, there is a need to leverage common preferences among multiple users to provide even greater value.

[0604] 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.

[0605] In this invention, the server includes means for integrating and storing preference data collected from users, means for analyzing collective preference patterns based on the preference data, and means for dynamically fusing multiple generation algorithms based on the analysis results to generate optimized information suggestions. This enables highly accurate information suggestions based on individual user preferences, and further enables multi-layered value provision through the analysis of collective preferences.

[0606] "Preference data" refers to a collection of information that shows a user's past behavior and interests.

[0607] A "generative algorithm" is a process that integrates multiple algorithms to generate optimal information based on data.

[0608] "Feedback" refers to the evaluations and opinions that users give regarding the information provided by the system.

[0609] A "common preference pattern" refers to characteristics that indicate shared interests and concerns among multiple users.

[0610] "Information suggestions" refer to customized information provided to users by a generation algorithm based on analysis results.

[0611] An "analytical algorithm to support group decision-making" is a computational process that analyzes the preferences and opinions of multiple users to help make optimal decisions.

[0612] A description of embodiments for carrying out this invention will be given.

[0613] The server serves as a means of receiving, integrating, and storing preference data sent by users in a database. This preference data includes content that users have previously accessed and interests they have shown. The server uses this data to run algorithms to analyze collective preference patterns. Machine learning techniques and AI methods are utilized in the analysis.

[0614] Next, based on the analysis results, the server dynamically merges multiple generation algorithms and executes the process to propose the most suitable information. This generation algorithm fusion involves combining different AI models to generate data that adapts to specific conditions.

[0615] The terminal receives information provided by the server and dynamically adjusts the interface presented to the user. This allows the user to obtain information intuitively and effectively. The information presented may take various forms, including text, images, and videos.

[0616] Furthermore, users can send feedback on the provided information from their devices. This feedback is collected on the server and used to further improve the performance of the generation algorithm. Through this process, the system is continuously improved, and the accuracy of suggestions to users becomes practically better.

[0617] For example, a user visiting a zoo might send a prompt message from their device such as, "Tell me the latest panda event information." In this case, the server generates and provides optimal information suggestions that reflect the user's interests. This allows the user to efficiently plan their visit.

[0618] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0619] Step 1:

[0620] The server receives user preference data sent from the terminal and stores it in a database. Input data includes the user's access history and items they are interested in. The server then processes this data to normalize it and store it in a consistent format. This process yields a dataset that reflects the user's preferences.

[0621] Step 2:

[0622] The server analyzes preference data stored in the database and extracts collective preference patterns. Previously stored preference data is used as input. The data is subjected to data calculations that apply machine learning algorithms to find common patterns, and the output is preference patterns and trends as analysis results. This result provides foundational data that enables information suggestions tailored to users and user groups.

[0623] Step 3:

[0624] The server generates information suggestions by fusing multiple generative AI models based on the analysis results of preference patterns. The input consists of the analysis results and available generative AI models. The server performs data calculations to integrate different AI models and generate optimal information, with the output being personalized information suggestions presented to the user. This process creates recommendations tailored to the user's preferences.

[0625] Step 4:

[0626] The server sends the generated information suggestions to the terminal. The input is the information suggestion data. The terminal receives this and dynamically constructs an interface to display the information appropriately for the user. The output is a display optimized for the user's screen. This makes the information easier for the user to understand intuitively.

[0627] Step 5:

[0628] Users submit feedback from their devices based on the information provided. Inputs include user satisfaction levels and requests for additional information. The server receives the feedback and performs an analysis. The output is feedback data used to improve the generated AI model. As a result, the system improves accuracy over time, enabling more effective information suggestions.

[0629] (Application Example 1)

[0630] 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".

[0631] There is a need to improve the accuracy of information provision based on users' interests and preferences, and to realize more personalized content suggestions. However, current systems struggle to efficiently provide information suitable for individual users, and the presentation of related product information is limited. The challenge is to solve this problem and provide a system that allows users to easily and intuitively search for and display information.

[0632] 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.

[0633] In this invention, the server includes means for integrating and managing interest information collected from users, means for fusing multiple generation algorithms based on the interest information to generate optimized information, and means for dynamically adjusting and displaying the generated information on the user's information processing device. This enables more personalized content suggestions for users by providing relevant data based on viewing history and displaying relevant product information.

[0634] "User" refers to an individual person who uses or consumes a particular system or content.

[0635] "Interest information" refers to data that indicates a user's interest in specific content or topics.

[0636] "Integrating and managing" refers to gathering data from different sources, organizing and storing it centrally, and making it usable efficiently.

[0637] A "generative algorithm" refers to a set of computational procedures or methods used to process data according to a specific purpose and generate new information.

[0638] "Dynamically adjusting and displaying information" means changing the way information is presented in real time according to the user's situation and requests.

[0639] An "information processing device" refers to a machine or device that has the function of collecting and analyzing data and displaying or saving the results.

[0640] "Related data" refers to information that is associated with the presented information and provides additional value.

[0641] "Product information" refers to data that describes details about a specific product, such as its specifications, features, price, and usage instructions.

[0642] "Personalized content suggestions" refers to providing information optimized for each individual user based on their interests and preferences.

[0643] This invention is based on a system centered around a server, a terminal, and a user, in order to provide personalized information to users.

[0644] First, the server collects and integrates user interest information. This interest information is gathered from the user's past interests and accessed content, and stored in a database. This creates a dataset that reflects the individual preferences of each user.

[0645] Next, the server uses a generative AI model based on the interest information. Here, multiple generative algorithms are dynamically merged to generate optimized information. The generated information is adapted to provide appropriate content suggestions for the user in a specific usage scenario.

[0646] The generated information is then transmitted to the user's information processing device, the terminal. The terminal receives this information, dynamically adjusts it according to the user's situation and device characteristics, and then displays it. This allows the user to receive information in a visually optimized format.

[0647] In addition, the server receives feedback from users and uses that feedback to improve the performance of the generation algorithm. This feedback loop gradually improves the overall recommendation accuracy of the system.

[0648] For example, if a movie enthusiast wants information on new releases, the server analyzes their movie viewing history and suggests relevant data, including related titles and trailers for new releases. Furthermore, it can also provide related product information, such as purchase information for DVDs and soundtracks.

[0649] An example of a prompt message is, "Generate the latest movie release information for action movies that this user likes, and also list recommended related merchandise." This is how instructions can be given to the generative AI model. The main hardware in this system is Amazon Web Services (AWS), and the software used to build the AI ​​model is PyTorch and TensorFlow.

[0650] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0651] Step 1: The server collects user interest information.

[0652] The server retrieves users' past access history and content evaluation data from a database and integrates this as interest information. The collected information indicates users' interests and behavioral patterns.

[0653] Step 2: The server performs data analysis using interest information.

[0654] Based on the input interest information, the server uses a collaborative filtering algorithm to analyze the data and identify highly relevant content. The output is the analysis results, which form the basis for providing users with the most relevant information.

[0655] Step 3: The server generates information suggestions using the generated AI model.

[0656] The server inputs the analysis results into a generative AI model, which then creates optimal information suggestions based on this input. In this process, different algorithms are combined, and a content list tailored to the user's interests is output according to the prompts.

[0657] Step 4: The server sends the generated information to the terminal.

[0658] The server sends the generated information suggestions as data packets to the user's terminal, which the terminal receives. This prepares the terminal to display information in response to the user's actions.

[0659] Step 5: The device dynamically displays information.

[0660] The device dynamically adjusts the layout, taking into account screen size and device specifications, to display received information in the most optimal format for the user. As a result, the user sees visually effective information on the screen.

[0661] Step 6: Evaluate the user's information and submit feedback.

[0662] Users provide ratings and comments on the displayed information and send this feedback from their device to the server. This accumulates data that helps improve the generated AI model.

[0663] 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.

[0664] This invention constructs a system that combines user preference data and emotional data to provide optimized information. The system consists of a server, terminals, an emotional engine, and the user. This makes it possible to provide a more personalized experience.

[0665] First, users register their hobbies and interests via a device. The device is equipped with a camera and microphone, and these devices are used to collect real-time emotional data from the user's facial expressions and tone of voice. The emotion engine analyzes this data to identify the user's emotional state.

[0666] The emotional data analyzed by the emotion engine, along with user preference data, is sent from the device to the server. Upon receiving this data, the server stores it in a database for centralized management.

[0667] The server then fuses and analyzes the received preference and emotion data. This utilizes a generative model that takes emotional tendencies into account. This model has the ability to select and generate appropriate information according to a specific emotional state. Specifically, it adjusts the content soothing if the user is relaxed, and provides stress-reducing information if they are tense.

[0668] The generated information is sent from the server to the terminal, which then presents this information to the user in an easy-to-understand manner. The interface is dynamically adjusted to provide a presentation that matches the user's current emotional state. This allows users to receive a service that fits their emotions, leading to increased satisfaction.

[0669] Specific example:

[0670] For example, when a user visiting a museum uses this system, the terminal detects their emotions from their facial expressions and voice. If they are relaxed, it suggests exhibition information, including soothing music that matches their current mood. If the user is excited, it can enhance their visit by providing more interactive and participatory activity information. By combining this emotion-driven information suggestion, users can have the most optimal experience at that moment.

[0671] The following describes the processing flow.

[0672] Step 1:

[0673] The device collects data on the user's hobbies and interests, and uses its camera and microphone to recognize the user's facial expressions and voice tone in real time as emotions. This data is then converted into emotional states through an emotion engine.

[0674] Step 2:

[0675] The device sends the collected preference and emotional data to the server. During this process, the data is appropriately formatted and encrypted to protect privacy.

[0676] Step 3:

[0677] The server stores received preference and emotion data in a database and updates individual user profiles. The database also includes records of each user's different emotional states, enabling dynamic data management.

[0678] Step 4:

[0679] The server analyzes the received data and generates optimized information suggestions at that point using a generative model that takes emotional data into account. For example, if the user is feeling stressed, the generative model might generate suggestions related to relaxation.

[0680] Step 5:

[0681] The server sends the generated suggestions to the terminal. Based on the received information, the terminal adjusts and displays the interface in a way that suits the user's emotions.

[0682] Step 6:

[0683] Users receive the presented information and can send feedback from their device to the server as needed. This feedback reflects the user's satisfaction level and newly identified preferences.

[0684] Step 7:

[0685] The server analyzes the feedback it receives and uses it to improve the generative model. The feedback data continuously improves the accuracy of user sentiment-based suggestions, thereby enhancing the overall system performance.

[0686] (Example 2)

[0687] 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".

[0688] In modern information processing systems, providing information suggestions that consider not only user preferences but also their real-time emotional state is crucial for delivering a highly satisfying experience. However, conventional systems have limitations in analyzing emotional data and providing appropriate information based on it, failing to achieve complete personalization that fully responds to user emotions. Furthermore, the technology for efficiently utilizing user feedback to improve information suggestions is insufficient.

[0689] 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.

[0690] In this invention, the server includes means for integrating and managing preference data and emotional data collected from users; means for fusing multiple generative models based on the preference data and emotional data to generate optimized information suggestions according to the user's emotional state; and means for dynamically adjusting and displaying the generated information on the user's terminal, and presenting it in a way that is appropriate to the user's current emotional state. This enables advanced personalization tailored to the user's emotions and continuous improvement of the system's performance through feedback.

[0691] "Preference data" refers to data that shows information about the areas and activities that users are interested in.

[0692] "Emotional data" refers to information that indicates the user's emotional state, and is acquired through facial recognition and voice analysis.

[0693] A "generative model" is an algorithm used to generate new content or information based on input data.

[0694] "Feedback" refers to information that users provide, expressing their evaluations and reactions to the information and services offered, and is used to improve the system.

[0695] Personalization is the process of optimizing services and content according to the individual preferences and needs of each user.

[0696] A "server" is a computer system that processes information, stores and manages data, and transmits information to terminals as needed.

[0697] A "terminal" is a device that allows users to access a system and receive information through its interface.

[0698] This invention constructs a system that combines user preference data and real-time sentiment data to provide personalized information. This system consists of a server, a terminal, a sentiment analysis engine, and the user, and each element works in cooperation with the others.

[0699] Users first register their hobbies and interests via a device. The device is equipped with a camera and microphone, and these devices are used to capture the user's facial expressions and voice tone, collecting real-time emotional data.

[0700] In this system, the terminal sends collected data to the sentiment analysis engine, which analyzes this data to identify the user's emotional state. The analysis results and preference data are then sent from the terminal to the server.

[0701] The server stores the received preference and emotion data in a database and then uses it for analysis. It uses a generative AI model to select and generate the most appropriate information based on a specific emotional state. For example, when the user is relaxed, it provides calming music information, and when they are stressed, it suggests information to reduce stress.

[0702] The generated information is sent from the server to the terminal and presented to the user in a dynamically adjusted form on the terminal. The user interface is optimized to adapt to the user's emotions, allowing the user to receive information that resonates with their feelings. As a result, a highly satisfying experience is provided.

[0703] As a concrete example, when a user visits a museum, the device detects a relaxed state from their facial expressions and voice and suggests calm exhibit information appropriate for the situation. On the other hand, if an excited state is detected, it presents more interactive activity information. This system allows users to enjoy the best possible experience according to their emotions at that moment.

[0704] An example of a prompt message used in a generative AI model would be an instruction such as, "Suggest optimal content for a relaxed user, and engage both their visual and auditory senses."

[0705] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0706] Step 1: The user registers their hobbies and interests through the device. The input is the user's own information about their hobbies and interests, and the output is saved on the device as preference data. Specifically, registration is performed by selecting items on the device's interface or filling in data in input forms.

[0707] Step 2: The device uses its built-in camera and microphone to collect real-time emotional data from the user. The input is the user's facial expressions and voice tone, and the output is emotional data obtained by analyzing these. Specifically, this involves capturing facial expressions with the camera and processing voice input.

[0708] Step 3: The device sends the collected emotional data to the emotion analysis engine. The input is the emotional data obtained in Step 2, and the output is the detailed emotional state analyzed by the emotion analysis engine. Specifically, the emotion analysis algorithm runs and the data is analyzed.

[0709] Step 4: The terminal sends the analyzed sentiment and preference data to the server. The input is the analyzed sentiment and preference data, and the output is the server that receives this data. Operationally, the data is encoded and securely transmitted over the network.

[0710] Step 5: The server stores the received preference and emotion data in a database and then integrates and analyzes this data. The input is the received preference and emotion data, and the output is the analysis results based on this data. Specifically, the process involves writing to the database and analyzing the data using a generative AI model.

[0711] Step 6: The server uses a generative AI model to select and generate information that matches the user's emotional state. The input is the analysis results obtained in Step 5, and the output is the optimized information provided to the user. The operation includes an information generation process by the AI ​​model based on prompt statements.

[0712] Step 7: The server sends the generated information to the terminal. The input is the generated information data, and the output is the terminal that received the information. Specifically, the information is sent based on the data transmission protocol from the server.

[0713] Step 8: The terminal dynamically adjusts the received information on the user interface and presents it to the user. The input is the information received from the server, and the output is the content displayed on the screen shown to the user. In operation, the interface dynamically changes according to the user's current emotional state, presenting the information in the most optimal way.

[0714] (Application Example 2)

[0715] 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".

[0716] This invention aims to address the challenge of personalizing digital content delivery in accordance with the user's emotional state. Existing content distribution systems generally provide information based solely on user preference data, and do not adequately provide flexible content recommendations that take into account the user's instantaneous emotional state. As a result, users often receive content that does not match their emotions or mood, leading to decreased satisfaction.

[0717] 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.

[0718] In this invention, the server includes means for integrating and managing preference data and emotional data collected from users; means for fusing multiple generative models based on the preference data and emotional data to generate information suggestions adapted to the user's emotional state; and means for dynamically adjusting the generated information on the user's terminal and presenting it in visual and auditory representations corresponding to the user's emotional state. This makes it possible to provide content that is appropriate to the user's emotions in a timely manner, thereby improving the user experience.

[0719] "Preference data" refers to information about the genres and content that users prefer, and is used for selecting and recommending content.

[0720] "Emotional data" refers to data that represents a user's current emotions and mood, and is information obtained from facial expressions, tone of voice, and other biosignals.

[0721] A "generative model" is an algorithm or program that generates or selects content that matches the user's needs and circumstances based on collected data.

[0722] "Information recommendations" are recommendations regarding content and services provided to users, and are determined based on preference data and sentiment data.

[0723] "Visual and auditory representations" refer to the format in which information is presented to the user, including on-screen visual and audio feedback.

[0724] Based on this invention, the system that implements the application example consists of a server, a terminal, an emotion engine, and a user. Specifically, it is implemented as follows:

[0725] First, the device is a smartphone equipped with a camera and microphone. This hardware captures the user's facial expressions and voice tone in real time and collects the data. The device sends this data to the emotion engine. The emotion engine uses the Google Cloud Vision API and IBM Watson Tone Analyzer to analyze the facial expressions and voice tone and identify the user's emotional state.

[0726] The analyzed sentiment data and preference data previously registered by the user via the device are sent to the server. The server stores and integrates this collected data in a database. Next, the server utilizes generative AI models, including OpenAI's GPT-3, to select appropriate content based on a specific sentiment state. In this selection process, the generative AI model uses prompt statements to generate content that matches the sentiment.

[0727] The generated information is sent from the server to the terminal, which then displays the content in a format that matches the user's emotional state. This display utilizes both visual and auditory representations, enabling a more personalized experience for the user.

[0728] As a concrete example, when a user is using the application in a relaxed state in the evening, classical music and sunset scenery videos selected based on their past preference data will be automatically presented. An example of a prompt message used in this case might be, "Please recommend music and videos that the user should watch when they are in a relaxed emotional state. They have a history of enjoying classical music."

[0729] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0730] Step 1:

[0731] The device uses a camera and microphone to capture the user's facial expressions and voice tone in real time. The input is the user's facial image and voice signal, and the output is the recording of them as digital data.

[0732] Step 2:

[0733] The terminal transmits the collected facial and audio data to the emotion engine. The input is the digital data obtained in step 1, which is then converted into a data format for analysis and used as the output.

[0734] Step 3:

[0735] The emotion engine uses the Google Cloud Vision API to analyze facial expressions and IBM Watson Tone Analyzer to analyze voice tone. The input is the analysis data format obtained in step 2, and the output is the analysis result indicating the user's emotional state. In this step, facial feature points and voice frequencies are analyzed to identify the emotional state.

[0736] Step 4:

[0737] The server integrates and manages emotional data received from terminals with preference data pre-registered by the user. Input consists of emotional data and preference data, which are combined, stored in a database, and output as basic data for information selection.

[0738] Step 5:

[0739] The server utilizes a generative AI model to generate information suggestions using prompt sentences based on preference and emotion data. The input is the data integrated in step 4, and the output is content information appropriate to the user's emotional state. In this process, the generative AI model plays the role of combining and generating the most suitable content.

[0740] Step 6:

[0741] The generated information is sent from the server to the terminal. The input is the content information obtained in step 5, and the output is converted into a data format for display in visual and auditory formats and sent to the terminal.

[0742] Step 7:

[0743] The device presents the received content using visual and auditory representations that match the user's emotional state. The input is the data received in step 6, and the output is the specific content display for the user. This display performs specific actions, such as playing classical music and soothing images if the user is relaxed.

[0744] 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.

[0745] 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.

[0746] 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.

[0747] 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.

[0748] 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.

[0749] 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.

[0750] 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.

[0751] 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.

[0752] 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."

[0753] 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.

[0754] 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.

[0755] 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.

[0756] 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.

[0757] 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.

[0758] 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.

[0759] 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.

[0760] 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.

[0761] 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.

[0762] 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.

[0763] 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.

[0764] 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 as being incorporated by reference.

[0765] The following is further disclosed regarding the embodiments described above.

[0766] (Claim 1)

[0767] [Means for integrating and managing preference data collected from users,

[0768] [Means for fusing multiple generative models based on the preference data to generate optimized information suggestions,

[0769] [Means for dynamically adjusting and displaying the generated information on the user's terminal,

[0770] A system that includes this.

[0771] (Claim 2)

[0772] [The system according to claim 1, which collects user feedback and improves the performance of the generative model based on said feedback.

[0773] (Claim 3)

[0774] [The system according to claim 1, which includes an algorithm for extracting common hobbies and preferences among multiple users, and which supports group decision-making.

[0775] "Example 1"

[0776] (Claim 1)

[0777] [Means for integrating and storing preference data collected from users,

[0778] [Means for analyzing collective preference patterns based on the preference data,

[0779] [A means for dynamically merging multiple generation algorithms based on analysis results to generate optimized information proposals,

[0780] [Means for dynamically adjusting and displaying the generated information on the user's device, taking into account the current location information,

[0781] A system that includes this.

[0782] (Claim 2)

[0783] [The system according to claim 1, which collects user feedback and analyzes said feedback to improve the performance of the generation algorithm.

[0784] (Claim 3)

[0785] [The system according to claim 1, comprising an analytical algorithm that extracts common preference patterns among multiple users and supports group decision-making.

[0786] "Application Example 1"

[0787] (Claim 1)

[0788] [Means for integrating and managing interest information collected from users,

[0789] [Means for merging multiple generation algorithms based on the interest information to generate optimized information provision,

[0790] [Means for dynamically adjusting and displaying the generated information on the user's information processing device,

[0791] [Means of providing relevant data based on viewing history and displaying relevant product information,

[0792] A system that includes this.

[0793] (Claim 2)

[0794] [The system according to claim 1, which collects user evaluations and improves the performance of the generation algorithm based on said evaluations.

[0795] (Claim 3)

[0796] [The system according to claim 1, which includes a calculation method for extracting common interests among multiple users and assists in the selection of a group.

[0797] "Example 2 of combining an emotion engine"

[0798] (Claim 1)

[0799] [Means for integrating and managing preference data and emotional data collected from users,

[0800] [Methods for fusing multiple generative models based on preference data and emotion data to generate optimized information suggestions according to the user's emotional state,

[0801] [A means of dynamically adjusting and displaying generated information on the user's device, in a way that is appropriate to the user's current emotional state,

[0802] A system that includes this.

[0803] (Claim 2)

[0804] [The system according to claim 1, which collects user feedback, improves the performance of the generative model based on said feedback, and further personalizes information suggestions.

[0805] (Claim 3)

[0806] [The system according to claim 1, which includes an algorithm for extracting common hobbies, preferences, and emotional trends among multiple users, and supports group decision-making based on emotional insights.

[0807] "Application example 2 when combining with an emotional engine"

[0808] (Claim 1)

[0809] [Means for integrating and managing preference data and emotional data collected from users,

[0810] [A means for fusing multiple generative models based on the preference data and emotion data to generate information suggestions adapted to the user's emotional state,

[0811] [Means for dynamically adjusting the generated information on the user's device and presenting it with visual and auditory expressions that correspond to the user's emotional state,

[0812] A system that includes this.

[0813] (Claim 2)

[0814] [The system according to claim 1, which collects user feedback and improves the performance of the generative model based on said feedback.

[0815] (Claim 3)

[0816] The system according to claim 1, comprising an algorithm that analyzes the emotional tendencies of multiple users and supports group decision-making based on common emotional states. [Explanation of Symbols]

[0817] 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 of integrating and managing preference data collected from users, A means for fusing multiple generative models based on the preference data to generate optimized information suggestions, A means for dynamically adjusting and displaying the generated information on the user's terminal, A system that includes this.

2. The system according to claim 1, which collects user feedback and improves the performance of the generative model based on said feedback.

3. The system according to claim 1, which includes an algorithm for extracting common hobbies and preferences among multiple users, and supports group decision-making.

Images