system

Abstract

We provide the system. [Solution] The service provider's system includes means for receiving interest information from users and storing such information in a data storage device. A means for analyzing the user's behavioral history data and detecting changes in their interests, A means for automatically generating information from the latest information resources based on the user's interests, using a generation means, A means for transmitting and displaying the generated information to the user's terminal device, A means for receiving feedback from users and using it to improve the accuracy of the generation means, 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, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern times, users are daily exposed to a large amount of digital information, and it has become difficult to quickly find useful information for themselves from among them. In addition, the abundance of information brings a sense of mental fatigue to users, and there is a demand to efficiently digest information. However, current technologies do not sufficiently address users' individual interests and preferences and provide an appropriate amount of necessary information. The purpose is to solve such problems.

Means for Solving the Problems

[0005] This invention provides a system for service providers that receives user interest information and stores it in a data storage device. Furthermore, it includes means for analyzing user behavior history data and detecting changes in interests. Using a generation means, information can be automatically generated from the latest information resources based on the user's interests, and the generated information can be transmitted to and displayed on the user's terminal device. In addition, by receiving feedback from the user and using it to improve the accuracy of the generation means, it is possible to constantly increase user satisfaction and efficiently provide necessary information.

[0006] A "service provider's system" is a combination of hardware and software used to provide information services to users via the internet.

[0007] "User" refers to an individual or group that seeks to obtain information by using the service.

[0008] "Interest information" refers to data that indicates a user's interests and concerns, including their selection of categories and topics.

[0009] A "data storage device" refers to a memory or storage device used to store data on a computer system.

[0010] "Behavioral history data" refers to data that includes records of actions taken by users in the past and content they have viewed.

[0011] "Analysis" refers to the computational or processing steps performed to extract meaningful information from data.

[0012] "Means for detecting changes in interests" refers to technologies and algorithms used to identify how a user's interests have changed over time.

[0013] "Generation means" refers to algorithms and models used to automatically generate information related to the user.

[0014] "Information resources" refers to the original data for the generation means to refer to, such as news articles, information in databases, website content, etc.

[0015] "Terminal device" is an electronic device used by users to receive and view information, including smartphones and PCs.

[0016] "Feedback" refers to the evaluations and opinions made by users on the provided information.

[0017] "Used for improving accuracy" refers to the process of using feedback information to improve the output content of the generation means and provide more appropriate information to users.

Brief Description of Drawings

[0018] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which multiple emotions are mapped. [Figure 10]Shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] In the following embodiments, a numbered 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.

[0022] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0023] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0024] 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).

[0025] 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."

[0026] [First Embodiment]

[0027] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0036] 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.

[0037] 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.

[0038] 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".

[0039] This invention provides a system that efficiently delivers information based on user interests. The system described below embodies a method for exchanging information between a server, a terminal, and a user, and for generating and displaying personalized content to the user.

[0040] The server first receives category data from the user indicating their interests. For example, if a user selects the categories "Sports" and "Technology" on their device, the server stores that information in a data storage device. Furthermore, the server collects and analyzes the user's past behavioral history to identify how the user's interests have changed based on this information.

[0041] The server then collects content from the latest information resources and generates information based on the user's interests using generation methods. This involves leveraging natural language processing techniques to extract and summarize user-relevant information from a vast dataset. The generated information is updated in real time and sent to the user's device at the appropriate time. The device displays this content to the user, allowing them to quickly digest information that interests them.

[0042] Furthermore, users can submit feedback on the displayed content. The server uses this feedback to improve the accuracy of its content generation methods. For example, if a user rates a particular news article as "useful," the server uses this information to improve future content generation, thereby enhancing the quality of information provided to individual users.

[0043] As a result, users can obtain the necessary information in an appropriate format, reducing fatigue caused by information overload. Through this system, information provision to users becomes more personalized, enabling it to meet diverse needs.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The user selects categories of interest on their device. These selections include categories such as entertainment, sports, and technology. The device then sends the selected category information to the server.

[0047] Step 2:

[0048] The server stores the received category information in a data storage device. This enables the provision of information based on the user's interests in subsequent processing.

[0049] Step 3:

[0050] The server periodically analyzes user behavior history data. This includes information such as content the user has viewed in the past and links they have clicked. Based on the analysis results, changes in the user's interests are detected.

[0051] Step 4:

[0052] The server collects the latest information resources, such as news articles and blog posts. To do this, it gathers information from web databases via scraping or APIs.

[0053] Step 5:

[0054] The server analyzes the collected information resources using natural language processing technology and summarizes and reorganizes content related to the user's selected category. Information tailored to the user is automatically generated by the generation mechanism.

[0055] Step 6:

[0056] The server sends the generated personalized content to the user's device. The device displays the received content in a format that the user can view.

[0057] Step 7:

[0058] Users view the content they receive and provide feedback on the information provided. This feedback includes opinions such as "helpful" or "not interesting."

[0059] Step 8:

[0060] The server receives feedback from users and uses it as data to improve the generation process. This will enable the provision of more accurate information in the future, thereby improving user satisfaction.

[0061] (Example 1)

[0062] 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."

[0063] In modern society, the overwhelming amount of information available makes it difficult for users to efficiently select and understand information relevant to them. Therefore, there is a need for a system that efficiently provides personalized information based on users' interests. Furthermore, it is challenging to flexibly respond to changes in users' interests and continuously improve the accuracy of information provided.

[0064] 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.

[0065] In this invention, the server includes means for acquiring interest information from the user and storing the information on a recording medium, means for analyzing the user's past operation history and identifying changes in interest, and means for utilizing automated information generation means to generate data based on the user's interests from the latest information sources. This makes it possible to provide users with personalized information, reduce fatigue caused by information overload, and meet the diverse needs of the user.

[0066] "Interest information" refers to information about specific fields or themes that users are interested in. This information is derived from the user's choices and actions.

[0067] "Recording media" refers to physical or electronic devices or infrastructure used to store data and information. This includes databases and server storage.

[0068] "Operation history" refers to a record of a series of actions and choices made by a user when using a system or device. This history is used to analyze user behavior patterns.

[0069] "To identify" refers to the process of identifying and clarifying specific elements or characteristics based on given information or data.

[0070] "Automated information generation methods" refer to processes that generate information without manual intervention using algorithms and models. This particularly involves the use of machine learning and natural language processing technologies.

[0071] "Source" refers to the data stream, website, or other information-providing platform from which information is obtained.

[0072] "Generating data" refers to the process of creating new information based on existing information. This allows for the provision of specialized information tailored to the user's needs and conditions.

[0073] This invention provides a system that enables the personalization of information based on user interests through the mutual cooperation of servers, terminals, and users.

[0074] The server first uses a data storage device to receive interest information sent by the user and stores it on a recording medium. Databases such as MySQL® or MongoDB are used for this operation. Next, the server collects the user's operation history and uses analysis software to identify changes in interest. Data processing libraries such as Python's Pandas and NumPy are used for this analysis.

[0075] The server further utilizes a generative AI model as an automated means of generating information. For this model, OpenAI® models are available to implement natural language processing technology. The server retrieves data from the latest information sources and uses text such as "The user's interest categories are 'Environment' and 'Science.' Please summarize the latest news and articles related to these fields" as prompts to input into the generative AI model. Based on these prompts, the AI ​​model generates data relevant to the user.

[0076] The generated information is immediately sent from the server to the terminal. The terminal receives the information in real time using protocols such as WebSocket or HTTP and displays it to the user. The user can provide various evaluation feedback on the displayed information. This feedback is sent back to the server and used to improve the accuracy of the generation method. Specifically, if the user evaluates "this information is useful," that feedback is used to adjust the generation AI model, enabling the provision of more precise information.

[0077] In this way, the entire system works in coordination, allowing users to receive accurate information without being overwhelmed by excessive information. The introduction of this system enables users to acquire necessary information with high efficiency, reducing the burden caused by information overload.

[0078] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0079] Step 1:

[0080] The user enters categories of interest on their device. For example, the user might check "Sports" or "Technology" from the application's interface. This action is a user selection, and the output is the selected category information. This category information forms the basis for subsequent data processing.

[0081] Step 2:

[0082] The device sends category information of interest selected by the user to the server. Specifically, it uses an HTTP request to send category information to the server's API. The input to this request is the category information selected by the user, and the output is data stored on the server. The server stores the received information in a database and saves this data to a storage medium.

[0083] Step 3:

[0084] The server retrieves and analyzes user activity history from the database. The input here is existing activity history data. The server uses tools such as Python's Pandas library to analyze this data and identify changes in user interests. The output obtained through this analysis is detailed data regarding changes in interests.

[0085] Step 4:

[0086] The server uses automated information generation methods to generate up-to-date information based on the user's category information. The input here consists of pre-collected category information and the results of past behavioral history analysis. The generating AI model is given a prompt such as, "The user's interest categories are 'Environment' and 'Science.' Please summarize the latest news and articles that match these categories." The output of this process is summary information tailored to the user's interests.

[0087] Step 5:

[0088] The generated information is sent from the server to the terminal in real time. The input is the summary information generated in step 4. The terminal receives this information via WebSocket or HTTP and displays it to the user in an easy-to-read format using a display device. The output is the information presented visually.

[0089] Step 6:

[0090] Users can evaluate the displayed information. Specifically, they send feedback such as "helpful" or "not interesting" to the server via an interface on their device. This feedback input is the user's evaluation. The server uses the received feedback to readjust the AI ​​model to improve the accuracy of the generation method. The output is the performance of the improved AI model.

[0091] Through this series of processing steps, the system provides users with efficient, accurate, and personalized information.

[0092] (Application Example 1)

[0093] 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."

[0094] In modern society, the sheer volume of information presents a challenge, making it difficult for users to quickly and effectively obtain the information they need. Furthermore, existing methods fail to adequately deliver information based on users' interests, resulting in limited personalized content delivery.

[0095] 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.

[0096] In this invention, the server includes means for the service provider's equipment to receive interest information from the user and store the information in a storage device, means for analyzing the user's behavioral history information and detecting changes in interests, and means for automatically generating information based on the user's interests from the latest information sources in order to generate information. This makes it possible to update the information provided to the user in real time, optimize the generation AI model by utilizing feedback, and efficiently provide personalized content.

[0097] "Service provider equipment" refers to the hardware or software used to receive interest information from users and store it in data storage.

[0098] "Interests" refers to information about categories or topics that users are particularly interested in.

[0099] A "storage device" is a device or system for storing digital data for the long term.

[0100] "Behavioral history information" refers to a record of information resources that a user has accessed and used in the past.

[0101] "Changes in interests" refers to a state in which a user's interests fluctuate over time or due to information acquisition.

[0102] "Information sources" refer to public or private resources that provide up-to-date data and information.

[0103] "Means of automatically generating information" refers to the process of automatically creating relevant information using algorithms and models based on the user's interests.

[0104] A "display device" is a device that provides generated information to the user visually.

[0105] A "generative AI model" refers to an artificial intelligence algorithm built to generate appropriate output based on user input.

[0106] "Feedback" refers to the evaluations and impressions that users give to the content provided, and is used to improve the personalization accuracy of the system.

[0107] The system for implementing this invention mainly consists of a server, a display terminal, and a user. The server first receives the user's interests and stores them in a storage device. At this time, the server analyzes the user's behavioral history information and identifies changes in interests. Python or Pandas is used to aggregate and analyze the data.

[0108] The server then utilizes a generative AI model to generate information. Using the Transformers library as a natural language processing technique, it automatically generates relevant data from the latest information sources based on user interests. This process employs machine learning algorithms to create personalized content for the user.

[0109] The generated information is updated in real time and sent from the server to the display terminal. This terminal is built using React Native and displays the content to the user through an efficient user interface.

[0110] Users can provide feedback on the displayed content, and the server uses this feedback to optimize the prompts of the generating AI model, improving the accuracy of information generation in the future.

[0111] For example, if a user who commutes by train uses the app on their smartphone and is interested in sports and technology, they can view the latest relevant articles and videos and rate them as "useful," and this feedback will be reflected in future content generation. Furthermore, a prompt such as, "Summarize and display the latest technology articles and sports news tailored to the user's interests. Use eye-catching headlines for important information," will ensure the generation AI model functions correctly.

[0112] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0113] Step 1:

[0114] The server receives user interest information as input and stores it as data in a storage device. Specifically, when a user selects a category such as sports or technology, that information is sent to the server.

[0115] Step 2:

[0116] The server analyzes behavioral history information stored on the storage device. Here, Pandas is used to aggregate past behavioral history and detect changes in interests. The input is behavioral history information, and the output is data showing the detected changes in interests.

[0117] Step 3:

[0118] The server automatically generates information using natural language processing techniques with a generative AI model. Specifically, it utilizes the Transformers library to extract relevant information from information sources based on past behavioral history data and current interests, and outputs it as a summary. The input consists of data on interests and related information sources.

[0119] Step 4:

[0120] The server sends the generated information to the display device. The device, built with React Native, provides the information to the user by displaying the automatically generated content. Specifically, a summary of the information is visually displayed on the user interface.

[0121] Step 5:

[0122] Users provide feedback on the displayed content and send this feedback to the server. The input is the user's feedback, and the output is the data necessary for improving accuracy. Based on the feedback, the prompts of the generated AI model are optimized.

[0123] Step 6:

[0124] The server readjusts the generative AI model for the next information generation. Specifically, prompts are updated based on new user feedback, improving accuracy in subsequent information generation. This is a process of refining the model's behavior using feedback.

[0125] 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.

[0126] This invention embodies a system that provides information based on the user's interests and emotional state. This system generates and displays personalized content by exchanging data and information between the server, terminal, and user.

[0127] Specifically, users can indirectly communicate their emotions at any given time by selecting categories of interest and providing feedback via their device. The server receives this input data and stores it in a data storage device. The server also has an emotion engine that analyzes the user's behavioral history and emotional information to identify the user's current emotional state.

[0128] The emotion engine identifies the emotions a user feels while viewing information, based on user input data and past behavioral history. This emotion information is used by a generation mechanism along with regular interest data. The generation mechanism automatically generates information from the latest information resources in a way that matches the user's interests and emotions, and then adjusts or optimizes the content. As a result, personalized content that is more relevant to the user and also responds to their emotional state is generated.

[0129] For example, if the emotion engine identifies that a user has positive feelings towards "sports" as a category, the server will generate positive news and articles that will attract the user's interest. The generated content is sent to the user's device, where the user can view it. In this way, the server can provide optimal information based on the user's emotions and interests.

[0130] Throughout this entire system, users can not only efficiently gather the information they need, but also enjoy a highly satisfying experience that takes their emotions into consideration.

[0131] The following describes the processing flow.

[0132] Step 1:

[0133] The user selects categories of interest on their device (for example, "News," "Entertainment," "Sports," etc.). This information is sent to the server via the device.

[0134] Step 2:

[0135] The server stores the received category data in the data storage device. This records each user's interests.

[0136] Step 3:

[0137] The device provides indirect feedback about the user's emotions by sending information such as user actions, comments, and browsing speed to the emotion engine.

[0138] Step 4:

[0139] The server uses an emotion engine to analyze user input data and behavioral history to identify the user's current emotional state. This emotional information reflects the emotions the user is experiencing while using the content.

[0140] Step 5:

[0141] The server collects the latest information resources from the web and databases. These resources include news articles, video content, and blog posts.

[0142] Step 6:

[0143] The server uses generation means to automatically generate content based on the user's interests and emotions from collected information resources, and then adjusts or optimizes the content.

[0144] Step 7:

[0145] The generated personalized content is sent from the server to the user's device.

[0146] Step 8:

[0147] The device displays the received content to the user, making it available for viewing and reading.

[0148] Step 9:

[0149] Users can provide feedback after viewing the content. This feedback will be used to improve future content and its accuracy.

[0150] Step 10:

[0151] The server incorporates new user feedback into the learning of its emotion engine and generation methods, helping to create more refined content. This allows the system to improve user satisfaction over time.

[0152] (Example 2)

[0153] 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 will be referred to as the "terminal."

[0154] In modern information delivery systems, providing information quickly and appropriately optimized based on users' interests and emotions is a challenging task. Existing systems often only consider users' interests, and there are limitations to personalization that utilizes emotional states. Therefore, it is necessary to achieve information delivery that is more satisfying for users.

[0155] 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.

[0156] In this invention, the server includes means for receiving interest information and emotional information from a user and storing the information in a storage device, means for analyzing the user's behavioral history data and emotional data to identify changes in interest and emotional state, and means for automatically generating information based on the user's interests and emotions from the latest information sources using generation means. This makes it possible to provide users with information that is more relevant and also corresponds to their emotional state.

[0157] "Service provider equipment" refers to a combination of hardware and software that constitutes a system for providing services to users.

[0158] "Users" refer to those who receive information or provide feedback through this system.

[0159] "Interest information" refers to data that represents the user's interest in a particular field or topic.

[0160] "Emotional information" refers to data that indicates the user's psychological state, such as emotions like positive, negative, or neutral.

[0161] A "storage device" is a device used to store digital information and is used to temporarily or permanently retain received data.

[0162] "Behavioral history data" refers to a dataset that includes records of actions and choices that users have made in the past.

[0163] "Analysis" is the process of processing received data statistically or algorithmically to derive useful information or patterns.

[0164] "Generative means" refers to the processes or technologies used to form and output information based on the user's interests and emotions.

[0165] "Information source" refers to the place or medium from which data or content used by a system to provide to users is transmitted.

[0166] "Automatic generation" refers to a system creating information based on specified conditions without human intervention.

[0167] "Terminal device" refers to a device used by a user to access a service, and includes computers, smartphones, tablets, and other similar devices.

[0168] In implementing this invention, the system mainly consists of a server, a terminal, and a user.

[0169] The server, as part of the service provider's equipment, receives interest and emotion information from users. This information is stored in a data storage device, such as a database. The server uses an emotion analysis engine developed with the machine learning library "TENSORFLOW®" and "Python" to analyze the user's behavioral history data and current emotion information. It then identifies the user's emotional state. Based on the changes in interest and emotional state identified through this analysis, new information is constructed using a generative AI model, which is a generation method. In this generation process, natural language processing technology is utilized to select content that matches the user's interests and emotions, and to automatically generate optimized information.

[0170] For example, if a user selects the "Sports" category and submits positive emotional information, the server processes this information through its sentiment analysis engine and generates positive and up-to-date sports news that is best suited to the user's state. An example of a prompt for this generating AI model is as follows:

[0171] Prompt: Please provide the latest and most positive sports news that will attract users when they are feeling positive emotions.

[0172] The device receives generated information sent from the server and displays it in a format viewable by the user. This allows users to experience content optimized to their interests and emotions.

[0173] Users send their interests and emotions to the system via their devices, providing feedback. This feedback is collected by the server and used to improve the accuracy of the generation process.

[0174] Therefore, this system can provide users with information that is highly relevant and emotionally resonant.

[0175] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0176] Step 1:

[0177] Users select their interest categories through their device and provide emotional feedback. This input information is sent from the device to the server.

[0178] Step 2:

[0179] The server stores interest categories and emotional information received from the terminal in its storage device. The input data includes categories selected by the user and feedback indicating their emotional state. Based on this, an entry is created in the database, and the user profile is updated.

[0180] Step 3:

[0181] The server uses an emotion analysis engine to analyze the user's past behavioral history data and newly received emotion information. Based on the received data, a process is initiated to identify the user's emotional state. This analysis identifies what the user wants and what information is appropriate for them.

[0182] Step 4:

[0183] The server uses a generative AI model as a generation tool to automatically generate content based on identified emotional states and interests. Input includes the user's current interests and emotional information, and output is personalized news articles and information. Generation prompts are input to the AI ​​model to generate information relevant to the user.

[0184] Step 5:

[0185] The server sends the generated content to the device. The transmitted data is converted to the optimal format on the device and displayed. The device then provides the user with the generated personalized content, which the user can view.

[0186] Step 6:

[0187] The user provides feedback on the displayed content. The device sends this feedback back to the server. This feedback is used by the server as training data to improve the accuracy of the generation method.

[0188] (Application Example 2)

[0189] 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 device 14 will be referred to as the "terminal."

[0190] In today's information-saturated age, users face the challenge of efficiently obtaining information optimized for their interests and emotions. Traditionally, information provision systems have provided information based on user interests, but have failed to provide appropriate information that takes into account the user's emotional state. As a result, user satisfaction has decreased, and the efficiency of information consumption has been impaired.

[0191] 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.

[0192] In this invention, the server includes means for receiving user interest information and storing it in a data storage device, means for analyzing user behavior history data and detecting changes in interests, means equipped with an emotion analysis engine for analyzing and identifying the user's emotional state, means for automatically generating information from the latest information resources based on the user's interests and emotional state using generation means, and means for transmitting and displaying the generated information to the user's terminal device. This makes it possible to accurately provide information that matches the user's interests and emotions, thereby improving user satisfaction and increasing the efficiency of information consumption.

[0193] A "service provider system" is a system that has a mechanism for receiving data from users and processing, storing, and analyzing that data.

[0194] A "data storage device" is a device for safely and efficiently recording and storing received data.

[0195] "Analyzing behavioral history data" refers to analyzing a user's past behavioral data to derive changes and trends in their interests and preferences.

[0196] An "emotion analysis engine" is a processing unit or program that identifies a user's current emotional state based on the user's input data and behavioral history.

[0197] "Generation means" refers to a technology or process for automatically generating up-to-date information based on the user's interests, concerns, and emotional state.

[0198] "Terminal devices" refer to various types of equipment (such as smartphones, tablets, and computers) that users use to receive and manipulate information.

[0199] "Feedback" refers to the responses or reactions that users provide to a system, and is used to improve the quality of the information generated.

[0200] This invention relates to the realization of an advanced personalized system that provides information based on the user's interests and emotions. The following is an example of how to specifically implement this invention.

[0201] The server first receives interest information from users and stores it in a data storage device. This step securely stores the data using a storage system located on a cloud platform (e.g., Amazon S3). The server also collects and analyzes user behavior history data. Data analysis tools (e.g., Google Analytics) are used for this analysis. This allows for understanding changes in user interests.

[0202] Furthermore, the server uses an emotion analysis engine to identify the user's emotional state. This analysis utilizes an emotion analysis API (e.g., Microsoft® Azure® Emotion API) that leverages natural language processing technology. The results are then integrated with the user's interest data.

[0203] Next, the server uses a generation mechanism to generate information that matches the user's interests and emotional state. In this step, a generation AI model (e.g., GPT-3®) is utilized to automatically generate and adjust content that is optimal for the user.

[0204] The generated content is sent to the user's device. This device may be a smartphone or tablet, and the user can view the content on these devices. This allows users to efficiently obtain information that is tailored to their interests and emotions.

[0205] For example, if a user selects the "Movies" category and indicates a desire to refresh, the server will generate and send information about new comedy movies and positive review articles. An example of a prompt in response to this would be: "The user is interested in recent movie news and is looking for something relaxing. Please suggest appropriate movie reviews and new release information."

[0206] This system allows users to receive information tailored to their interests and emotions, enabling a highly satisfying information experience.

[0207] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0208] Step 1:

[0209] Users input interest information and feedback using their devices. For example, a user might select the category "movies" and input a feeling such as "feeling happy." This input data is then sent from the device to the server.

[0210] Step 2:

[0211] The server stores the received interest information and feedback in a data storage device. The data is stored in a cloud storage system. This ensures that the data necessary for analysis in subsequent processing is securely retained.

[0212] Step 3:

[0213] The server analyzes the stored behavioral history data. Using data analysis tools such as Google Analytics, it detects changes in the user's interests. During this process, aggregation and trend analysis are performed based on the user's past behavioral data.

[0214] Step 4:

[0215] The server uses an emotion analysis engine to identify the user's emotional state. Based on the input data, it analyzes emotions using the Microsoft Azure Emotion API and extracts specific emotional states. This result is then used in subsequent information generation processes.

[0216] Step 5:

[0217] The server utilizes a generative AI model as a generation tool to automatically generate content based on the user's interests and emotions. For example, it inputs prompt text into an OpenAI GPT-3 model to generate information and articles best suited to the user. At this stage, the content and format of the generated text are optimized.

[0218] Step 6:

[0219] The generated content is sent from the server to the user's device. The user can view the information on their device and, as a result, consume the provided content. This improves user satisfaction and the efficiency of information consumption.

[0220] 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.

[0221] 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.

[0222] 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.

[0223] [Second Embodiment]

[0224] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0225] 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.

[0226] 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).

[0227] 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.

[0228] 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.

[0229] 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).

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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".

[0236] This invention provides a system that efficiently delivers information based on user interests. The system described below embodies a method for exchanging information between a server, a terminal, and a user, and for generating and displaying personalized content to the user.

[0237] The server first receives category data from the user indicating their interests. For example, if a user selects the categories "Sports" and "Technology" on their device, the server stores that information in a data storage device. Furthermore, the server collects and analyzes the user's past behavioral history to identify how the user's interests have changed based on this information.

[0238] The server then collects content from the latest information resources and generates information based on the user's interests using generation methods. This involves leveraging natural language processing techniques to extract and summarize user-relevant information from a vast dataset. The generated information is updated in real time and sent to the user's device at the appropriate time. The device displays this content to the user, allowing them to quickly digest information that interests them.

[0239] Furthermore, users can submit feedback on the displayed content. The server uses this feedback to improve the accuracy of its content generation methods. For example, if a user rates a particular news article as "useful," the server uses this information to improve future content generation, thereby enhancing the quality of information provided to individual users.

[0240] As a result, users can obtain the necessary information in an appropriate format, reducing fatigue caused by information overload. Through this system, information provision to users becomes more personalized, enabling it to meet diverse needs.

[0241] The following describes the processing flow.

[0242] Step 1:

[0243] The user selects categories of interest on their device. These selections include categories such as entertainment, sports, and technology. The device then sends the selected category information to the server.

[0244] Step 2:

[0245] The server stores the received category information in a data storage device. This enables the provision of information based on the user's interests in subsequent processing.

[0246] Step 3:

[0247] The server periodically analyzes user behavior history data. This includes information such as content the user has viewed in the past and links they have clicked. Based on the analysis results, changes in the user's interests are detected.

[0248] Step 4:

[0249] The server collects the latest information resources, such as news articles and blog posts. To do this, it gathers information from web databases via scraping or APIs.

[0250] Step 5:

[0251] The server analyzes the collected information resources using natural language processing technology and summarizes and reorganizes content related to the user's selected category. Information tailored to the user is automatically generated by the generation mechanism.

[0252] Step 6:

[0253] The server sends the generated personalized content to the user's device. The device displays the received content in a format that the user can view.

[0254] Step 7:

[0255] Users view the content they receive and provide feedback on the information provided. This feedback includes opinions such as "helpful" or "not interesting."

[0256] Step 8:

[0257] The server receives feedback from users and uses it as data to improve the generation process. This will enable the provision of more accurate information in the future, thereby improving user satisfaction.

[0258] (Example 1)

[0259] 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."

[0260] In modern society, the overwhelming amount of information available makes it difficult for users to efficiently select and understand information relevant to them. Therefore, there is a need for a system that efficiently provides personalized information based on users' interests. Furthermore, it is challenging to flexibly respond to changes in users' interests and continuously improve the accuracy of information provided.

[0261] 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.

[0262] In this invention, the server includes means for acquiring interest information from the user and storing the information on a recording medium, means for analyzing the user's past operation history and identifying changes in interest, and means for utilizing automated information generation means to generate data based on the user's interests from the latest information sources. This makes it possible to provide users with personalized information, reduce fatigue caused by information overload, and meet the diverse needs of the user.

[0263] "Interest information" refers to information about specific fields or themes that users are interested in. This information is derived from the user's choices and actions.

[0264] "Recording media" refers to physical or electronic devices or infrastructure used to store data and information. This includes databases and server storage.

[0265] "Operation history" refers to a record of a series of actions and choices made by a user when using a system or device. This history is used to analyze user behavior patterns.

[0266] "To identify" refers to the process of identifying and clarifying specific elements or characteristics based on given information or data.

[0267] "Automated information generation methods" refer to processes that generate information without manual intervention using algorithms and models. This particularly involves the use of machine learning and natural language processing technologies.

[0268] "Source" refers to the data stream, website, or other information-providing platform from which information is obtained.

[0269] "Generating data" refers to the process of creating new information based on existing information. This allows for the provision of specialized information tailored to the user's needs and conditions.

[0270] This invention provides a system that enables the personalization of information based on user interests through the mutual cooperation of servers, terminals, and users.

[0271] The server first uses a data storage device to receive interest information sent by the user and stores it on a recording medium. Databases such as MySQL or MongoDB are used for this process. Next, the server collects the user's activity history and uses analysis software to identify changes in interest. Data processing libraries such as Python's Pandas and NumPy are used for this analysis.

[0272] The server further utilizes a generative AI model as an automated means of generating information. For this model, OpenAI models are available to implement natural language processing technology. The server retrieves data from the latest information sources and uses text such as "The user's interest categories are 'Environment' and 'Science.' Please summarize the latest news and articles related to these fields" as prompts to input into the generative AI model. Based on these prompts, the AI ​​model generates data relevant to the user.

[0273] The generated information is immediately sent from the server to the terminal. The terminal receives the information in real time using protocols such as WebSocket or HTTP and displays it to the user. The user can provide various evaluation feedback on the displayed information. This feedback is sent back to the server and used to improve the accuracy of the generation method. Specifically, if the user evaluates "this information is useful," that feedback is used to adjust the generation AI model, enabling the provision of more precise information.

[0274] In this way, the entire system works in coordination, allowing users to receive accurate information without being overwhelmed by excessive information. The introduction of this system enables users to acquire necessary information with high efficiency, reducing the burden caused by information overload.

[0275] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0276] Step 1:

[0277] The user enters categories of interest on their device. For example, the user might check "Sports" or "Technology" from the application's interface. This action is a user selection, and the output is the selected category information. This category information forms the basis for subsequent data processing.

[0278] Step 2:

[0279] The device sends category information of interest selected by the user to the server. Specifically, it uses an HTTP request to send category information to the server's API. The input to this request is the category information selected by the user, and the output is data stored on the server. The server stores the received information in a database and saves this data to a storage medium.

[0280] Step 3:

[0281] The server retrieves the user's operation history from the database and performs analysis. The input here is the existing operation history data. The server uses tools such as Python's Pandas to analyze these data and identify changes in the user's interests. The output obtained through this analysis is detailed data regarding changes in interests.

[0282] Step 4:

[0283] The server uses automated information generation means to generate the latest information based on the user's category information. The input here is the pre-collected category information and the results of past behavior history analysis. For the generation AI model, a prompt sentence such as "The user's interested categories are 'Environment' and 'Science'. Please summarize the latest news and articles that match this." is used. The output of this process is summary information specialized for the user's interests.

[0284] Step 5:

[0285] The generated information is sent from the server to the terminal in real time. The input is the summary information generated in Step 4. The terminal receives this information via WebSocket or HTTP and displays it in an easy-to-view manner for the user using a display device. The output is the visually presented information.

[0286] Step 6:

[0287] The user can evaluate the displayed information. Specifically, feedback such as "useful" or "not interested" is sent to the server via the interface on the terminal. The input of this feedback is the user's evaluation. The server uses the received feedback to readjust the AI model in order to improve the accuracy of the generation means. The output is the performance of the improved AI model.

[0288] Through this series of processing steps, the system provides users with efficient, accurate, and personalized information.

[0289] (Application Example 1)

[0290] 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."

[0291] In modern society, the sheer volume of information presents a challenge, making it difficult for users to quickly and effectively obtain the information they need. Furthermore, existing methods fail to adequately deliver information based on users' interests, resulting in limited personalized content delivery.

[0292] 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.

[0293] In this invention, the server includes means for the service provider's equipment to receive interest information from the user and store the information in a storage device, means for analyzing the user's behavioral history information and detecting changes in interests, and means for automatically generating information based on the user's interests from the latest information sources in order to generate information. This makes it possible to update the information provided to the user in real time, optimize the generation AI model by utilizing feedback, and efficiently provide personalized content.

[0294] "Service provider equipment" refers to the hardware or software used to receive interest information from users and store it in data storage.

[0295] "Interests" refers to information about categories or topics that users are particularly interested in.

[0296] A "storage device" is a device or system for storing digital data for the long term.

[0297] "Behavioral history information" refers to a record of information resources that a user has accessed and used in the past.

[0298] "Changes in interests" refers to a state in which a user's interests fluctuate over time or due to information acquisition.

[0299] "Information sources" refer to public or private resources that provide up-to-date data and information.

[0300] "Means of automatically generating information" refers to the process of automatically creating relevant information using algorithms and models based on the user's interests.

[0301] A "display device" is a device that provides generated information to the user visually.

[0302] A "generative AI model" refers to an artificial intelligence algorithm built to generate appropriate output based on user input.

[0303] "Feedback" refers to the evaluations and impressions that users give to the content provided, and is used to improve the personalization accuracy of the system.

[0304] The system for implementing this invention mainly consists of a server, a display terminal, and a user. The server first receives the user's interests and stores them in a storage device. At this time, the server analyzes the user's behavioral history information and identifies changes in interests. Python or Pandas is used to aggregate and analyze the data.

[0305] The server then utilizes a generative AI model to generate information. Using the Transformers library as a natural language processing technique, it automatically generates relevant data from the latest information sources based on user interests. This process employs machine learning algorithms to create personalized content for the user.

[0306] The generated information is updated in real time and sent from the server to the display terminal. This terminal is built using React Native and displays content to the user through an efficient user interface.

[0307] The user can provide feedback on the displayed content, and the server uses this feedback to optimize the prompts of the generative AI model and improve the accuracy of information generation for subsequent times.

[0308] As a specific example, if a user who commutes by train uses an app on their smartphone and is interested in sports and technology, by browsing relevant latest articles and videos and evaluating them as "useful", this feedback will be reflected in the next content generation. Also, as an example of a prompt sentence, "Summarize and display the latest technology articles and sports news that match the user's interests. Please add eye-catching headings to important information." can make the generative AI model operate appropriately.

[0309] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0310] Step 1:

[0311] The server receives the user's interesting content as input and stores it as data in the storage device. Specifically, when the user selects categories such as sports or technology, that information is sent to the server.

[0312] Step 2:

[0313] [[ID=*31]]The server analyzes the action history information stored in the storage device. Here, Pandas is used to aggregate the past action history and perform a process to detect changes in interests. The input is the action history information, and the output is data indicating the detected changes in interests.

[0314] Step 3:

[0315] The server automatically generates information using natural language processing techniques with a generative AI model. Specifically, it utilizes the Transformers library to extract relevant information from information sources based on past behavioral history data and current interests, and outputs it as a summary. The input consists of data on interests and related information sources.

[0316] Step 4:

[0317] The server sends the generated information to the display device. The device, built with React Native, provides the information to the user by displaying the automatically generated content. Specifically, a summary of the information is visually displayed on the user interface.

[0318] Step 5:

[0319] Users provide feedback on the displayed content and send this feedback to the server. The input is the user's feedback, and the output is the data necessary for improving accuracy. Based on the feedback, the prompts of the generated AI model are optimized.

[0320] Step 6:

[0321] The server readjusts the generative AI model for the next information generation. Specifically, prompts are updated based on new user feedback, improving accuracy in subsequent information generation. This is a process of refining the model's behavior using feedback.

[0322] 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.

[0323] This invention embodies a system that provides information based on the user's interests and emotional state. This system generates and displays personalized content by exchanging data and information between the server, terminal, and user.

[0324] Specifically, users can indirectly communicate their emotions at any given time by selecting categories of interest and providing feedback via their device. The server receives this input data and stores it in a data storage device. The server also has an emotion engine that analyzes the user's behavioral history and emotional information to identify the user's current emotional state.

[0325] The emotion engine identifies the emotions a user feels while viewing information, based on user input data and past behavioral history. This emotion information is used by a generation mechanism along with regular interest data. The generation mechanism automatically generates information from the latest information resources in a way that matches the user's interests and emotions, and then adjusts or optimizes the content. As a result, personalized content that is more relevant to the user and also responds to their emotional state is generated.

[0326] For example, if the emotion engine identifies that a user has positive feelings towards "sports" as a category, the server will generate positive news and articles that will attract the user's interest. The generated content is sent to the user's device, where the user can view it. In this way, the server can provide optimal information based on the user's emotions and interests.

[0327] Throughout this entire system, users can not only efficiently gather the information they need, but also enjoy a highly satisfying experience that takes their emotions into consideration.

[0328] The following describes the processing flow.

[0329] Step 1:

[0330] The user selects categories of interest on their device (for example, "News," "Entertainment," "Sports," etc.). This information is sent to the server via the device.

[0331] Step 2:

[0332] The server stores the received category data in the data storage device. This records each user's interests.

[0333] Step 3:

[0334] The device provides indirect feedback about the user's emotions by sending information such as user actions, comments, and browsing speed to the emotion engine.

[0335] Step 4:

[0336] The server uses an emotion engine to analyze user input data and behavioral history to identify the user's current emotional state. This emotional information reflects the emotions the user is experiencing while using the content.

[0337] Step 5:

[0338] The server collects the latest information resources from the web and databases. These resources include news articles, video content, and blog posts.

[0339] Step 6:

[0340] The server uses generation means to automatically generate content based on the user's interests and emotions from collected information resources, and then adjusts or optimizes the content.

[0341] Step 7:

[0342] The generated personalized content is sent from the server to the user's device.

[0343] Step 8:

[0344] The device displays the received content to the user, making it available for viewing and reading.

[0345] Step 9:

[0346] Users can provide feedback after viewing the content. This feedback will be used to improve future content and its accuracy.

[0347] Step 10:

[0348] The server incorporates new user feedback into the learning of its emotion engine and generation methods, helping to create more refined content. This allows the system to improve user satisfaction over time.

[0349] (Example 2)

[0350] 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".

[0351] In modern information delivery systems, providing information quickly and appropriately optimized based on users' interests and emotions is a challenging task. Existing systems often only consider users' interests, and there are limitations to personalization that utilizes emotional states. Therefore, it is necessary to achieve information delivery that is more satisfying for users.

[0352] 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.

[0353] In this invention, the server includes means for receiving interest information and emotional information from a user and storing the information in a storage device, means for analyzing the user's behavioral history data and emotional data to identify changes in interest and emotional state, and means for automatically generating information based on the user's interests and emotions from the latest information sources using generation means. This makes it possible to provide users with information that is more relevant and also corresponds to their emotional state.

[0354] "Service provider equipment" refers to a combination of hardware and software that constitutes a system for providing services to users.

[0355] "Users" refer to those who receive information or provide feedback through this system.

[0356] "Interest information" refers to data that represents the user's interest in a particular field or topic.

[0357] "Emotional information" refers to data that indicates the user's psychological state, such as emotions like positive, negative, or neutral.

[0358] A "storage device" is a device used to store digital information and is used to temporarily or permanently retain received data.

[0359] "Behavioral history data" refers to a dataset that includes records of actions and choices that users have made in the past.

[0360] "Analysis" is the process of processing received data statistically or algorithmically to derive useful information or patterns.

[0361] "Generative means" refers to the processes or technologies used to form and output information based on the user's interests and emotions.

[0362] "Information source" refers to the place or medium from which data or content used by a system to provide to users is transmitted.

[0363] "Automatic generation" refers to a system creating information based on specified conditions without human intervention.

[0364] "Terminal device" refers to a device used by a user to access a service, and includes computers, smartphones, tablets, and other similar devices.

[0365] In implementing this invention, the system mainly consists of a server, a terminal, and a user.

[0366] The server, as part of the service provider's equipment, receives interest and emotion information from users. This information is stored in a data storage device, such as a database. The server uses an emotion analysis engine developed with machine learning libraries such as "TensorFlow" and "Python" to analyze the user's behavioral history data and current emotion information. It then identifies the user's emotional state. Based on the changes in interest and emotional state identified through this analysis, a generative AI model is used to construct new information. In this generation process, natural language processing technology is utilized to select content that matches the user's interests and emotions, and to automatically generate optimized information.

[0367] For example, if a user selects the "Sports" category and submits positive emotional information, the server processes this information through its sentiment analysis engine and generates positive and up-to-date sports news that is best suited to the user's state. An example of a prompt for this generating AI model is as follows:

[0368] Prompt: Please provide the latest and most positive sports news that will attract users when they are feeling positive emotions.

[0369] The device receives generated information sent from the server and displays it in a format viewable by the user. This allows users to experience content optimized to their interests and emotions.

[0370] Users send their interests and emotions to the system via their devices, providing feedback. This feedback is collected by the server and used to improve the accuracy of the generation process.

[0371] Therefore, this system can provide users with information that is highly relevant and emotionally resonant.

[0372] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0373] Step 1:

[0374] Users select their interest categories through their device and provide emotional feedback. This input information is sent from the device to the server.

[0375] Step 2:

[0376] The server stores interest categories and emotional information received from the terminal in its storage device. The input data includes categories selected by the user and feedback indicating their emotional state. Based on this, an entry is created in the database, and the user profile is updated.

[0377] Step 3:

[0378] The server uses an emotion analysis engine to analyze the user's past behavioral history data and newly received emotion information. Based on the received data, a process is initiated to identify the user's emotional state. This analysis identifies what the user wants and what information is appropriate for them.

[0379] Step 4:

[0380] The server uses a generative AI model as a generation tool to automatically generate content based on identified emotional states and interests. Input includes the user's current interests and emotional information, and output is personalized news articles and information. Generation prompts are input to the AI ​​model to generate information relevant to the user.

[0381] Step 5:

[0382] The server sends the generated content to the device. The transmitted data is converted to the optimal format on the device and displayed. The device then provides the user with the generated personalized content, which the user can view.

[0383] Step 6:

[0384] The user provides feedback on the displayed content. The device sends this feedback back to the server. This feedback is used by the server as training data to improve the accuracy of the generation method.

[0385] (Application Example 2)

[0386] 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."

[0387] In today's information-saturated age, users face the challenge of efficiently obtaining information optimized for their interests and emotions. Traditionally, information provision systems have provided information based on user interests, but have failed to provide appropriate information that takes into account the user's emotional state. As a result, user satisfaction has decreased, and the efficiency of information consumption has been impaired.

[0388] 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.

[0389] In this invention, the server includes means for receiving user interest information and storing it in a data storage device, means for analyzing user behavior history data and detecting changes in interests, means equipped with an emotion analysis engine for analyzing and identifying the user's emotional state, means for automatically generating information from the latest information resources based on the user's interests and emotional state using generation means, and means for transmitting and displaying the generated information to the user's terminal device. This makes it possible to accurately provide information that matches the user's interests and emotions, thereby improving user satisfaction and increasing the efficiency of information consumption.

[0390] A "service provider system" is a system that has a mechanism for receiving data from users and processing, storing, and analyzing that data.

[0391] A "data storage device" is a device for safely and efficiently recording and storing received data.

[0392] "Analyzing behavioral history data" refers to analyzing a user's past behavioral data to derive changes and trends in their interests and preferences.

[0393] An "emotion analysis engine" is a processing unit or program that identifies a user's current emotional state based on the user's input data and behavioral history.

[0394] "Generation means" refers to a technology or process for automatically generating up-to-date information based on the user's interests, concerns, and emotional state.

[0395] "Terminal devices" refer to various types of equipment (such as smartphones, tablets, and computers) that users use to receive and manipulate information.

[0396] "Feedback" refers to the responses or reactions that users provide to a system, and is used to improve the quality of the information generated.

[0397] This invention relates to the realization of an advanced personalized system that provides information based on the user's interests and emotions. The following is an example of how to specifically implement this invention.

[0398] The server first receives interest information from users and stores it in a data storage device. This step securely stores the data using a storage system located on a cloud platform (e.g., Amazon S3). The server also collects and analyzes user behavior history data. Data analysis tools (e.g., Google Analytics) are used for this analysis. This allows for understanding changes in user interests.

[0399] Furthermore, the server uses an emotion analysis engine to identify the user's emotional state. This analysis utilizes an emotion analysis API (e.g., Microsoft Azure Emotion API) that leverages natural language processing technology. The results are then integrated with the user's interest data.

[0400] Next, the server uses a generation mechanism to generate information that matches the user's interests and emotional state. In this step, a generation AI model (e.g., GPT-3) is utilized to automatically generate and adjust content that is optimal for the user.

[0401] The generated content is sent to the user's device. This device may be a smartphone or tablet, and the user can view the content on these devices. This allows users to efficiently obtain information that is tailored to their interests and emotions.

[0402] For example, if a user selects the "Movies" category and indicates a desire to refresh, the server will generate and send information about new comedy movies and positive review articles. An example of a prompt in response to this would be: "The user is interested in recent movie news and is looking for something relaxing. Please suggest appropriate movie reviews and new release information."

[0403] This system allows users to receive information tailored to their interests and emotions, enabling a highly satisfying information experience.

[0404] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0405] Step 1:

[0406] Users input interest information and feedback using their devices. For example, a user might select the category "movies" and input a feeling such as "feeling happy." This input data is then sent from the device to the server.

[0407] Step 2:

[0408] The server stores the received interest information and feedback in a data storage device. The data is stored in a cloud storage system. This ensures that the data necessary for analysis in subsequent processing is securely retained.

[0409] Step 3:

[0410] The server analyzes the stored behavioral history data. Using data analysis tools such as Google Analytics, it detects changes in the user's interests. During this process, aggregation and trend analysis are performed based on the user's past behavioral data.

[0411] Step 4:

[0412] The server uses an emotion analysis engine to identify the user's emotional state. Based on the input data, it analyzes emotions using the Microsoft Azure Emotion API and extracts specific emotional states. This result is then used in subsequent information generation processes.

[0413] Step 5:

[0414] The server utilizes a generative AI model as a generation tool to automatically generate content based on the user's interests and emotions. For example, it inputs prompt text into an OpenAI GPT-3 model to generate information and articles best suited to the user. At this stage, the content and format of the generated text are optimized.

[0415] Step 6:

[0416] The generated content is sent from the server to the user's device. The user can view the information on their device and, as a result, consume the provided content. This improves user satisfaction and the efficiency of information consumption.

[0417] 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.

[0418] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0419] 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.

[0420] [Third Embodiment]

[0421] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0422] 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.

[0423] 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).

[0424] 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.

[0425] 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.

[0426] 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).

[0427] 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.

[0428] 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.

[0429] 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.

[0430] 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.

[0431] 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.

[0432] 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".

[0433] This invention provides a system that efficiently delivers information based on user interests. The system described below embodies a method for exchanging information between a server, a terminal, and a user, and for generating and displaying personalized content to the user.

[0434] The server first receives category data from the user indicating their interests. For example, if a user selects the categories "Sports" and "Technology" on their device, the server stores that information in a data storage device. Furthermore, the server collects and analyzes the user's past behavioral history to identify how the user's interests have changed based on this information.

[0435] The server then collects content from the latest information resources and generates information based on the user's interests using generation methods. This involves leveraging natural language processing techniques to extract and summarize user-relevant information from a vast dataset. The generated information is updated in real time and sent to the user's device at the appropriate time. The device displays this content to the user, allowing them to quickly digest information that interests them.

[0436] Furthermore, users can submit feedback on the displayed content. The server uses this feedback to improve the accuracy of its content generation methods. For example, if a user rates a particular news article as "useful," the server uses this information to improve future content generation, thereby enhancing the quality of information provided to individual users.

[0437] As a result, users can obtain the necessary information in an appropriate format, reducing fatigue caused by information overload. Through this system, information provision to users becomes more personalized, enabling it to meet diverse needs.

[0438] The following describes the processing flow.

[0439] Step 1:

[0440] The user selects categories of interest on their device. These selections include categories such as entertainment, sports, and technology. The device then sends the selected category information to the server.

[0441] Step 2:

[0442] The server stores the received category information in a data storage device. This enables the provision of information based on the user's interests in subsequent processing.

[0443] Step 3:

[0444] The server periodically analyzes user behavior history data. This includes information such as content the user has viewed in the past and links they have clicked. Based on the analysis results, changes in the user's interests are detected.

[0445] Step 4:

[0446] The server collects the latest information resources, such as news articles and blog posts. To do this, it gathers information from web databases via scraping or APIs.

[0447] Step 5:

[0448] The server analyzes the collected information resources using natural language processing technology and summarizes and reorganizes content related to the user's selected category. Information tailored to the user is automatically generated by the generation mechanism.

[0449] Step 6:

[0450] The server sends the generated personalized content to the user's device. The device displays the received content in a format that the user can view.

[0451] Step 7:

[0452] Users view the content they receive and provide feedback on the information provided. This feedback includes opinions such as "helpful" or "not interesting."

[0453] Step 8:

[0454] The server receives feedback from users and uses it as data to improve the generation process. This will enable the provision of more accurate information in the future, thereby improving user satisfaction.

[0455] (Example 1)

[0456] 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."

[0457] In modern society, the overwhelming amount of information available makes it difficult for users to efficiently select and understand information relevant to them. Therefore, there is a need for a system that efficiently provides personalized information based on users' interests. Furthermore, it is challenging to flexibly respond to changes in users' interests and continuously improve the accuracy of information provided.

[0458] 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.

[0459] In this invention, the server includes means for acquiring interest information from the user and storing the information on a recording medium, means for analyzing the user's past operation history and identifying changes in interest, and means for utilizing automated information generation means to generate data based on the user's interests from the latest information sources. This makes it possible to provide users with personalized information, reduce fatigue caused by information overload, and meet the diverse needs of the user.

[0460] "Interest information" refers to information about specific fields or themes that users are interested in. This information is derived from the user's choices and actions.

[0461] "Recording media" refers to physical or electronic devices or infrastructure used to store data and information. This includes databases and server storage.

[0462] "Operation history" refers to a record of a series of actions and choices made by a user when using a system or device. This history is used to analyze user behavior patterns.

[0463] "To identify" refers to the process of identifying and clarifying specific elements or characteristics based on given information or data.

[0464] "Automated information generation methods" refer to processes that generate information without manual intervention using algorithms and models. This particularly involves the use of machine learning and natural language processing technologies.

[0465] "Source" refers to the data stream, website, or other information-providing platform from which information is obtained.

[0466] "Generating data" refers to the process of creating new information based on existing information. This allows for the provision of specialized information tailored to the user's needs and conditions.

[0467] This invention provides a system that enables the personalization of information based on user interests through the mutual cooperation of servers, terminals, and users.

[0468] The server first uses a data storage device to receive interest information sent by the user and stores it on a recording medium. Databases such as MySQL or MongoDB are used for this process. Next, the server collects the user's activity history and uses analysis software to identify changes in interest. Data processing libraries such as Python's Pandas and NumPy are used for this analysis.

[0469] The server further utilizes a generative AI model as an automated means of generating information. For this model, OpenAI models are available to implement natural language processing technology. The server retrieves data from the latest information sources and uses text such as "The user's interest categories are 'Environment' and 'Science.' Please summarize the latest news and articles related to these fields" as prompts to input into the generative AI model. Based on these prompts, the AI ​​model generates data relevant to the user.

[0470] The generated information is immediately sent from the server to the terminal. The terminal receives the information in real time using protocols such as WebSocket or HTTP and displays it to the user. The user can provide various evaluation feedback on the displayed information. This feedback is sent back to the server and used to improve the accuracy of the generation method. Specifically, if the user evaluates "this information is useful," that feedback is used to adjust the generation AI model, enabling the provision of more precise information.

[0471] In this way, the entire system works in coordination, allowing users to receive accurate information without being overwhelmed by excessive information. The introduction of this system enables users to acquire necessary information with high efficiency, reducing the burden caused by information overload.

[0472] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0473] Step 1:

[0474] The user enters categories of interest on their device. For example, the user might check "Sports" or "Technology" from the application's interface. This action is a user selection, and the output is the selected category information. This category information forms the basis for subsequent data processing.

[0475] Step 2:

[0476] The device sends category information of interest selected by the user to the server. Specifically, it uses an HTTP request to send category information to the server's API. The input to this request is the category information selected by the user, and the output is data stored on the server. The server stores the received information in a database and saves this data to a storage medium.

[0477] Step 3:

[0478] The server retrieves and analyzes user activity history from the database. The input here is existing activity history data. The server uses tools such as Python's Pandas library to analyze this data and identify changes in user interests. The output obtained through this analysis is detailed data regarding changes in interests.

[0479] Step 4:

[0480] The server uses automated information generation methods to generate up-to-date information based on the user's category information. The input here consists of pre-collected category information and the results of past behavioral history analysis. The generating AI model is given a prompt such as, "The user's interest categories are 'Environment' and 'Science.' Please summarize the latest news and articles that match these categories." The output of this process is summary information tailored to the user's interests.

[0481] Step 5:

[0482] The generated information is sent from the server to the terminal in real time. The input is the summary information generated in step 4. The terminal receives this information via WebSocket or HTTP and displays it to the user in an easy-to-read format using a display device. The output is the information presented visually.

[0483] Step 6:

[0484] Users can evaluate the displayed information. Specifically, they send feedback such as "helpful" or "not interesting" to the server via an interface on their device. This feedback input is the user's evaluation. The server uses the received feedback to readjust the AI ​​model to improve the accuracy of the generation method. The output is the performance of the improved AI model.

[0485] Through this series of processing steps, the system provides users with efficient, accurate, and personalized information.

[0486] (Application Example 1)

[0487] 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."

[0488] In modern society, the sheer volume of information presents a challenge, making it difficult for users to quickly and effectively obtain the information they need. Furthermore, existing methods fail to adequately deliver information based on users' interests, resulting in limited personalized content delivery.

[0489] 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.

[0490] In this invention, the server includes means for the service provider's equipment to receive interest information from the user and store the information in a storage device, means for analyzing the user's behavioral history information and detecting changes in interests, and means for automatically generating information based on the user's interests from the latest information sources in order to generate information. This makes it possible to update the information provided to the user in real time, optimize the generation AI model by utilizing feedback, and efficiently provide personalized content.

[0491] "Service provider equipment" refers to the hardware or software used to receive interest information from users and store it in data storage.

[0492] "Interests" refers to information about categories or topics that users are particularly interested in.

[0493] A "storage device" is a device or system for storing digital data for the long term.

[0494] "Behavioral history information" refers to a record of information resources that a user has accessed and used in the past.

[0495] "Changes in interests" refers to a state in which a user's interests fluctuate over time or due to information acquisition.

[0496] "Information sources" refer to public or private resources that provide up-to-date data and information.

[0497] "Means of automatically generating information" refers to the process of automatically creating relevant information using algorithms and models based on the user's interests.

[0498] A "display device" is a device that provides generated information to the user visually.

[0499] A "generative AI model" refers to an artificial intelligence algorithm built to generate appropriate output based on user input.

[0500] "Feedback" refers to the evaluations and impressions that users give to the content provided, and is used to improve the personalization accuracy of the system.

[0501] The system for implementing this invention mainly consists of a server, a display terminal, and a user. The server first receives the user's interests and stores them in a storage device. At this time, the server analyzes the user's behavioral history information and identifies changes in interests. Python or Pandas is used to aggregate and analyze the data.

[0502] The server then utilizes a generative AI model to generate information. Using the Transformers library as a natural language processing technique, it automatically generates relevant data from the latest information sources based on user interests. This process employs machine learning algorithms to create personalized content for the user.

[0503] The generated information is updated in real time and sent from the server to the display terminal. This terminal is built using React Native and displays the content to the user through an efficient user interface.

[0504] Users can provide feedback on the displayed content, and the server uses this feedback to optimize the prompts of the generating AI model, improving the accuracy of information generation in the future.

[0505] For example, if a user who commutes by train uses the app on their smartphone and is interested in sports and technology, they can view the latest relevant articles and videos and rate them as "useful," and this feedback will be reflected in future content generation. Furthermore, a prompt such as, "Summarize and display the latest technology articles and sports news tailored to the user's interests. Use eye-catching headlines for important information," will ensure the generation AI model functions correctly.

[0506] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0507] Step 1:

[0508] The server receives user interest information as input and stores it as data in a storage device. Specifically, when a user selects a category such as sports or technology, that information is sent to the server.

[0509] Step 2:

[0510] The server analyzes behavioral history information stored on the storage device. Here, Pandas is used to aggregate past behavioral history and detect changes in interests. The input is behavioral history information, and the output is data showing the detected changes in interests.

[0511] Step 3:

[0512] The server automatically generates information using natural language processing techniques with a generative AI model. Specifically, it utilizes the Transformers library to extract relevant information from information sources based on past behavioral history data and current interests, and outputs it as a summary. The input consists of data on interests and related information sources.

[0513] Step 4:

[0514] The server sends the generated information to the display device. The device, built with React Native, provides the information to the user by displaying the automatically generated content. Specifically, a summary of the information is visually displayed on the user interface.

[0515] Step 5:

[0516] Users provide feedback on the displayed content and send this feedback to the server. The input is the user's feedback, and the output is the data necessary for improving accuracy. Based on the feedback, the prompts of the generated AI model are optimized.

[0517] Step 6:

[0518] The server readjusts the generative AI model for the next information generation. Specifically, prompts are updated based on new user feedback, improving accuracy in subsequent information generation. This is a process of refining the model's behavior using feedback.

[0519] 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.

[0520] This invention embodies a system that provides information based on the user's interests and emotional state. This system generates and displays personalized content by exchanging data and information between the server, terminal, and user.

[0521] Specifically, users can indirectly communicate their emotions at any given time by selecting categories of interest and providing feedback via their device. The server receives this input data and stores it in a data storage device. The server also has an emotion engine that analyzes the user's behavioral history and emotional information to identify the user's current emotional state.

[0522] The emotion engine identifies the emotions a user feels while viewing information, based on user input data and past behavioral history. This emotion information is used by a generation mechanism along with regular interest data. The generation mechanism automatically generates information from the latest information resources in a way that matches the user's interests and emotions, and then adjusts or optimizes the content. As a result, personalized content that is more relevant to the user and also responds to their emotional state is generated.

[0523] For example, if the emotion engine identifies that a user has positive feelings towards "sports" as a category, the server will generate positive news and articles that will attract the user's interest. The generated content is sent to the user's device, where the user can view it. In this way, the server can provide optimal information based on the user's emotions and interests.

[0524] Throughout this entire system, users can not only efficiently gather the information they need, but also enjoy a highly satisfying experience that takes their emotions into consideration.

[0525] The following describes the processing flow.

[0526] Step 1:

[0527] The user selects categories of interest on their device (for example, "News," "Entertainment," "Sports," etc.). This information is sent to the server via the device.

[0528] Step 2:

[0529] The server stores the received category data in the data storage device. This records each user's interests.

[0530] Step 3:

[0531] The device provides indirect feedback about the user's emotions by sending information such as user actions, comments, and browsing speed to the emotion engine.

[0532] Step 4:

[0533] The server uses an emotion engine to analyze user input data and behavioral history to identify the user's current emotional state. This emotional information reflects the emotions the user is experiencing while using the content.

[0534] Step 5:

[0535] The server collects the latest information resources from the web and databases. These resources include news articles, video content, and blog posts.

[0536] Step 6:

[0537] The server uses generation means to automatically generate content based on the user's interests and emotions from collected information resources, and then adjusts or optimizes the content.

[0538] Step 7:

[0539] The generated personalized content is sent from the server to the user's device.

[0540] Step 8:

[0541] The device displays the received content to the user, making it available for viewing and reading.

[0542] Step 9:

[0543] Users can provide feedback after viewing the content. This feedback will be used to improve future content and its accuracy.

[0544] Step 10:

[0545] The server incorporates new user feedback into the learning of its emotion engine and generation methods, helping to create more refined content. This allows the system to improve user satisfaction over time.

[0546] (Example 2)

[0547] 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."

[0548] In modern information delivery systems, providing information quickly and appropriately optimized based on users' interests and emotions is a challenging task. Existing systems often only consider users' interests, and there are limitations to personalization that utilizes emotional states. Therefore, it is necessary to achieve information delivery that is more satisfying for users.

[0549] 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.

[0550] In this invention, the server includes means for receiving interest information and emotional information from a user and storing the information in a storage device, means for analyzing the user's behavioral history data and emotional data to identify changes in interest and emotional state, and means for automatically generating information based on the user's interests and emotions from the latest information sources using generation means. This makes it possible to provide users with information that is more relevant and also corresponds to their emotional state.

[0551] "Service provider equipment" refers to a combination of hardware and software that constitutes a system for providing services to users.

[0552] "Users" refer to those who receive information or provide feedback through this system.

[0553] "Interest information" refers to data that represents the user's interest in a particular field or topic.

[0554] "Emotional information" refers to data that indicates the user's psychological state, such as emotions like positive, negative, or neutral.

[0555] A "storage device" is a device used to store digital information and is used to temporarily or permanently retain received data.

[0556] "Behavioral history data" refers to a dataset that includes records of actions and choices that users have made in the past.

[0557] "Analysis" is the process of processing received data statistically or algorithmically to derive useful information or patterns.

[0558] "Generative means" refers to the processes or technologies used to form and output information based on the user's interests and emotions.

[0559] "Information source" refers to the place or medium from which data or content used by a system to provide to users is transmitted.

[0560] "Automatic generation" refers to a system creating information based on specified conditions without human intervention.

[0561] "Terminal device" refers to a device used by a user to access a service, and includes computers, smartphones, tablets, and other similar devices.

[0562] In implementing this invention, the system mainly consists of a server, a terminal, and a user.

[0563] The server, as part of the service provider's equipment, receives interest and emotion information from users. This information is stored in a data storage device, such as a database. The server uses an emotion analysis engine developed with machine learning libraries such as "TensorFlow" and "Python" to analyze the user's behavioral history data and current emotion information. It then identifies the user's emotional state. Based on the changes in interest and emotional state identified through this analysis, a generative AI model is used to construct new information. In this generation process, natural language processing technology is utilized to select content that matches the user's interests and emotions, and to automatically generate optimized information.

[0564] For example, if a user selects the "Sports" category and submits positive emotional information, the server processes this information through its sentiment analysis engine and generates positive and up-to-date sports news that is best suited to the user's state. An example of a prompt for this generating AI model is as follows:

[0565] Prompt: Please provide the latest and most positive sports news that will attract users when they are feeling positive emotions.

[0566] The device receives generated information sent from the server and displays it in a format viewable by the user. This allows users to experience content optimized to their interests and emotions.

[0567] Users send their interests and emotions to the system via their devices, providing feedback. This feedback is collected by the server and used to improve the accuracy of the generation process.

[0568] Therefore, this system can provide users with information that is highly relevant and emotionally resonant.

[0569] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0570] Step 1:

[0571] Users select their interest categories through their device and provide emotional feedback. This input information is sent from the device to the server.

[0572] Step 2:

[0573] The server stores interest categories and emotional information received from the terminal in its storage device. The input data includes categories selected by the user and feedback indicating their emotional state. Based on this, an entry is created in the database, and the user profile is updated.

[0574] Step 3:

[0575] The server uses an emotion analysis engine to analyze the user's past behavioral history data and newly received emotion information. Based on the received data, a process is initiated to identify the user's emotional state. This analysis identifies what the user wants and what information is appropriate for them.

[0576] Step 4:

[0577] The server uses a generative AI model as a generation tool to automatically generate content based on identified emotional states and interests. Input includes the user's current interests and emotional information, and output is personalized news articles and information. Generation prompts are input to the AI ​​model to generate information relevant to the user.

[0578] Step 5:

[0579] The server sends the generated content to the device. The transmitted data is converted to the optimal format on the device and displayed. The device then provides the user with the generated personalized content, which the user can view.

[0580] Step 6:

[0581] The user provides feedback on the displayed content. The device sends this feedback back to the server. This feedback is used by the server as training data to improve the accuracy of the generation method.

[0582] (Application Example 2)

[0583] 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."

[0584] In today's information-saturated age, users face the challenge of efficiently obtaining information optimized for their interests and emotions. Traditionally, information provision systems have provided information based on user interests, but have failed to provide appropriate information that takes into account the user's emotional state. As a result, user satisfaction has decreased, and the efficiency of information consumption has been impaired.

[0585] 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.

[0586] In this invention, the server includes means for receiving user interest information and storing it in a data storage device, means for analyzing user behavior history data and detecting changes in interests, means equipped with an emotion analysis engine for analyzing and identifying the user's emotional state, means for automatically generating information from the latest information resources based on the user's interests and emotional state using generation means, and means for transmitting and displaying the generated information to the user's terminal device. This makes it possible to accurately provide information that matches the user's interests and emotions, thereby improving user satisfaction and increasing the efficiency of information consumption.

[0587] A "service provider system" is a system that has a mechanism for receiving data from users and processing, storing, and analyzing that data.

[0588] A "data storage device" is a device for safely and efficiently recording and storing received data.

[0589] "Analyzing behavioral history data" refers to analyzing a user's past behavioral data to derive changes and trends in their interests and preferences.

[0590] An "emotion analysis engine" is a processing unit or program that identifies a user's current emotional state based on the user's input data and behavioral history.

[0591] "Generation means" refers to a technology or process for automatically generating up-to-date information based on the user's interests, concerns, and emotional state.

[0592] "Terminal devices" refer to various types of equipment (such as smartphones, tablets, and computers) that users use to receive and manipulate information.

[0593] "Feedback" refers to the responses or reactions that users provide to a system, and is used to improve the quality of the information generated.

[0594] This invention relates to the realization of an advanced personalized system that provides information based on the user's interests and emotions. The following is an example of how to specifically implement this invention.

[0595] The server first receives interest information from users and stores it in a data storage device. This step securely stores the data using a storage system located on a cloud platform (e.g., Amazon S3). The server also collects and analyzes user behavior history data. Data analysis tools (e.g., Google Analytics) are used for this analysis. This allows for understanding changes in user interests.

[0596] Furthermore, the server uses an emotion analysis engine to identify the user's emotional state. This analysis utilizes an emotion analysis API (e.g., Microsoft Azure Emotion API) that leverages natural language processing technology. The results are then integrated with the user's interest data.

[0597] Next, the server uses a generation mechanism to generate information that matches the user's interests and emotional state. In this step, a generation AI model (e.g., GPT-3) is utilized to automatically generate and adjust content that is optimal for the user.

[0598] The generated content is sent to the user's device. This device may be a smartphone or tablet, and the user can view the content on these devices. This allows users to efficiently obtain information that is tailored to their interests and emotions.

[0599] For example, if a user selects the "Movies" category and indicates a desire to refresh, the server will generate and send information about new comedy movies and positive review articles. An example of a prompt in response to this would be: "The user is interested in recent movie news and is looking for something relaxing. Please suggest appropriate movie reviews and new release information."

[0600] This system allows users to receive information tailored to their interests and emotions, enabling a highly satisfying information experience.

[0601] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0602] Step 1:

[0603] Users input interest information and feedback using their devices. For example, a user might select the category "movies" and input a feeling such as "feeling happy." This input data is then sent from the device to the server.

[0604] Step 2:

[0605] The server stores the received interest information and feedback in a data storage device. The data is stored in a cloud storage system. This ensures that the data necessary for analysis in subsequent processing is securely retained.

[0606] Step 3:

[0607] The server analyzes the stored behavioral history data. Using data analysis tools such as Google Analytics, it detects changes in the user's interests. During this process, aggregation and trend analysis are performed based on the user's past behavioral data.

[0608] Step 4:

[0609] The server uses an emotion analysis engine to identify the user's emotional state. Based on the input data, it analyzes emotions using the Microsoft Azure Emotion API and extracts specific emotional states. This result is then used in subsequent information generation processes.

[0610] Step 5:

[0611] The server utilizes a generative AI model as a generation tool to automatically generate content based on the user's interests and emotions. For example, it inputs prompt text into an OpenAI GPT-3 model to generate information and articles best suited to the user. At this stage, the content and format of the generated text are optimized.

[0612] Step 6:

[0613] The generated content is sent from the server to the user's device. The user can view the information on their device and, as a result, consume the provided content. This improves user satisfaction and the efficiency of information consumption.

[0614] 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.

[0615] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0616] 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.

[0617] [Fourth Embodiment]

[0618] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0619] 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.

[0620] 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).

[0621] 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.

[0622] 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.

[0623] 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).

[0624] 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.

[0625] 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.

[0626] 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.

[0627] 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.

[0628] 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.

[0629] 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.

[0630] 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".

[0631] This invention provides a system that efficiently delivers information based on user interests. The system described below embodies a method for exchanging information between a server, a terminal, and a user, and for generating and displaying personalized content to the user.

[0632] The server first receives category data from the user indicating their interests. For example, if a user selects the categories "Sports" and "Technology" on their device, the server stores that information in a data storage device. Furthermore, the server collects and analyzes the user's past behavioral history to identify how the user's interests have changed based on this information.

[0633] The server then collects content from the latest information resources and generates information based on the user's interests using generation methods. This involves leveraging natural language processing techniques to extract and summarize user-relevant information from a vast dataset. The generated information is updated in real time and sent to the user's device at the appropriate time. The device displays this content to the user, allowing them to quickly digest information that interests them.

[0634] Furthermore, users can submit feedback on the displayed content. The server uses this feedback to improve the accuracy of its content generation methods. For example, if a user rates a particular news article as "useful," the server uses this information to improve future content generation, thereby enhancing the quality of information provided to individual users.

[0635] As a result, users can obtain the necessary information in an appropriate format, reducing fatigue caused by information overload. Through this system, information provision to users becomes more personalized, enabling it to meet diverse needs.

[0636] The following describes the processing flow.

[0637] Step 1:

[0638] The user selects categories of interest on their device. These selections include categories such as entertainment, sports, and technology. The device then sends the selected category information to the server.

[0639] Step 2:

[0640] The server stores the received category information in a data storage device. This enables the provision of information based on the user's interests in subsequent processing.

[0641] Step 3:

[0642] The server periodically analyzes user behavior history data. This includes information such as content the user has viewed in the past and links they have clicked. Based on the analysis results, changes in the user's interests are detected.

[0643] Step 4:

[0644] The server collects the latest information resources, such as news articles and blog posts. To do this, it gathers information from web databases via scraping or APIs.

[0645] Step 5:

[0646] The server analyzes the collected information resources using natural language processing technology and summarizes and reorganizes content related to the user's selected category. Information tailored to the user is automatically generated by the generation mechanism.

[0647] Step 6:

[0648] The server sends the generated personalized content to the user's device. The device displays the received content in a format that the user can view.

[0649] Step 7:

[0650] Users view the content they receive and provide feedback on the information provided. This feedback includes opinions such as "helpful" or "not interesting."

[0651] Step 8:

[0652] The server receives feedback from users and uses it as data to improve the generation process. This will enable the provision of more accurate information in the future, thereby improving user satisfaction.

[0653] (Example 1)

[0654] 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".

[0655] In modern society, the overwhelming amount of information available makes it difficult for users to efficiently select and understand information relevant to them. Therefore, there is a need for a system that efficiently provides personalized information based on users' interests. Furthermore, it is challenging to flexibly respond to changes in users' interests and continuously improve the accuracy of information provided.

[0656] 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.

[0657] In this invention, the server includes means for acquiring interest information from the user and storing the information on a recording medium, means for analyzing the user's past operation history and identifying changes in interest, and means for utilizing automated information generation means to generate data based on the user's interests from the latest information sources. This makes it possible to provide users with personalized information, reduce fatigue caused by information overload, and meet the diverse needs of the user.

[0658] "Interest information" refers to information about specific fields or themes that users are interested in. This information is derived from the user's choices and actions.

[0659] "Recording media" refers to physical or electronic devices or infrastructure used to store data and information. This includes databases and server storage.

[0660] "Operation history" refers to a record of a series of actions and choices made by a user when using a system or device. This history is used to analyze user behavior patterns.

[0661] "To identify" refers to the process of identifying and clarifying specific elements or characteristics based on given information or data.

[0662] "Automated information generation methods" refer to processes that generate information without manual intervention using algorithms and models. This particularly involves the use of machine learning and natural language processing technologies.

[0663] "Source" refers to the data stream, website, or other information-providing platform from which information is obtained.

[0664] "Generating data" refers to the process of creating new information based on existing information. This allows for the provision of specialized information tailored to the user's needs and conditions.

[0665] This invention provides a system that enables the personalization of information based on user interests through the mutual cooperation of servers, terminals, and users.

[0666] The server first uses a data storage device to receive interest information sent by the user and stores it on a recording medium. Databases such as MySQL or MongoDB are used for this process. Next, the server collects the user's activity history and uses analysis software to identify changes in interest. Data processing libraries such as Python's Pandas and NumPy are used for this analysis.

[0667] The server further utilizes a generative AI model as an automated means of generating information. For this model, OpenAI models are available to implement natural language processing technology. The server retrieves data from the latest information sources and uses text such as "The user's interest categories are 'Environment' and 'Science.' Please summarize the latest news and articles related to these fields" as prompts to input into the generative AI model. Based on these prompts, the AI ​​model generates data relevant to the user.

[0668] The generated information is immediately sent from the server to the terminal. The terminal receives the information in real time using protocols such as WebSocket or HTTP and displays it to the user. The user can provide various evaluation feedback on the displayed information. This feedback is sent back to the server and used to improve the accuracy of the generation method. Specifically, if the user evaluates "this information is useful," that feedback is used to adjust the generation AI model, enabling the provision of more precise information.

[0669] In this way, the entire system works in coordination, allowing users to receive accurate information without being overwhelmed by excessive information. The introduction of this system enables users to acquire necessary information with high efficiency, reducing the burden caused by information overload.

[0670] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0671] Step 1:

[0672] The user enters categories of interest on their device. For example, the user might check "Sports" or "Technology" from the application's interface. This action is a user selection, and the output is the selected category information. This category information forms the basis for subsequent data processing.

[0673] Step 2:

[0674] The device sends category information of interest selected by the user to the server. Specifically, it uses an HTTP request to send category information to the server's API. The input to this request is the category information selected by the user, and the output is data stored on the server. The server stores the received information in a database and saves this data to a storage medium.

[0675] Step 3:

[0676] The server retrieves and analyzes user activity history from the database. The input here is existing activity history data. The server uses tools such as Python's Pandas library to analyze this data and identify changes in user interests. The output obtained through this analysis is detailed data regarding changes in interests.

[0677] Step 4:

[0678] The server uses automated information generation methods to generate up-to-date information based on the user's category information. The input here consists of pre-collected category information and the results of past behavioral history analysis. The generating AI model is given a prompt such as, "The user's interest categories are 'Environment' and 'Science.' Please summarize the latest news and articles that match these categories." The output of this process is summary information tailored to the user's interests.

[0679] Step 5:

[0680] The generated information is sent from the server to the terminal in real time. The input is the summary information generated in step 4. The terminal receives this information via WebSocket or HTTP and displays it to the user in an easy-to-read format using a display device. The output is the information presented visually.

[0681] Step 6:

[0682] Users can evaluate the displayed information. Specifically, they send feedback such as "helpful" or "not interesting" to the server via an interface on their device. This feedback input is the user's evaluation. The server uses the received feedback to readjust the AI ​​model to improve the accuracy of the generation method. The output is the performance of the improved AI model.

[0683] Through this series of processing steps, the system provides users with efficient, accurate, and personalized information.

[0684] (Application Example 1)

[0685] 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".

[0686] In modern society, the sheer volume of information presents a challenge, making it difficult for users to quickly and effectively obtain the information they need. Furthermore, existing methods fail to adequately deliver information based on users' interests, resulting in limited personalized content delivery.

[0687] 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.

[0688] In this invention, the server includes means for the service provider's equipment to receive interest information from the user and store the information in a storage device, means for analyzing the user's behavioral history information and detecting changes in interests, and means for automatically generating information based on the user's interests from the latest information sources in order to generate information. This makes it possible to update the information provided to the user in real time, optimize the generation AI model by utilizing feedback, and efficiently provide personalized content.

[0689] "Service provider equipment" refers to the hardware or software used to receive interest information from users and store it in data storage.

[0690] "Interests" refers to information about categories or topics that users are particularly interested in.

[0691] A "storage device" is a device or system for storing digital data for the long term.

[0692] "Behavioral history information" refers to a record of information resources that a user has accessed and used in the past.

[0693] "Changes in interests" refers to a state in which a user's interests fluctuate over time or due to information acquisition.

[0694] "Information sources" refer to public or private resources that provide up-to-date data and information.

[0695] "Means of automatically generating information" refers to the process of automatically creating relevant information using algorithms and models based on the user's interests.

[0696] A "display device" is a device that provides generated information to the user visually.

[0697] A "generative AI model" refers to an artificial intelligence algorithm built to generate appropriate output based on user input.

[0698] "Feedback" refers to the evaluations and impressions that users give to the content provided, and is used to improve the personalization accuracy of the system.

[0699] The system for implementing this invention mainly consists of a server, a display terminal, and a user. The server first receives the user's interests and stores them in a storage device. At this time, the server analyzes the user's behavioral history information and identifies changes in interests. Python or Pandas is used to aggregate and analyze the data.

[0700] The server then utilizes a generative AI model to generate information. Using the Transformers library as a natural language processing technique, it automatically generates relevant data from the latest information sources based on user interests. This process employs machine learning algorithms to create personalized content for the user.

[0701] The generated information is updated in real time and sent from the server to the display terminal. This terminal is built using React Native and displays the content to the user through an efficient user interface.

[0702] Users can provide feedback on the displayed content, and the server uses this feedback to optimize the prompts of the generating AI model, improving the accuracy of information generation in the future.

[0703] For example, if a user who commutes by train uses the app on their smartphone and is interested in sports and technology, they can view the latest relevant articles and videos and rate them as "useful," and this feedback will be reflected in future content generation. Furthermore, a prompt such as, "Summarize and display the latest technology articles and sports news tailored to the user's interests. Use eye-catching headlines for important information," will ensure the generation AI model functions correctly.

[0704] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0705] Step 1:

[0706] The server receives user interest information as input and stores it as data in a storage device. Specifically, when a user selects a category such as sports or technology, that information is sent to the server.

[0707] Step 2:

[0708] The server analyzes behavioral history information stored on the storage device. Here, Pandas is used to aggregate past behavioral history and detect changes in interests. The input is behavioral history information, and the output is data showing the detected changes in interests.

[0709] Step 3:

[0710] The server automatically generates information using natural language processing techniques with a generative AI model. Specifically, it utilizes the Transformers library to extract relevant information from information sources based on past behavioral history data and current interests, and outputs it as a summary. The input consists of data on interests and related information sources.

[0711] Step 4:

[0712] The server sends the generated information to the display device. The device, built with React Native, provides the information to the user by displaying the automatically generated content. Specifically, a summary of the information is visually displayed on the user interface.

[0713] Step 5:

[0714] Users provide feedback on the displayed content and send this feedback to the server. The input is the user's feedback, and the output is the data necessary for improving accuracy. Based on the feedback, the prompts of the generated AI model are optimized.

[0715] Step 6:

[0716] The server readjusts the generative AI model for the next information generation. Specifically, prompts are updated based on new user feedback, improving accuracy in subsequent information generation. This is a process of refining the model's behavior using feedback.

[0717] 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.

[0718] This invention embodies a system that provides information based on the user's interests and emotional state. This system generates and displays personalized content by exchanging data and information between the server, terminal, and user.

[0719] Specifically, users can indirectly communicate their emotions at any given time by selecting categories of interest and providing feedback via their device. The server receives this input data and stores it in a data storage device. The server also has an emotion engine that analyzes the user's behavioral history and emotional information to identify the user's current emotional state.

[0720] The emotion engine identifies the emotions a user feels while viewing information, based on user input data and past behavioral history. This emotion information is used by a generation mechanism along with regular interest data. The generation mechanism automatically generates information from the latest information resources in a way that matches the user's interests and emotions, and then adjusts or optimizes the content. As a result, personalized content that is more relevant to the user and also responds to their emotional state is generated.

[0721] For example, if the emotion engine identifies that a user has positive feelings towards "sports" as a category, the server will generate positive news and articles that will attract the user's interest. The generated content is sent to the user's device, where the user can view it. In this way, the server can provide optimal information based on the user's emotions and interests.

[0722] Throughout this entire system, users can not only efficiently gather the information they need, but also enjoy a highly satisfying experience that takes their emotions into consideration.

[0723] The following describes the processing flow.

[0724] Step 1:

[0725] The user selects categories of interest on their device (for example, "News," "Entertainment," "Sports," etc.). This information is sent to the server via the device.

[0726] Step 2:

[0727] The server stores the received category data in the data storage device. This records each user's interests.

[0728] Step 3:

[0729] The device provides indirect feedback about the user's emotions by sending information such as user actions, comments, and browsing speed to the emotion engine.

[0730] Step 4:

[0731] The server uses an emotion engine to analyze user input data and behavioral history to identify the user's current emotional state. This emotional information reflects the emotions the user is experiencing while using the content.

[0732] Step 5:

[0733] The server collects the latest information resources from the web and databases. These resources include news articles, video content, and blog posts.

[0734] Step 6:

[0735] The server uses generation means to automatically generate content based on the user's interests and emotions from collected information resources, and then adjusts or optimizes the content.

[0736] Step 7:

[0737] The generated personalized content is sent from the server to the user's device.

[0738] Step 8:

[0739] The device displays the received content to the user, making it available for viewing and reading.

[0740] Step 9:

[0741] Users can provide feedback after viewing the content. This feedback will be used to improve future content and its accuracy.

[0742] Step 10:

[0743] The server incorporates new user feedback into the learning of its emotion engine and generation methods, helping to create more refined content. This allows the system to improve user satisfaction over time.

[0744] (Example 2)

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

[0746] In modern information delivery systems, providing information quickly and appropriately optimized based on users' interests and emotions is a challenging task. Existing systems often only consider users' interests, and there are limitations to personalization that utilizes emotional states. Therefore, it is necessary to achieve information delivery that is more satisfying for users.

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

[0748] In this invention, the server includes means for receiving interest information and emotional information from a user and storing the information in a storage device, means for analyzing the user's behavioral history data and emotional data to identify changes in interest and emotional state, and means for automatically generating information based on the user's interests and emotions from the latest information sources using generation means. This makes it possible to provide users with information that is more relevant and also corresponds to their emotional state.

[0749] "Service provider equipment" refers to a combination of hardware and software that constitutes a system for providing services to users.

[0750] "Users" refer to those who receive information or provide feedback through this system.

[0751] "Interest information" refers to data that represents the user's interest in a particular field or topic.

[0752] "Emotional information" refers to data that indicates the user's psychological state, such as emotions like positive, negative, or neutral.

[0753] A "storage device" is a device used to store digital information and is used to temporarily or permanently retain received data.

[0754] "Behavioral history data" refers to a dataset that includes records of actions and choices that users have made in the past.

[0755] "Analysis" is the process of processing received data statistically or algorithmically to derive useful information or patterns.

[0756] "Generative means" refers to the processes or technologies used to form and output information based on the user's interests and emotions.

[0757] "Information source" refers to the place or medium from which data or content used by a system to provide to users is transmitted.

[0758] "Automatic generation" refers to a system creating information based on specified conditions without human intervention.

[0759] "Terminal device" refers to a device used by a user to access a service, and includes computers, smartphones, tablets, and other similar devices.

[0760] In implementing this invention, the system mainly consists of a server, a terminal, and a user.

[0761] The server, as part of the service provider's equipment, receives interest and emotion information from users. This information is stored in a data storage device, such as a database. The server uses an emotion analysis engine developed with machine learning libraries such as "TensorFlow" and "Python" to analyze the user's behavioral history data and current emotion information. It then identifies the user's emotional state. Based on the changes in interest and emotional state identified through this analysis, a generative AI model is used to construct new information. In this generation process, natural language processing technology is utilized to select content that matches the user's interests and emotions, and to automatically generate optimized information.

[0762] For example, if a user selects the "Sports" category and submits positive emotional information, the server processes this information through its sentiment analysis engine and generates positive and up-to-date sports news that is best suited to the user's state. An example of a prompt for this generating AI model is as follows:

[0763] Prompt: Please provide the latest and most positive sports news that will attract users when they are feeling positive emotions.

[0764] The device receives generated information sent from the server and displays it in a format viewable by the user. This allows users to experience content optimized to their interests and emotions.

[0765] Users send their interests and emotions to the system via their devices, providing feedback. This feedback is collected by the server and used to improve the accuracy of the generation process.

[0766] Therefore, this system can provide users with information that is highly relevant and emotionally resonant.

[0767] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0768] Step 1:

[0769] Users select their interest categories through their device and provide emotional feedback. This input information is sent from the device to the server.

[0770] Step 2:

[0771] The server stores interest categories and emotional information received from the terminal in its storage device. The input data includes categories selected by the user and feedback indicating their emotional state. Based on this, an entry is created in the database, and the user profile is updated.

[0772] Step 3:

[0773] The server uses an emotion analysis engine to analyze the user's past behavioral history data and newly received emotion information. Based on the received data, a process is initiated to identify the user's emotional state. This analysis identifies what the user wants and what information is appropriate for them.

[0774] Step 4:

[0775] The server uses a generative AI model as a generation tool to automatically generate content based on identified emotional states and interests. Input includes the user's current interests and emotional information, and output is personalized news articles and information. Generation prompts are input to the AI ​​model to generate information relevant to the user.

[0776] Step 5:

[0777] The server sends the generated content to the device. The transmitted data is converted to the optimal format on the device and displayed. The device then provides the user with the generated personalized content, which the user can view.

[0778] Step 6:

[0779] The user provides feedback on the displayed content. The device sends this feedback back to the server. This feedback is used by the server as training data to improve the accuracy of the generation method.

[0780] (Application Example 2)

[0781] 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".

[0782] In today's information-saturated age, users face the challenge of efficiently obtaining information optimized for their interests and emotions. Traditionally, information provision systems have provided information based on user interests, but have failed to provide appropriate information that takes into account the user's emotional state. As a result, user satisfaction has decreased, and the efficiency of information consumption has been impaired.

[0783] 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.

[0784] In this invention, the server includes means for receiving user interest information and storing it in a data storage device, means for analyzing user behavior history data and detecting changes in interests, means equipped with an emotion analysis engine for analyzing and identifying the user's emotional state, means for automatically generating information from the latest information resources based on the user's interests and emotional state using generation means, and means for transmitting and displaying the generated information to the user's terminal device. This makes it possible to accurately provide information that matches the user's interests and emotions, thereby improving user satisfaction and increasing the efficiency of information consumption.

[0785] A "service provider system" is a system that has a mechanism for receiving data from users and processing, storing, and analyzing that data.

[0786] A "data storage device" is a device for safely and efficiently recording and storing received data.

[0787] "Analyzing behavioral history data" refers to analyzing a user's past behavioral data to derive changes and trends in their interests and preferences.

[0788] An "emotion analysis engine" is a processing unit or program that identifies a user's current emotional state based on the user's input data and behavioral history.

[0789] "Generation means" refers to a technology or process for automatically generating up-to-date information based on the user's interests, concerns, and emotional state.

[0790] "Terminal devices" refer to various types of equipment (such as smartphones, tablets, and computers) that users use to receive and manipulate information.

[0791] "Feedback" refers to the responses or reactions that users provide to a system, and is used to improve the quality of the information generated.

[0792] This invention relates to the realization of an advanced personalized system that provides information based on the user's interests and emotions. The following is an example of how to specifically implement this invention.

[0793] The server first receives interest information from users and stores it in a data storage device. This step securely stores the data using a storage system located on a cloud platform (e.g., Amazon S3). The server also collects and analyzes user behavior history data. Data analysis tools (e.g., Google Analytics) are used for this analysis. This allows for understanding changes in user interests.

[0794] Furthermore, the server uses an emotion analysis engine to identify the user's emotional state. This analysis utilizes an emotion analysis API (e.g., Microsoft Azure Emotion API) that leverages natural language processing technology. The results are then integrated with the user's interest data.

[0795] Next, the server uses a generation mechanism to generate information that matches the user's interests and emotional state. In this step, a generation AI model (e.g., GPT-3) is utilized to automatically generate and adjust content that is optimal for the user.

[0796] The generated content is sent to the user's device. This device may be a smartphone or tablet, and the user can view the content on these devices. This allows users to efficiently obtain information that is tailored to their interests and emotions.

[0797] For example, if a user selects the "Movies" category and indicates a desire to refresh, the server will generate and send information about new comedy movies and positive review articles. An example of a prompt in response to this would be: "The user is interested in recent movie news and is looking for something relaxing. Please suggest appropriate movie reviews and new release information."

[0798] This system allows users to receive information tailored to their interests and emotions, enabling a highly satisfying information experience.

[0799] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0800] Step 1:

[0801] Users input interest information and feedback using their devices. For example, a user might select the category "movies" and input a feeling such as "feeling happy." This input data is then sent from the device to the server.

[0802] Step 2:

[0803] The server stores the received interest information and feedback in a data storage device. The data is stored in a cloud storage system. This ensures that the data necessary for analysis in subsequent processing is securely retained.

[0804] Step 3:

[0805] The server analyzes the stored behavioral history data. Using data analysis tools such as Google Analytics, it detects changes in the user's interests. During this process, aggregation and trend analysis are performed based on the user's past behavioral data.

[0806] Step 4:

[0807] The server uses an emotion analysis engine to identify the user's emotional state. Based on the input data, it analyzes emotions using the Microsoft Azure Emotion API and extracts specific emotional states. This result is then used in subsequent information generation processes.

[0808] Step 5:

[0809] The server utilizes a generative AI model as a generation tool to automatically generate content based on the user's interests and emotions. For example, it inputs prompt text into an OpenAI GPT-3 model to generate information and articles best suited to the user. At this stage, the content and format of the generated text are optimized.

[0810] Step 6:

[0811] The generated content is sent from the server to the user's device. The user can view the information on their device and, as a result, consume the provided content. This improves user satisfaction and the efficiency of information consumption.

[0812] 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.

[0813] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0814] 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.

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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."

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0833] The following is further disclosed regarding the embodiments described above.

[0834] (Claim 1)

[0835] The service provider's system includes means for receiving interest information from users and storing such information in a data storage device.

[0836] A means for analyzing the user's behavioral history data and detecting changes in their interests,

[0837] A means for automatically generating information from the latest information resources based on the user's interests, using a generation means,

[0838] A means for transmitting and displaying the generated information to the user's terminal device,

[0839] A means for receiving feedback from users and using it to improve the accuracy of the generation means,

[0840] A system that includes this.

[0841] (Claim 2)

[0842] The system according to claim 1, wherein the user's interest data is entered through category selection.

[0843] (Claim 3)

[0844] The system according to claim 1, wherein the generation means includes a machine learning model using natural language processing technology.

[0845] "Example 1"

[0846] (Claim 1)

[0847] A means for acquiring interest information from users and storing such information on a recording medium,

[0848] A means of analyzing a user's past activity history and identifying changes in their interests,

[0849] A means of generating data based on the user's interests from the latest information sources, utilizing automated information generation means,

[0850] A means for transmitting and outputting the generated data to the user's display device,

[0851] A means for receiving evaluation information from users and applying it to improve the accuracy of the automated information generation means,

[0852] A system that includes this.

[0853] (Claim 2)

[0854] The system according to claim 1, wherein the user's interest information is entered through classification selection.

[0855] (Claim 3)

[0856] The system according to claim 1, wherein the automated information generation means includes a learning algorithm model using natural language processing technology.

[0857] "Application Example 1"

[0858] (Claim 1)

[0859] The service provider's device includes means for receiving user interest information and storing that information in a storage device.

[0860] A means for analyzing the user's behavioral history information and detecting changes in their interests,

[0861] In order to generate information, means for automatically generating information from the latest information sources based on the user's interests,

[0862] A means for transmitting and displaying the generated information on the user's display device,

[0863] A means for receiving feedback from users and using it to improve the accuracy of the generation means,

[0864] A means of providing information that is updated in real time and efficiently delivers personalized content on a display device,

[0865] A means to improve the accuracy of future information generation using a generative AI model after receiving user feedback,

[0866] A system that includes this.

[0867] (Claim 2)

[0868] The system according to claim 1, wherein the user's interests are entered via category selection.

[0869] (Claim 3)

[0870] The system according to claim 1, wherein the generation means includes a machine learning algorithm using natural language processing technology.

[0871] "Example 2 of combining an emotion engine"

[0872] (Claim 1)

[0873] The service provider's equipment includes means for receiving interest information and emotional information from users and storing such information in a storage device.

[0874] A means for analyzing the user's behavioral history data and emotional data to identify changes in interest and emotional state,

[0875] A means for automatically generating information from the latest information sources based on the user's interests and emotions,

[0876] A means for transmitting and displaying the generated information to the user's terminal device,

[0877] A means for receiving feedback from users and using it to improve the accuracy of the generation means,

[0878] A system that includes this.

[0879] (Claim 2)

[0880] The system according to claim 1, wherein the user's interest data and emotional information are obtained through category selection and feedback input.

[0881] (Claim 3)

[0882] The system according to claim 1, wherein the generation means includes a machine learning model using natural language processing technology and an emotion analysis engine.

[0883] "Application example 2 when combining with an emotional engine"

[0884] (Claim 1)

[0885] The service provider's system includes means for receiving interest information from users and storing such information in a data storage device.

[0886] A means for analyzing the user's behavioral history data and detecting changes in their interests,

[0887] A means equipped with an emotion analysis engine for analyzing and identifying the emotional state of a user,

[0888] A means for automatically generating information from the latest information resources based on the user's interests and emotional state, using a generation means,

[0889] A means for transmitting and displaying the generated information to the user's terminal device,

[0890] A means for receiving feedback from users and using it to improve the accuracy of the generation means,

[0891] A system that includes this.

[0892] (Claim 2)

[0893] The system according to claim 1, wherein the user's interest data is entered through category selection.

[0894] (Claim 3)

[0895] The system according to claim 1, wherein the generation means includes a machine learning model using natural language processing technology and a generation means for adjusting content based on the user's emotional state. [Explanation of Symbols]

[0896] 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. The service provider's system includes means for receiving interest information from users and storing such information in a data storage device. A means for analyzing the user's behavioral history data and detecting changes in their interests, A means for automatically generating information from the latest information resources based on the user's interests, using a generation means, A means for transmitting and displaying the generated information to the user's terminal device, A means for receiving feedback from users and using it to improve the accuracy of the generation means, A system that includes this.

2. The system according to claim 1, wherein the user's interest data is entered through category selection.

3. The system according to claim 1, wherein the generation means includes a machine learning model using natural language processing technology.

Images