System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting user input preferences and interests; means for collecting news data from a plurality of news sources; means for filtering the collected news data based on user preferences and interests and generating a summary; means for generating a personalized news list for each user and delivering it to a terminal; and means for collecting and re-learning user feedback to improve the accuracy of news list generation.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In today's world, while there are a wide variety of ways to obtain information, it is difficult to provide an appropriate news experience for each individual. Specifically, users often miss important information, have to scroll through articles they are not interested in, and spend a lot of time searching for the information they need. Furthermore, insufficient news integration and summarization reduces opportunities for users to obtain information from multiple perspectives. These issues, which lead to stress and time wasted due to information overload, require solutions. [Means for solving the problem]

[0005] This invention proposes a system that provides a service for customizing news according to a user's preferences and interests. Specifically, the system includes a means for collecting information about preferences and interests entered by the user and a means for collecting news data from multiple news sources. The system also includes a means for filtering the news data based on the user's preferences and generating summaries. Furthermore, the system provides a means for generating a news list personalized for each user and delivering it to the terminal. Additionally, the system includes a means for collecting user feedback, relearning, and improving the accuracy of generating the news list. This system allows users to efficiently obtain information that is important to them and obtain information from multiple perspectives, thereby reducing stress and time wasted due to information overload.

[0006] "User" refers to any individual or entity that receives information using the System.

[0007] "Information about preferences and interests" refers to preference information such as genre, topic, visual style, language, region, number and length of news, selected or specified by the user based on their own interests and concerns.

[0008] A "news source" refers to a medium or platform that provides news data, and specifically includes news sites, RSS feeds, news APIs, etc.

[0009] "News Data" refers to information related to news content, such as articles, summaries, images, and videos, obtained from news sources.

[0010] "Filtering" refers to the process of sorting news data based on a user's preferences and interests.

[0011] A "summary" refers to a short sentence that simplifies the content of news data and summarizes only the important information.

[0012] A "personalized news list" refers to a list of news articles that is customized based on a user's preferences and interests.

[0013] "Terminal" refers to the electronic device used by the user to use this system, specifically a smartphone, tablet, PC, etc.

[0014] "Feedback" refers to opinions or ratings provided by users regarding news lists, including actions such as "Like" or "Not Interested."

[0015] "Retraining" refers to the process of retraining the AI ​​algorithm based on collected feedback to improve the accuracy of generating news lists. [Brief explanation of the drawings]

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

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

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

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

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

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

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

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

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

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

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

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0037] The present invention is a system that customizes news based on a user's preferences and interests, providing a personalized news experience. Below, we will create a program for this system and explain each processing step in natural language.

[0038] Registering users and setting preferences

[0039] 1. When a user accesses the application for the first time, a new user registration screen is displayed.

[0040] 2. Users enter basic information such as their name, email address, and password, and also select genres and topics of interest (e.g., politics, economics, entertainment).

[0041] 3. Users set visual styles such as font size, color, preferred language, region, word count and length of news.

[0042] 4. The above information is sent from the user's device to the server, which stores it in a database.

[0043] News gathering

[0044] 1. The server periodically accesses multiple predefined news sources (e.g., news sites, RSS feeds, news APIs) to collect the latest news data.

[0045] 2. The collected news data is stored in a database on the server.

[0046] News analysis based on user preferences

[0047] 1. The server retrieves user preferences and settings from a database.

[0048] 2. The server filters the collected news data based on the user's preferences and interests, using criteria such as genre, topic, language, region, and word count.

[0049] 3. The server uses AI algorithms to generate filtered news summaries, sometimes supplemented with related news and perspectives.

[0050] Personalized news generation

[0051] 1. The server generates a news list optimized for each user.

[0052] 2. This news list is stored in a database on the server and linked to the user's account.

[0053] News distribution to users

[0054] 1. The server sends a personalized news list to the user's device.

[0055] 2. The user's device displays this news list on the user interface so that the user can check it.

[0056] User feedback and retraining

[0057] 1. Users can provide feedback on the displayed news, such as "like" or "not interested."

[0058] 2. This feedback information is sent from the device to the server, where it is stored in a database.

[0059] 3. The server uses this feedback to retrain its AI algorithms to improve the accuracy of future news list generation.

[0060] For example, if a user prefers the "Economy" genre and selects a "long-form" and "image and video-focused" style, the server will collect relevant economic news, analyze it in detail, and provide an optimized news list. The user can review this on their device and provide feedback on articles they find interesting. This feedback will then be reflected in the next news list generation.

[0061] In this way, the system provides a news experience optimized to the user's preferences, reducing the stress and time wasted caused by information overload.

[0062] The processing flow will be explained below.

[0063] Step 1:

[0064] A user accesses the application and is presented with a new user registration screen.

[0065] Step 2:

[0066] Users enter basic information such as their name, email address, and password, as well as genres and topics of interest (e.g., politics, economics, entertainment), and set visual styles such as font size, color, preferred language, region, and word count and length of news.

[0067] Step 3:

[0068] The terminal collects this information and sends it to the server.

[0069] Step 4:

[0070] The server stores the received user information and setting information in a database.

[0071] Step 5:

[0072] The server periodically accesses multiple predefined news sources (e.g., news sites, RSS feeds, news APIs) to collect news data.

[0073] Step 6:

[0074] The collected news data is stored in a database on the server.

[0075] Step 7:

[0076] The server retrieves user preferences and settings from a database.

[0077] Step 8:

[0078] The server filters the news data based on the user's preferences, such as genre, topic, language, region, and word count.

[0079] Step 9:

[0080] The server uses AI algorithms to generate filtered news summaries, adding related news and perspectives as needed.

[0081] Step 10:

[0082] The server aggregates the summarized news and generates a personalized news list for each user.

[0083] Step 11:

[0084] The generated news list is stored in a database on the server and linked to the user's account.

[0085] Step 12:

[0086] The server sends the news list to the user's terminal.

[0087] Step 13:

[0088] The terminal displays the received news list on the user interface.

[0089] Step 14:

[0090] Users provide feedback on the displayed news, such as "like" or "not interested."

[0091] Step 15:

[0092] The terminal transmits the feedback information to the server.

[0093] Step 16:

[0094] The server stores the feedback information in a database and uses it to retrain the AI ​​algorithm.

[0095] Step 17:

[0096] The retrained AI algorithm will improve the accuracy of the next news list generation.

[0097] Example 1

[0098] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0099] In today's information society, users are faced with a vast amount of news information, making it difficult to find useful information. This information overload can be stressful and time-consuming for users. Furthermore, providing news tailored to users' preferences and interests requires collecting, filtering, personalizing, and incorporating feedback from news data, but efficient methods for doing so are lacking. Therefore, the present invention aims to solve these problems and provide a news experience optimized for users' preferences.

[0100] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0101] In this invention, the server includes means for collecting information on preferences and interests input by the user, means for collecting news data from multiple information sources, means for filtering the collected news data based on the user's preferences and interests and generating summaries, means for generating a news list personalized for each user and distributing it to the terminal, and means for collecting user feedback, relearning, and improving the accuracy of generating the news list. This makes it possible to provide a news experience optimized for the user's preferences and reduce stress and time wasted due to information overload.

[0102] A "user" is an individual or organization that uses the system to view news and enter information about their preferences and interests.

[0103] "Preferences and interests" refers to preferences such as genres and topics that interest the user, visual style, language, region, etc.

[0104] "Sources" refers to digital media such as multiple websites, data feeds, and news APIs that provide news data.

[0105] "News data" refers to data collected from various sources, including news articles, reports, and media content.

[0106] "Filtering" is the process of selecting highly relevant information from collected news data based on the user's preferences and interests.

[0107] A "summary" refers to a text or media that compactly summarizes filtered news data and succinctly expresses the main content.

[0108] A "personalized news list" is a list of news presented in a way that is optimized for each user, and is generated based on the user's preferences and feedback.

[0109] "Feedback" refers to opinions and thoughts about news provided by users, such as "like" or "not interested."

[0110] "Relearning" is the process of updating the AI ​​algorithm based on collected feedback to improve the accuracy of generating news lists in future.

[0111] The present invention is a system that customizes news based on a user's preferences and interests, providing a personalized news experience. Below, we will explain in natural language the means for generating programs for this system and the processing based on them.

[0112] First, this system is composed of multiple components and has three main actors: the server, the terminal, and the user. The server is responsible for collecting data, filtering, generating summaries, generating and distributing news lists, and collecting feedback and relearning. The terminal provides the user interface, sending input from the user to the server and displaying responses from the server. The user interacts with the system, inputting required information and providing feedback.

[0113] 1. User Registration and Preferences

[0114] When a user accesses the application for the first time, a new user registration screen appears. The user enters basic information such as name, email address, and password, and also selects the genres and topics of interest. They also set visual style settings (font size, color, preferred language, region, number of characters and length of news). This information is sent from the user's device to the server, which stores it in a database. In terms of specific hardware, the server is a computer with a high-performance CPU, while the device can be a smartphone or PC. In terms of software, Python and SQL are used on the server side, and JavaScript (registered trademark), HTML, and CSS are used on the device side.

[0115] 2. News gathering

[0116] The server periodically accesses multiple predefined news sources (e.g., news websites, RSS feeds, news APIs) to collect the latest news data using web scraping techniques (Python libraries Beautiful Soup and Selenium) and API calls, and stores the collected news data in a database on the server.

[0117] 3. Analyzing news based on user preferences

[0118] The server retrieves user preferences and settings from the database and filters the collected news data based on them. Filtering criteria include genre, topic, language, region, and word count. Furthermore, it generates summaries of the filtered news using AI algorithms (e.g., natural language processing models such as GPT-3 (registered trademark) and BERT). Related news and information from multiple perspectives are also added.

[0119] 4. Personalized news generation and delivery

[0120] The server generates a news list optimized for each user, stores it in a database, and associates it with the user's account. This news list is periodically sent to the user's device, which displays it on the user interface. The user can then review the list, select articles of interest, and view them.

[0121] 5. User Feedback and Retraining

[0122] Users provide feedback on the displayed news, such as "Like" or "Not Interested." This feedback information is sent from the device to the server and stored in a database. The server uses the received feedback to retrain the AI ​​algorithm and improve the accuracy of news list generation.

[0123] Specific examples

[0124] For example, if a user prefers the "Economy" genre and selects "Long Text" and "Image and Video Focused" styles, the server will collect relevant economic news, analyze it in detail, and provide it as an optimized news list. The user can check this on their device and provide feedback on articles that interest them. Specific examples of prompts include the following:

[0125] "Please create a news list that displays long economic news articles with images and videos as the main content."

[0126] In this way, the system can provide a news experience that is optimized to the user's preferences, reducing the stress and time wasted caused by information overload.

[0127] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0128] Step 1: Registering a user

[0129] Input: The user enters their name, email address, password, genres and topics of interest, and visual style (font size, color, language, region, number and length of news).

[0130] Operation: The user enters the information they provided into the input form and clicks the submit button. At this time, validation checks are performed on the input data (e.g., checking that required fields are entered, checking the format of the email address).

[0131] Output: Data about the user's basic information and preferences is sent from the device to the server, which stores this data in a database.

[0132] Step 2: Gathering news

[0133] Input: The server is pre-configured with a list of news source URLs and API information.

[0134] How it works: The server periodically contacts predefined news sources (news sites, RSS feeds, news APIs, etc.) and uses web scraping techniques and API calls to gather the latest news data.

[0135] Output: The collected news data is stored in a database on the server.

[0136] Step 3: Analyzing news based on user preferences

[0137] Input: The server retrieves user preferences and settings from the database, and also inputs collected news data.

[0138] How it works: The server filters news data based on user preferences and settings (genre, topic, language, region, word count, etc.), extracts news based on the conditions using Python's Pandas library, and then generates a summary of the filtered news using an AI algorithm (e.g., GPT-3 or BERT).

[0139] Output: Filtered and summarized news data.

[0140] Step 4: Generate a personalized news list

[0141] Input: Filtered and summarized news data.

[0142] How it works: The server generates a news list optimized for each user. News items are tagged and ranked to reflect the user's preferences. The generated news list is saved in JSON format.

[0143] Output: The generated news list is stored in the server's database and associated with the user's account.

[0144] Step 5: Delivering news to users

[0145] Input: The generated personalized news list.

[0146] How it works: The server periodically delivers news lists to the user's device, sending data via GET requests using the REST API.

[0147] Output: The news list is sent to the terminal, which displays the received news list on its user interface.

[0148] Step 6: User feedback and retraining

[0149] Input: Feedback provided by the user regarding the news displayed (e.g. "Like" or "Not interested").

[0150] How it works: Users provide feedback on the displayed news by clicking or tapping. The device sends the feedback information to the server, which stores it in a database. The server then retrains the AI ​​algorithm and processes the results in a batch process to improve the accuracy of the next news list generation.

[0151] Output: An updated AI model and improved accuracy of news list generation based on it.

[0152] (Application example 1)

[0153] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0154] Currently, many news platforms are unable to provide news based on users' individual preferences and interests, resulting in stress and time wasted due to information overload. Furthermore, the news provided is not optimized for users' preferences, resulting in differences in how users perceive and value the information. Furthermore, insufficient news summaries and related information mean users are unable to quickly grasp the information they need.

[0155] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0156] In this invention, the server includes means for collecting information on preferences and interests input by the user, means for collecting news data from multiple news sources, means for filtering the collected news data based on the user's preferences and interests and generating summaries, means for generating a news list personalized for each user and distributing it to the terminal, means for collecting user feedback and relearning to improve the accuracy of generating the news list, and means for summarizing the collected news data using an artificial intelligence model. This makes it possible to reduce stress caused by information overload and provide news optimized to the user's preferences.

[0157] "User" refers to a person who uses the news application.

[0158] "Preferences and interests" refers to personal preferences such as the genres and topics that interest a user, visual style, language, and region.

[0159] "News source" refers to an external source of news data, including news sites, RSS feeds, news APIs, etc.

[0160] "News data" refers to a collection of information, such as articles and reports, collected from news sources.

[0161] "Filtering" refers to the process of selecting collected news data based on the user's preferences and interests.

[0162] A "summary" is a concise summary of the main points or content of a news article.

[0163] A "personalized news list" refers to a list of news articles optimized for each user.

[0164] "Device" refers to the device used to receive the personalized news list, including a smartphone, tablet, or computer.

[0165] "Feedback" refers to user-provided ratings and opinions on news articles.

[0166] "Retraining" refers to the process of using collected feedback information to retrain the algorithm to improve the accuracy of the system.

[0167] "Artificial intelligence model" refers to the machine learning algorithms and models used to generate summaries for collected news data.

[0168] This invention is a system that customizes news based on a user's preferences and interests, providing a personalized news experience. The program and processing of this system are described below.

[0169] Registering users and setting preferences

[0170] Users first enter their basic information into the news application, along with personal preferences such as genres and topics of interest, visual style, language, and region. This information is sent from the user's device to the server and stored in a database. This information collection allows the system to understand the user's individual preferences and use them for subsequent processing.

[0171] News gathering

[0172] The server periodically collects news data from multiple predefined news sources, including news websites, RSS feeds, and news APIs. This collected news data is then stored in the server's database. During this process, technologies such as APIs are used to ensure that the collected data is up-to-date and abundant.

[0173] News analysis based on user preferences

[0174] The server retrieves user preferences and settings from the database and filters the collected news data based on the user's preferences, using criteria such as genre, topic, language, region, and word count. During this process, artificial intelligence models and machine learning algorithms are used to filter and summarize the news.

[0175] Personalized news generation

[0176] Based on the filtered news data, the server generates a news list optimized for each user. This news list is stored in the server's database and linked to the user's account. The generated news list efficiently provides information that the user is interested in.

[0177] News distribution to users

[0178] The server sends the personalized news list to the user's device, which displays it. This process can be carried out on devices such as smartphones or tablets.

[0179] User feedback and retraining

[0180] Users can provide feedback on the displayed news, such as "Like" or "Not Interested." This feedback information is sent from the device to the server and stored in a database. The server uses this feedback to retrain the AI ​​algorithm and improve the accuracy of future news list generation.

[0181] Program processing

[0182] The system is implemented using Python, Flask, the Requests library, and a news API. For example, the news API is used to collect news data, Flask is used for user registration and feedback processing, and an artificial intelligence model (e.g., OpenAI's GPT model) is used to generate news summaries.

[0183] As a concrete example, the following prompt sentence will be used.

[0184] Prompt Sentence Examples

[0185] Generate a summary of the following news article:

[0186] The content of the news article goes here.

[0187] summary:

[0188] In this way, the system can provide a news experience optimized to the user's preferences, reducing stress and time wasted due to information overload.

[0189] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0190] Step 1:

[0191] Sign up and set your preferences

[0192] When a user first accesses the application, they launch it and enter information such as their name, email address, password, genres and topics of interest, visual style, preferred language, and region.

[0193] The terminal transmits this input information to the server.

[0194] The server stores the received information in a database.

[0195] Input: Name, Email, Password, Genre, Topic, Visual Style, Language, Region

[0196] Data processing: The server formats this information into structured data and stores it in a database.

[0197] Output: User profile stored in the database

[0198] Step 2:

[0199] News gathering

[0200] The server periodically accesses multiple news sources such as news APIs to collect news data.

[0201] The news data is stored in a database on the server.

[0202] Input: News API endpoint

[0203] Data processing: The server converts the acquired news data into the required structure and records it in the database.

[0204] Output: News data stored in a database

[0205] Step 3:

[0206] News analysis based on user preferences

[0207] The server retrieves user preferences and settings from a database.

[0208] The server filters the collected news data based on user settings, such as genre, topic, language, region, and word count.

[0209] Generate summaries of filtered news data using artificial intelligence models.

[0210] Input: User profiles and news data in a database

[0211] Data processing: filtering, summarization

[0212] Output: filtered and summarized news data

[0213] Step 4:

[0214] Personalized news generation

[0215] The server generates a news list optimized for each user based on the filtered and summarized news data.

[0216] This news list is stored in a database on the server and linked to the user's account.

[0217] Input: filtered and summarized news data

[0218] Data processing: News list generation, linking to user accounts

[0219] Output: A personalized news list

[0220] Step 5:

[0221] News distribution to users

[0222] The server sends a personalized news list to the user's terminal.

[0223] The terminal displays the received news list on the user interface.

[0224] Input: personalized news list

[0225] Data processing: Data transmission via communication

[0226] Output: A personalized news list displayed on the device.

[0227] Step 6:

[0228] User feedback and retraining

[0229] Users provide feedback on news lists (such as "like" or "not interested").

[0230] The terminal transmits the feedback information to the server.

[0231] The server stores the feedback information in a database and retrains the AI ​​algorithm.

[0232] Input: User feedback

[0233] Data processing: saving feedback information and re-learning process

[0234] Output: Updated AI model and improved accuracy of future news list generation

[0235] In this way, through a series of processing steps, the system provides a personalized news experience tailored to the user's preferences.

[0236] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0237] The present invention is a system that provides news tailored to the user's preferences and interests, and also combines an emotion engine to provide an optimal news experience according to the emotional state of each individual user. Below, we will explain the program processing and specific examples of this system.

[0238] Registering users and setting preferences

[0239] 1. A user accesses the application and is presented with a new user registration screen.

[0240] 2. Users enter basic information such as their name, email address, and password, as well as their preferred genres and topics (e.g., politics, economics, entertainment), and set visual styles such as font size, color, preferred language, region, and number and length of news characters.

[0241] 3. The information provided by the user is sent from the device to the server, where it is stored in a database.

[0242] News gathering

[0243] 1. The server periodically accesses multiple news sources (e.g., news sites, RSS feeds, news APIs) to collect the latest news data.

[0244] 2. The collected news data is stored in a database on the server.

[0245] News analysis based on user preferences

[0246] 1. The server retrieves user preferences and settings from a database.

[0247] 2. The server filters the collected news data based on the user's preferences, taking into account criteria such as genre, topic, language, region, and word count.

[0248] 3. The server uses AI algorithms to summarize the filtered news, and may add related news and information from multiple perspectives.

[0249] Introducing the Emotion Engine

[0250] 1. The emotion engine installed on the device uses the user's camera and microphone to analyze facial expressions and tone of voice to recognize the user's emotional state.

[0251] 2. The recognized emotion data is sent from the device to the server.

[0252] 3. The server adjusts the priority and content of the news list based on the emotion data.

[0253] Personalized news generation

[0254] 1. The server generates an optimized news list based on the user's preferences and sentiment data.

[0255] 2. This news list is stored in a database and linked to the user's account.

[0256] News distribution to users

[0257] 1. The server sends the news list to the user's terminal.

[0258] 2. The terminal displays the news list on the user interface so that the user can check it.

[0259] User feedback and retraining

[0260] 1. Users provide feedback on the displayed news, such as "like" or "not interested."

[0261] 2. The feedback information is sent from the device to the server and stored in a database.

[0262] 3. The server uses the feedback to retrain the AI ​​algorithm to improve the accuracy of generating news lists.

[0263] For example, if a user likes the "Entertainment" genre and the emotion engine recognizes the user's positive emotional state, the server will prioritize filtering entertainment news containing optimistic content and add it to the news list along with summaries. On the other hand, if the user is in a negative emotional state, the server will include positive news articles to improve the user's mood.

[0264] In this way, the system provides a personalized news experience that takes into account the user's preferences and emotional state, reducing stress and time wasted due to information overload and promoting the user's mental health.

[0265] The processing flow will be explained below.

[0266] Step 1:

[0267] A user accesses the application and is presented with a new user registration screen.

[0268] Step 2:

[0269] Users enter basic information such as their name, email address, and password, as well as their preferred genres and topics (e.g., politics, economics, entertainment), and set visual styles such as font size, color, language, region, and word count and length of news.

[0270] Step 3:

[0271] The terminal collects this information and sends it to the server.

[0272] Step 4:

[0273] The server stores the received user information and setting information in a database.

[0274] Step 5:

[0275] The server periodically accesses multiple predefined news sources (e.g., news sites, RSS feeds, news APIs) to collect the latest news data.

[0276] Step 6:

[0277] The collected news data is stored in a database on the server.

[0278] Step 7:

[0279] The server retrieves user preferences and settings from a database.

[0280] Step 8:

[0281] The server filters the news data based on the user's preferences, such as genre, topic, language, region, and word count.

[0282] Step 9:

[0283] The server uses AI algorithms to generate filtered news summaries, adding related news and perspectives as needed.

[0284] Step 10:

[0285] The emotion engine installed on the device uses the user's camera and microphone to analyze facial expressions and tone of voice to recognize the user's emotional state.

[0286] Step 11:

[0287] The recognized emotion data is transmitted from the terminal to the server.

[0288] Step 12:

[0289] The server adjusts the priority and content of the news list based on the emotional data, selecting news according to the user's emotional state, such as positive or negative emotions.

[0290] Step 13:

[0291] The server generates a personalized news list taking into account the emotional data and user preferences.

[0292] Step 14:

[0293] The generated news list is stored in a database on the server and linked to the user's account.

[0294] Step 15:

[0295] The server sends the news list to the user's terminal.

[0296] Step 16:

[0297] The terminal displays the news list on the user interface so that the user can check it.

[0298] Step 17:

[0299] Users provide feedback on the displayed news, such as "like" or "not interested."

[0300] Step 18:

[0301] The feedback information is sent from the terminal to the server.

[0302] Step 19:

[0303] The server stores the feedback information in a database and uses it to retrain the AI ​​algorithm.

[0304] Step 20:

[0305] The retrained AI algorithm will improve the accuracy of the next news list generation.

[0306] Example 2

[0307] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0308] Current news delivery systems primarily provide news based on users' preferences and interests, but few systems consider the user's emotional state when providing news. This can result in users receiving news that is inappropriate for their current emotional state, potentially adversely affecting how they receive and understand information. Furthermore, there are insufficient mechanisms for reducing stress and fatigue caused by information overload, making it difficult to maintain users' mental health.

[0309] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting information on preferences and interests input by the user, means for collecting data from multiple information sources, means for filtering the collected data based on the user's preferences and interests and generating a summary, means for analyzing the user's emotional state using an emotion recognition engine of the terminal and adjusting the data based on this information, means for generating a list personalized for each user and delivering it to the terminal, and means for collecting user feedback, re-learning, and improving the accuracy of list generation. This enables personalized news delivery that takes into account not only the user's preferences and interests but also their emotional state.

[0310] "User-entered preference and interest information" refers to personal preference information provided by individual users, such as genres, topics, types of news, and visual styles that interest them.

[0311] "Multiple sources" refers to various news sources, such as news sites, RSS feeds, and news APIs.

[0312] "Data filtering" is the process of selecting collected news data based on the user's preferences and interests.

[0313] "Generating a summary" is the process of shortening the filtered news data into a concise format that includes the main points.

[0314] An "emotion recognition engine" is software that uses the device's built-in camera and microphone to analyze the user's facial expressions and tone of voice and recognize their emotional state.

[0315] "Adjusting data" is a process of changing the contents and priorities of the news list based on the emotion data obtained from the emotion recognition engine.

[0316] A "personalized list" is a collection of news articles that is customized based on an individual user's preferences and emotional state.

[0317] "Delivering to terminal" refers to the process of sending the generated news list to the device used by the user.

[0318] "Feedback" refers to user-provided ratings and reactions to news articles, such as "like" or "not interested."

[0319] "Retraining" is the process of improving the AI ​​algorithm based on collected feedback to improve the accuracy of generating news lists.

[0320] This invention is a system that provides optimal information experiences according to the emotional state of each individual user by combining a system that provides information tailored to the user's preferences and interests with an emotion recognition engine. The specific configuration and operating procedures for implementing this system are described below.

[0321] Registering users and setting preferences

[0322] 1. When a user accesses the application, a new user registration screen appears, where the user enters basic information such as name, email address, and password, as well as the genres and topics of interest.

[0323] 2. The user further configures the visual style, such as font size, color, language, region, and length and character count of the information.

[0324] 3. The information entered from the device is sent to the server. For security reasons, an encrypted protocol (e.g., HTTPS) is used for this transmission.

[0325] 4. The server stores the received information in a database.

[0326] Collection of information

[0327] 1. The server automatically collects data from multiple sources (e.g., websites, RSS feeds, APIs) and this collection is configured to occur periodically.

[0328] 2. Data from each source is collected on the server in a standard format (e.g., JSON, XML).

[0329] 3. The server stores the collected data in a database and keeps the information up to date.

[0330] Analyzing information based on user preferences

[0331] 1. The server retrieves user preferences and settings from a database, including information about genre, topic, language, region, and character count.

[0332] 2. The server filters the collected data based on the user's preferences. For example, if a user is interested in the entertainment genre, it will only show articles in that genre.

[0333] 3. The server uses AI algorithms (e.g., natural language processing models, generative AI models) to summarize the filtered data and add relevant information and multifaceted perspectives.

[0334] Introducing the Emotion Engine

[0335] 1. The device's built-in emotion recognition engine uses the camera and microphone to analyze the user's facial expressions and tone of voice to recognize their emotional state. This analysis uses machine learning models (e.g., facial expression recognition model, voice emotion recognition model).

[0336] 2. The recognized emotion data is sent from the device to the server.

[0337] 3. The server adjusts the priority and content of the information list based on the emotional data. For example, when the user is in a positive emotional state, information with positive content is displayed preferentially.

[0338] Generate personalized information

[0339] 1. The server generates an optimal information list based on the user's preferences and emotional data. This list is customized for each user.

[0340] 2. The generated information list is stored in a database and linked to each user's account.

[0341] Information distribution to users

[0342] 1. The server sends the optimized information list to the device using a secure communication protocol (e.g., HTTPS, WebSocket).

[0343] 2. The terminal displays the received information list on the user interface for easy access by the user.

[0344] User feedback and retraining

[0345] 1. The user provides feedback on the displayed information, such as "like" or "not interested."

[0346] 2. The device sends user feedback to the server and receives real-time ratings.

[0347] 3. The server retrains the AI ​​algorithm based on the feedback to improve the accuracy of generating information lists.

[0348] For example, if a user likes the "Entertainment" genre and the emotion engine recognizes the user's positive emotional state, the server will prioritize filtering entertainment information containing optimistic content and add it to the information list along with a summary. On the other hand, if the user is in a negative emotional state, the server will adjust the information list to include positive information to improve the user's mood.

[0349] An example of a prompt sentence to input to the generative AI model could be, "If the user is interested in entertainment and is currently in a positive emotional state, generate an optimistic news title. For example, 'The latest movie is a huge hit!'"

[0350] This system provides information that takes into account the user's preferences and emotional state, thereby reducing stress caused by information overload and helping to maintain the user's mental health.

[0351] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0352] Step 1:

[0353] When a user accesses the application, a new user registration screen appears. At this point, the user enters information such as their name, email address, password, genres and topics of interest, font size, color, preferred language, region, number and length of news characters, etc. This information is sent from the device to the server as the user's individual setting data.

[0354] Input: User's personal information (name, email address, password, genre, topic, font size, color, language, region, number of characters and length of news)

[0355] Output: Sending configuration information from the device to the server

[0356] Step 2:

[0357] The server receives the user's individual setting information sent from the terminal and stores it in a database. This database is used to centrally manage the individual setting information of all users.

[0358] Input: User personalized information sent from the device

[0359] Output: User personalization information stored in the database

[0360] Step 3:

[0361] The server accesses multiple news sources (e.g., news sites, RSS feeds, news APIs) at regular intervals to automatically collect new news data, which is then stored in a database in a specific format (e.g., JSON, XML).

[0362] Input: Latest news data from news sources

[0363] Output: Latest news data stored in a database

[0364] Step 4:

[0365] The server retrieves user preferences and settings from the database, and uses this information to filter the collected news data and extract only news that matches the user's interests and settings.

[0366] Input: User preferences and settings information and latest news data from a database

[0367] Output: Filtered news data

[0368] Step 5:

[0369] The server uses AI algorithms (e.g., natural language processing models, generative AI models) to summarize the filtered news data. The summary is a concise representation of the main points, and may also include related news and other perspectives.

[0370] Input: Filtered news data

[0371] Output: Summarized news data and related information

[0372] Step 6:

[0373] The device's built-in emotion recognition engine uses the camera and microphone to analyze the user's facial expressions and tone of voice, and then uses machine learning models to identify the user's emotional state.

[0374] Input: User facial and voice data via camera and microphone

[0375] Output: Analyzed sentiment data

[0376] Step 7:

[0377] The device sends the acquired emotional data to the server, which then adjusts the content and priority of the news list based on this data. For example, if the user is in a positive emotional state, news with positive content will be displayed first.

[0378] Input: Emotion data sent from the device

[0379] Output: Adjusted news list

[0380] Step 8:

[0381] The server generates a news list based on the user's preferences and sentiment data, which is customized for each user.

[0382] Input: User preferences, settings, and emotional data

[0383] Output: A personalized news list

[0384] Step 9:

[0385] The server sends the generated news list to the terminal using a secure protocol (e.g. HTTPS, WebSocket).

[0386] Input: personalized news list

[0387] Output: News list delivered to the device

[0388] Step 10:

[0389] The terminal displays the received news list on the user interface and provides it to the user, who then checks the news list and provides feedback.

[0390] Input: News list sent from the server

[0391] Output: Display the news list in a user interface

[0392] Step 11:

[0393] Users provide feedback such as "like" or "not interested" to the displayed news, which is then sent from the device to the server.

[0394] Input: User feedback

[0395] Output: Sending feedback from the device to the server

[0396] Step 12:

[0397] The server collects user feedback and stores it in a database, which is used to retrain the AI ​​algorithm to improve the accuracy of generating news lists.

[0398] Input: User feedback

[0399] Output: Retrained AI algorithm and improved news list generation accuracy

[0400] (Application example 2)

[0401] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0402] Conventional news delivery systems only consider the user's preferences and interests, ignoring the user's emotional state. As a result, users may feel stressed due to information overload, or the news provided may not match their mood at the time. Furthermore, when news is provided in an autonomous vehicle, passengers may not be able to relax while driving. To solve these problems, a personalized news delivery system that considers both the user's preferences and emotional state is needed.

[0403] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting information related to preferences and interests input by the user; means for collecting information data from multiple information sources; means for filtering the collected information data based on the user's preferences and interests and generating a summary; means for generating an information list personalized for each user and distributing it to the device; means for collecting user feedback and relearning to improve the accuracy of generating the information list; means for recognizing the user's emotional state based on facial expressions and tone of voice; and means for adjusting the priority and content of the information list based on the user's emotional state. This enables an optimal news experience that takes into account the user's preferences and emotional state.

[0404] A "user" is a person who uses the system.

[0405] "Information about preferences and interests" includes information such as the genres and topics, visual style, language, and region in which the user is interested.

[0406] "Sources" are sources that provide news data, such as news sites, RSS feeds, and news APIs.

[0407] "Information data" is data collected from information sources such as news, articles, and reports.

[0408] "Filtering" is the process of selecting appropriate data from collected information data based on the user's preferences and interests.

[0409] The "summary" is a concise summary of the filtered information data.

[0410] An "information list" is a list of news and articles that has been filtered and summarized and is provided to the user.

[0411] "Devices" refer to devices such as smartphones, tablets, and head-mounted displays installed inside autonomous vehicles.

[0412] "Feedback" refers to ratings and comments such as "like" or "not interested" that users make about the displayed news.

[0413] "Retraining" is the process of using collected feedback information to refine the system's algorithms and improve the accuracy of the information list.

[0414] "Emotional state" refers to the psychological state of the user, which is analyzed from facial expressions and tone of voice.

[0415] "Priority and content adjustment" is the process of adapting the display order and content of news and articles in an information list based on the user's emotional state.

[0416] This invention combines an emotion engine with a system that provides news tailored to the user's preferences and interests to provide an optimal news experience that matches the emotional state of each individual user. The following describes the processing content of the program and the hardware and software used to realize this system.

[0417] Registering users and setting preferences

[0418] When a user accesses the application, a new user registration screen is displayed. The user enters basic information such as name, email address, and password, as well as genres and topics of interest (e.g., politics, economics, entertainment). The user also sets visual styles such as font size, color, preferred language, region, and number and length of news characters. This information is sent from the device to the server, where it is stored in a database.

[0419] News gathering

[0420] The server periodically accesses multiple news sources (e.g., news sites, RSS feeds, news APIs) to collect the latest news data, which is then stored in the server's database.

[0421] News analysis based on user preferences

[0422] The server retrieves user preferences and settings from the database and filters the collected news data based on the user's preferences. It considers criteria such as genre, topic, language, region, and word count, and then uses an AI algorithm to summarize the filtered news. In some cases, related news and information from multiple perspectives are also added.

[0423] Introducing the Emotion Engine

[0424] The device's built-in emotion engine analyzes the user's facial expressions and tone of voice to recognize their emotional state. This emotion data is sent from the device to a server, which then adjusts the priority and content of the news list based on the emotion data.

[0425] Personalized news generation

[0426] The server generates an optimized news list based on the user's preferences and sentiment data, which is stored in a database and linked to the user's account.

[0427] News distribution to users

[0428] The server transmits the news list to the user's terminal, which displays the news list on a user interface.

[0429] User feedback and retraining

[0430] Users provide feedback on the displayed news, such as "like" or "not interested," which is then sent from the device to the server and stored in a database. The server then uses the feedback to retrain the AI ​​algorithm and improve the accuracy of generating news lists.

[0431] For example, if a user is interested in entertainment in an autonomous vehicle, the emotion engine will recognize the user's positive emotional state and the server will prioritize entertainment news with optimistic content to add to the list. Conversely, if the user is in a negative emotional state, the server will include positive news articles to improve the user's mood.

[0432] Example prompt sentence:

[0433] Generate sample code for a system that takes user preferences into account and uses an emotion engine to provide the most appropriate news articles. This system is intended for use in self-driving cars. It uses the in-car camera and microphone to analyze passenger emotions in real time and prioritizes the display of news articles according to their emotional state. The system continuously optimizes the news suggestions based on passenger feedback.

[0434] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0435] Step 1: Register and set your preferences

[0436] When a user logs in to the application, a new user registration screen is displayed. The user enters basic information such as name, email address, and password, as well as the genres and topics they are interested in. They also set visual styles such as font size and color, preferred language, region, and number and length of news characters. This input data is sent from the device to the server, where it is stored in a database.

[0437] Step 2: Gathering news

[0438] The server periodically accesses multiple news sources to collect the latest news data. This input data is obtained from various news sites, RSS feeds, news APIs, etc. and stored in a database on the server. The server analyzes the news title, content, publication time, images, etc., and stores them in a structured database.

[0439] Step 3: Analyzing and filtering news based on user preferences

[0440] The server retrieves user preferences and settings from the database and uses them as input to filter the collected news data. In this step, it considers criteria such as genre, topic, language, region, and word count to select news that matches the user's interests. The filtered news data is output and then sent to the summarization process.

[0441] Step 4: Generate news summaries and add related news

[0442] The server uses AI algorithms to summarize the filtered news and also adds related news and information from multiple perspectives. The input data is the filtered news data, and from this it generates summaries and related information. The output is a summarized news list.

[0443] Step 5: Analyze the user's emotional state with the emotion engine

[0444] The device uses a camera and microphone to capture the user's facial expressions and tone of voice. This captured data is analyzed on the device to recognize the user's emotional state. The emotional data is generated as output and sent to the server.

[0445] Step 6: Adjusting the news list based on emotional state

[0446] The server obtains the emotional data and adjusts the ranking and content of the news list based on it. The input data are the emotional data and the summarized news list, and the adjustment is made based on these. The output is a news list optimized based on the emotional state.

[0447] Step 7: Generate and deliver personalized news

[0448] The server generates an optimized news list for each user and stores it in a database. The news list is then delivered to the autonomous vehicle's terminal for display. The input data is the adjusted news list, and the output is the news list displayed on the device.

[0449] Step 8: User feedback and retraining

[0450] Users provide feedback on the displayed news, such as "like" or "not interested." This feedback data is sent from the device to the server, which stores it in a database. The server then retrains the AI ​​algorithm based on the collected feedback to improve the accuracy of news list generation. The input data is the feedback information, and the output is an improved algorithm.

[0451] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0452] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0453] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0454] [Second embodiment]

[0455] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0456] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0457] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0458] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0459] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0460] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0461] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0462] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0463] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0464] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0465] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0466] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0467] The present invention is a system that customizes news based on a user's preferences and interests, providing a personalized news experience. Below, we will create a program for this system and explain each processing step in natural language.

[0468] Registering users and setting preferences

[0469] 1. When a user accesses the application for the first time, a new user registration screen is displayed.

[0470] 2. Users enter basic information such as their name, email address, and password, and also select genres and topics of interest (e.g., politics, economics, entertainment).

[0471] 3. Users set visual styles such as font size, color, preferred language, region, word count and length of news.

[0472] 4. The above information is sent from the user's device to the server, which stores it in a database.

[0473] News gathering

[0474] 1. The server periodically accesses multiple predefined news sources (e.g., news sites, RSS feeds, news APIs) to collect the latest news data.

[0475] 2. The collected news data is stored in a database on the server.

[0476] News analysis based on user preferences

[0477] 1. The server retrieves user preferences and settings from a database.

[0478] 2. The server filters the collected news data based on the user's preferences and interests, using criteria such as genre, topic, language, region, and word count.

[0479] 3. The server uses AI algorithms to generate filtered news summaries, sometimes supplemented with related news and perspectives.

[0480] Personalized news generation

[0481] 1. The server generates a news list optimized for each user.

[0482] 2. This news list is stored in a database on the server and linked to the user's account.

[0483] News distribution to users

[0484] 1. The server sends a personalized news list to the user's device.

[0485] 2. The user's device displays this news list on the user interface so that the user can check it.

[0486] User feedback and retraining

[0487] 1. Users can provide feedback on the displayed news, such as "like" or "not interested."

[0488] 2. This feedback information is sent from the device to the server, where it is stored in a database.

[0489] 3. The server uses this feedback to retrain its AI algorithms to improve the accuracy of future news list generation.

[0490] For example, if a user prefers the "Economy" genre and selects a "long-form" and "image and video-focused" style, the server will collect relevant economic news, analyze it in detail, and provide an optimized news list. The user can review this on their device and provide feedback on articles they find interesting. This feedback will then be reflected in the next news list generation.

[0491] In this way, the system provides a news experience optimized to the user's preferences, reducing the stress and time wasted caused by information overload.

[0492] The processing flow will be explained below.

[0493] Step 1:

[0494] A user accesses the application and is presented with a new user registration screen.

[0495] Step 2:

[0496] Users enter basic information such as their name, email address, and password, as well as genres and topics of interest (e.g., politics, economics, entertainment), and set visual styles such as font size, color, preferred language, region, and word count and length of news.

[0497] Step 3:

[0498] The terminal collects this information and sends it to the server.

[0499] Step 4:

[0500] The server stores the received user information and setting information in a database.

[0501] Step 5:

[0502] The server periodically accesses multiple predefined news sources (e.g., news sites, RSS feeds, news APIs) to collect news data.

[0503] Step 6:

[0504] The collected news data is stored in a database on the server.

[0505] Step 7:

[0506] The server retrieves user preferences and settings from a database.

[0507] Step 8:

[0508] The server filters the news data based on the user's preferences, such as genre, topic, language, region, and word count.

[0509] Step 9:

[0510] The server uses AI algorithms to generate filtered news summaries, adding related news and perspectives as needed.

[0511] Step 10:

[0512] The server aggregates the summarized news and generates a personalized news list for each user.

[0513] Step 11:

[0514] The generated news list is stored in a database on the server and linked to the user's account.

[0515] Step 12:

[0516] The server sends the news list to the user's terminal.

[0517] Step 13:

[0518] The terminal displays the received news list on the user interface.

[0519] Step 14:

[0520] Users provide feedback on the displayed news, such as "like" or "not interested."

[0521] Step 15:

[0522] The terminal transmits the feedback information to the server.

[0523] Step 16:

[0524] The server stores the feedback information in a database and uses it to retrain the AI ​​algorithm.

[0525] Step 17:

[0526] The retrained AI algorithm will improve the accuracy of the next news list generation.

[0527] Example 1

[0528] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0529] In today's information society, users are faced with a vast amount of news information, making it difficult to find useful information. This information overload can be stressful and time-consuming for users. Furthermore, providing news tailored to users' preferences and interests requires collecting, filtering, personalizing, and incorporating feedback from news data, but efficient methods for doing so are lacking. Therefore, the present invention aims to solve these problems and provide a news experience optimized for users' preferences.

[0530] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0531] In this invention, the server includes means for collecting information on preferences and interests input by the user, means for collecting news data from multiple information sources, means for filtering the collected news data based on the user's preferences and interests and generating summaries, means for generating a news list personalized for each user and distributing it to the terminal, and means for collecting user feedback, relearning, and improving the accuracy of generating the news list. This makes it possible to provide a news experience optimized for the user's preferences and reduce stress and time wasted due to information overload.

[0532] A "user" is an individual or organization that uses the system to view news and enter information about their preferences and interests.

[0533] "Preferences and interests" refers to preferences such as genres and topics that interest the user, visual style, language, region, etc.

[0534] "Sources" refers to digital media such as multiple websites, data feeds, and news APIs that provide news data.

[0535] "News data" refers to data collected from various sources, including news articles, reports, and media content.

[0536] "Filtering" is the process of selecting highly relevant information from collected news data based on the user's preferences and interests.

[0537] A "summary" refers to a text or media that compactly summarizes filtered news data and succinctly expresses the main content.

[0538] A "personalized news list" is a list of news presented in a way that is optimized for each user, and is generated based on the user's preferences and feedback.

[0539] "Feedback" refers to opinions and thoughts about news provided by users, such as "like" or "not interested."

[0540] "Relearning" is the process of updating the AI ​​algorithm based on collected feedback to improve the accuracy of generating news lists in future.

[0541] The present invention is a system that customizes news based on a user's preferences and interests, providing a personalized news experience. Below, we will explain in natural language the means for generating programs for this system and the processing based on them.

[0542] First, this system is composed of multiple components and has three main actors: the server, the terminal, and the user. The server is responsible for collecting data, filtering, generating summaries, generating and distributing news lists, and collecting feedback and relearning. The terminal provides the user interface, sending input from the user to the server and displaying responses from the server. The user interacts with the system, inputting required information and providing feedback.

[0543] 1. User Registration and Preferences

[0544] When a user accesses the application for the first time, a new user registration screen is displayed. The user enters basic information such as name, email address, and password, and also selects the genres and topics they are interested in. They also set visual style preferences (font size, color, preferred language, region, number of characters and length of news). This information is sent from the user's device to the server, which stores it in a database. In terms of specific hardware, the server is a computer with a high-performance CPU, while the device can be a smartphone or PC. In terms of software, Python and SQL are used on the server side, and JavaScript, HTML, and CSS are used on the device side.

[0545] 2. News gathering

[0546] The server periodically accesses multiple predefined news sources (e.g., news websites, RSS feeds, news APIs) to collect the latest news data using web scraping techniques (Python libraries Beautiful Soup and Selenium) and API calls, and stores the collected news data in a database on the server.

[0547] 3. Analyzing news based on user preferences

[0548] The server retrieves user preferences and settings from the database and filters the collected news data based on them. Filtering criteria include genre, topic, language, region, and word count. Furthermore, it uses AI algorithms (e.g., natural language processing models such as GPT-3 and BERT) to generate summaries of the filtered news. Related news and information from multiple perspectives are also added.

[0549] 4. Personalized news generation and delivery

[0550] The server generates a news list optimized for each user, stores it in a database, and associates it with the user's account. This news list is periodically sent to the user's device, which displays it on the user interface. The user can then review the list, select articles of interest, and view them.

[0551] 5. User Feedback and Retraining

[0552] Users provide feedback on the displayed news, such as "Like" or "Not Interested." This feedback information is sent from the device to the server and stored in a database. The server uses the received feedback to retrain the AI ​​algorithm and improve the accuracy of news list generation.

[0553] Specific examples

[0554] For example, if a user prefers the "Economy" genre and selects "Long Text" and "Image and Video Focused" styles, the server will collect relevant economic news, analyze it in detail, and provide it as an optimized news list. The user can check this on their device and provide feedback on articles that interest them. Specific examples of prompts include the following:

[0555] "Please create a news list that displays long economic news articles with images and videos as the main content."

[0556] In this way, the system can provide a news experience that is optimized to the user's preferences, reducing the stress and time wasted caused by information overload.

[0557] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0558] Step 1: Registering a user

[0559] Input: The user enters their name, email address, password, genres and topics of interest, and visual style (font size, color, language, region, number and length of news).

[0560] Operation: The user enters the information they provided into the input form and clicks the submit button. At this time, validation checks are performed on the input data (e.g., checking that required fields are entered, checking the format of the email address).

[0561] Output: Data about the user's basic information and preferences is sent from the device to the server, which stores this data in a database.

[0562] Step 2: Gathering news

[0563] Input: The server is pre-configured with a list of news source URLs and API information.

[0564] How it works: The server periodically contacts predefined news sources (news sites, RSS feeds, news APIs, etc.) and uses web scraping techniques and API calls to gather the latest news data.

[0565] Output: The collected news data is stored in a database on the server.

[0566] Step 3: Analyzing news based on user preferences

[0567] Input: The server retrieves user preferences and settings from the database, and also inputs collected news data.

[0568] How it works: The server filters news data based on user preferences and settings (genre, topic, language, region, word count, etc.), extracts news based on the conditions using Python's Pandas library, and then generates a summary of the filtered news using an AI algorithm (e.g., GPT-3 or BERT).

[0569] Output: Filtered and summarized news data.

[0570] Step 4: Generate a personalized news list

[0571] Input: Filtered and summarized news data.

[0572] How it works: The server generates a news list optimized for each user. News items are tagged and ranked to reflect the user's preferences. The generated news list is saved in JSON format.

[0573] Output: The generated news list is stored in the server's database and associated with the user's account.

[0574] Step 5: Delivering news to users

[0575] Input: The generated personalized news list.

[0576] How it works: The server periodically delivers news lists to the user's device, sending data via GET requests using the REST API.

[0577] Output: The news list is sent to the terminal, which displays the received news list on its user interface.

[0578] Step 6: User feedback and retraining

[0579] Input: Feedback provided by the user regarding the news displayed (e.g. "Like" or "Not interested").

[0580] How it works: Users provide feedback on the displayed news by clicking or tapping. The device sends the feedback information to the server, which stores it in a database. The server then retrains the AI ​​algorithm and processes the results in a batch process to improve the accuracy of the next news list generation.

[0581] Output: An updated AI model and improved accuracy of news list generation based on it.

[0582] (Application example 1)

[0583] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0584] Currently, many news platforms are unable to provide news based on users' individual preferences and interests, resulting in stress and time wasted due to information overload. Furthermore, the news provided is not optimized for users' preferences, resulting in differences in how users perceive and value the information. Furthermore, insufficient news summaries and related information mean users are unable to quickly grasp the information they need.

[0585] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0586] In this invention, the server includes means for collecting information on preferences and interests input by the user, means for collecting news data from multiple news sources, means for filtering the collected news data based on the user's preferences and interests and generating summaries, means for generating a news list personalized for each user and distributing it to the terminal, means for collecting user feedback and relearning to improve the accuracy of generating the news list, and means for summarizing the collected news data using an artificial intelligence model. This makes it possible to reduce stress caused by information overload and provide news optimized to the user's preferences.

[0587] "User" refers to a person who uses the news application.

[0588] "Preferences and interests" refers to personal preferences such as the genres and topics that interest a user, visual style, language, and region.

[0589] "News source" refers to an external source of news data, including news sites, RSS feeds, news APIs, etc.

[0590] "News data" refers to a collection of information, such as articles and reports, collected from news sources.

[0591] "Filtering" refers to the process of selecting collected news data based on the user's preferences and interests.

[0592] A "summary" is a concise summary of the main points or content of a news article.

[0593] A "personalized news list" refers to a list of news articles optimized for each user.

[0594] "Device" refers to the device used to receive the personalized news list, including a smartphone, tablet, or computer.

[0595] "Feedback" refers to user-provided ratings and opinions on news articles.

[0596] "Retraining" refers to the process of using collected feedback information to retrain the algorithm to improve the accuracy of the system.

[0597] "Artificial intelligence model" refers to the machine learning algorithms and models used to generate summaries for collected news data.

[0598] This invention is a system that customizes news based on a user's preferences and interests, providing a personalized news experience. The program and processing of this system are described below.

[0599] Registering users and setting preferences

[0600] Users first enter their basic information into the news application, along with personal preferences such as genres and topics of interest, visual style, language, and region. This information is sent from the user's device to the server and stored in a database. This information collection allows the system to understand the user's individual preferences and use them for subsequent processing.

[0601] News gathering

[0602] The server periodically collects news data from multiple predefined news sources, including news websites, RSS feeds, and news APIs. This collected news data is then stored in the server's database. During this process, technologies such as APIs are used to ensure that the collected data is up-to-date and abundant.

[0603] News analysis based on user preferences

[0604] The server retrieves user preferences and settings from the database and filters the collected news data based on the user's preferences, using criteria such as genre, topic, language, region, and word count. During this process, artificial intelligence models and machine learning algorithms are used to filter and summarize the news.

[0605] Personalized news generation

[0606] Based on the filtered news data, the server generates a news list optimized for each user. This news list is stored in the server's database and linked to the user's account. The generated news list efficiently provides information that the user is interested in.

[0607] News distribution to users

[0608] The server sends the personalized news list to the user's device, which displays it. This process can be carried out on devices such as smartphones or tablets.

[0609] User feedback and retraining

[0610] Users can provide feedback on the displayed news, such as "Like" or "Not Interested." This feedback information is sent from the device to the server and stored in a database. The server uses this feedback to retrain the AI ​​algorithm and improve the accuracy of future news list generation.

[0611] Program processing

[0612] The system is implemented using Python, Flask, the Requests library, and a news API. For example, the news API is used to collect news data, Flask is used for user registration and feedback processing, and an artificial intelligence model (e.g., OpenAI's GPT model) is used to generate news summaries.

[0613] As a concrete example, the following prompt sentence will be used.

[0614] Prompt Sentence Examples

[0615] Generate a summary of the following news article:

[0616] The content of the news article goes here.

[0617] summary:

[0618] In this way, the system can provide a news experience optimized to the user's preferences, reducing stress and time wasted due to information overload.

[0619] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0620] Step 1:

[0621] Sign up and set your preferences

[0622] When a user first accesses the application, they launch it and enter information such as their name, email address, password, genres and topics of interest, visual style, preferred language, and region.

[0623] The terminal transmits this input information to the server.

[0624] The server stores the received information in a database.

[0625] Input: Name, Email, Password, Genre, Topic, Visual Style, Language, Region

[0626] Data processing: The server formats this information into structured data and stores it in a database.

[0627] Output: User profile stored in the database

[0628] Step 2:

[0629] News gathering

[0630] The server periodically accesses multiple news sources such as news APIs to collect news data.

[0631] The news data is stored in a database on the server.

[0632] Input: News API endpoint

[0633] Data processing: The server converts the acquired news data into the required structure and records it in the database.

[0634] Output: News data stored in a database

[0635] Step 3:

[0636] News analysis based on user preferences

[0637] The server retrieves user preferences and settings from a database.

[0638] The server filters the collected news data based on user settings, such as genre, topic, language, region, and word count.

[0639] Generate summaries of filtered news data using artificial intelligence models.

[0640] Input: User profiles and news data in a database

[0641] Data processing: filtering, summarization

[0642] Output: filtered and summarized news data

[0643] Step 4:

[0644] Personalized news generation

[0645] The server generates a news list optimized for each user based on the filtered and summarized news data.

[0646] This news list is stored in a database on the server and linked to the user's account.

[0647] Input: filtered and summarized news data

[0648] Data processing: News list generation, linking to user accounts

[0649] Output: A personalized news list

[0650] Step 5:

[0651] News distribution to users

[0652] The server sends a personalized news list to the user's terminal.

[0653] The terminal displays the received news list on the user interface.

[0654] Input: personalized news list

[0655] Data processing: Data transmission via communication

[0656] Output: A personalized news list displayed on the device.

[0657] Step 6:

[0658] User feedback and retraining

[0659] Users provide feedback on news lists (such as "like" or "not interested").

[0660] The terminal transmits the feedback information to the server.

[0661] The server stores the feedback information in a database and retrains the AI ​​algorithm.

[0662] Input: User feedback

[0663] Data processing: saving feedback information and re-learning process

[0664] Output: Updated AI model and improved accuracy of future news list generation

[0665] In this way, through a series of processing steps, the system provides a personalized news experience tailored to the user's preferences.

[0666] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0667] The present invention is a system that provides news tailored to the user's preferences and interests, and also combines an emotion engine to provide an optimal news experience according to the emotional state of each individual user. Below, we will explain the program processing and specific examples of this system.

[0668] Registering users and setting preferences

[0669] 1. A user accesses the application and is presented with a new user registration screen.

[0670] 2. Users enter basic information such as their name, email address, and password, as well as their preferred genres and topics (e.g., politics, economics, entertainment), and set visual styles such as font size, color, preferred language, region, and number and length of news characters.

[0671] 3. The information provided by the user is sent from the device to the server, where it is stored in a database.

[0672] News gathering

[0673] 1. The server periodically accesses multiple news sources (e.g., news sites, RSS feeds, news APIs) to collect the latest news data.

[0674] 2. The collected news data is stored in a database on the server.

[0675] News analysis based on user preferences

[0676] 1. The server retrieves user preferences and settings from a database.

[0677] 2. The server filters the collected news data based on the user's preferences, taking into account criteria such as genre, topic, language, region, and word count.

[0678] 3. The server uses AI algorithms to summarize the filtered news, sometimes adding related news and other perspectives.

[0679] Introducing the Emotion Engine

[0680] 1. The emotion engine installed on the device uses the user's camera and microphone to analyze facial expressions and tone of voice to recognize the user's emotional state.

[0681] 2. The recognized emotion data is sent from the device to the server.

[0682] 3. The server adjusts the priority and content of the news list based on the emotion data.

[0683] Personalized news generation

[0684] 1. The server generates an optimized news list based on the user's preferences and sentiment data.

[0685] 2. This news list is stored in a database and linked to the user's account.

[0686] News distribution to users

[0687] 1. The server sends the news list to the user's terminal.

[0688] 2. The terminal displays the news list on the user interface so that the user can check it.

[0689] User feedback and retraining

[0690] 1. Users provide feedback on the displayed news, such as "like" or "not interested."

[0691] 2. The feedback information is sent from the device to the server and stored in a database.

[0692] 3. The server uses the feedback to retrain the AI ​​algorithm to improve the accuracy of generating news lists.

[0693] For example, if a user likes the "Entertainment" genre and the emotion engine recognizes the user's positive emotional state, the server will prioritize filtering entertainment news containing optimistic content and add it to the news list along with summaries. On the other hand, if the user is in a negative emotional state, the server will include positive news articles to improve the user's mood.

[0694] In this way, the system provides a personalized news experience that takes into account the user's preferences and emotional state, reducing stress and time wasted due to information overload and promoting the user's mental health.

[0695] The processing flow will be explained below.

[0696] Step 1:

[0697] A user accesses the application and is presented with a new user registration screen.

[0698] Step 2:

[0699] Users enter basic information such as their name, email address, and password, as well as their preferred genres and topics (e.g., politics, economics, entertainment), and set visual styles such as font size, color, language, region, and word count and length of news.

[0700] Step 3:

[0701] The terminal collects this information and sends it to the server.

[0702] Step 4:

[0703] The server stores the received user information and setting information in a database.

[0704] Step 5:

[0705] The server periodically accesses multiple predefined news sources (e.g., news sites, RSS feeds, news APIs) to collect the latest news data.

[0706] Step 6:

[0707] The collected news data is stored in a database on the server.

[0708] Step 7:

[0709] The server retrieves user preferences and settings from a database.

[0710] Step 8:

[0711] The server filters the news data based on the user's preferences, such as genre, topic, language, region, and word count.

[0712] Step 9:

[0713] The server uses AI algorithms to generate filtered news summaries, adding related news and perspectives as needed.

[0714] Step 10:

[0715] The emotion engine installed on the device uses the user's camera and microphone to analyze facial expressions and tone of voice to recognize the user's emotional state.

[0716] Step 11:

[0717] The recognized emotion data is transmitted from the terminal to the server.

[0718] Step 12:

[0719] The server adjusts the priority and content of the news list based on the emotional data, selecting news according to the user's emotional state, such as positive or negative emotions.

[0720] Step 13:

[0721] The server generates a personalized news list taking into account the emotional data and user preferences.

[0722] Step 14:

[0723] The generated news list is stored in a database on the server and linked to the user's account.

[0724] Step 15:

[0725] The server sends the news list to the user's terminal.

[0726] Step 16:

[0727] The terminal displays the news list on the user interface so that the user can check it.

[0728] Step 17:

[0729] Users provide feedback on the displayed news, such as "like" or "not interested."

[0730] Step 18:

[0731] The feedback information is sent from the terminal to the server.

[0732] Step 19:

[0733] The server stores the feedback information in a database and uses it to retrain the AI ​​algorithm.

[0734] Step 20:

[0735] The retrained AI algorithm will improve the accuracy of the next news list generation.

[0736] Example 2

[0737] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0738] Current news delivery systems primarily provide news based on users' preferences and interests, but few systems consider the user's emotional state when providing news. This can result in users receiving news that is inappropriate for their current emotional state, potentially adversely affecting how they receive and understand information. Furthermore, there are insufficient mechanisms for reducing stress and fatigue caused by information overload, making it difficult to maintain users' mental health.

[0739] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting information on preferences and interests input by the user, means for collecting data from multiple information sources, means for filtering the collected data based on the user's preferences and interests and generating a summary, means for analyzing the user's emotional state using an emotion recognition engine of the terminal and adjusting the data based on this information, means for generating a list personalized for each user and delivering it to the terminal, and means for collecting user feedback, re-learning, and improving the accuracy of list generation. This enables personalized news delivery that takes into account not only the user's preferences and interests but also their emotional state.

[0740] "User-entered preference and interest information" refers to personal preference information provided by individual users, such as genres, topics, types of news, and visual styles that interest them.

[0741] "Multiple sources" refers to various news sources, such as news sites, RSS feeds, and news APIs.

[0742] "Data filtering" is the process of selecting collected news data based on the user's preferences and interests.

[0743] "Generating a summary" is the process of shortening the filtered news data into a concise format that includes the main points.

[0744] An "emotion recognition engine" is software that uses the device's built-in camera and microphone to analyze the user's facial expressions and tone of voice and recognize their emotional state.

[0745] "Adjusting data" is a process of changing the contents and priorities of the news list based on the emotion data obtained from the emotion recognition engine.

[0746] A "personalized list" is a collection of news articles that is customized based on an individual user's preferences and emotional state.

[0747] "Delivering to terminal" refers to the process of sending the generated news list to the device used by the user.

[0748] "Feedback" refers to user-provided ratings and reactions to news articles, such as "like" or "not interested."

[0749] "Retraining" is the process of improving the AI ​​algorithm based on collected feedback to improve the accuracy of generating news lists.

[0750] This invention is a system that provides optimal information experiences according to the emotional state of each individual user by combining a system that provides information tailored to the user's preferences and interests with an emotion recognition engine. The specific configuration and operating procedures for implementing this system are described below.

[0751] Registering users and setting preferences

[0752] 1. When a user accesses the application, a new user registration screen appears, where the user enters basic information such as name, email address, and password, as well as the genres and topics of interest.

[0753] 2. The user further configures the visual style, such as font size, color, language, region, and length and character count of the information.

[0754] 3. The information entered from the device is sent to the server. For security reasons, an encrypted protocol (e.g., HTTPS) is used for this transmission.

[0755] 4. The server stores the received information in a database.

[0756] Collection of information

[0757] 1. The server automatically collects data from multiple sources (e.g., websites, RSS feeds, APIs) and this collection is configured to occur periodically.

[0758] 2. Data from each source is collected on the server in a standard format (e.g., JSON, XML).

[0759] 3. The server stores the collected data in a database and keeps the information up to date.

[0760] Analyzing information based on user preferences

[0761] 1. The server retrieves user preferences and settings from a database, including information about genre, topic, language, region, and character count.

[0762] 2. The server filters the collected data based on the user's preferences. For example, if a user is interested in the entertainment genre, it will only show articles in that genre.

[0763] 3. The server uses AI algorithms (e.g., natural language processing models, generative AI models) to summarize the filtered data and add relevant information and multifaceted perspectives.

[0764] Introducing the Emotion Engine

[0765] 1. The device's built-in emotion recognition engine uses the camera and microphone to analyze the user's facial expressions and tone of voice to recognize their emotional state. This analysis uses machine learning models (e.g., facial expression recognition model, voice emotion recognition model).

[0766] 2. The recognized emotion data is sent from the device to the server.

[0767] 3. The server adjusts the priority and content of the information list based on the emotional data. For example, when the user is in a positive emotional state, information with positive content is displayed preferentially.

[0768] Generate personalized information

[0769] 1. The server generates an optimal information list based on the user's preferences and emotional data. This list is customized for each user.

[0770] 2. The generated information list is stored in a database and linked to each user's account.

[0771] Information distribution to users

[0772] 1. The server sends the optimized information list to the device using a secure communication protocol (e.g., HTTPS, WebSocket).

[0773] 2. The terminal displays the received information list on the user interface for easy access by the user.

[0774] User feedback and retraining

[0775] 1. The user provides feedback on the displayed information, such as "like" or "not interested."

[0776] 2. The device sends user feedback to the server and receives real-time ratings.

[0777] 3. The server retrains the AI ​​algorithm based on the feedback to improve the accuracy of generating information lists.

[0778] For example, if a user likes the "Entertainment" genre and the emotion engine recognizes the user's positive emotional state, the server will prioritize filtering entertainment information containing optimistic content and add it to the information list along with a summary. On the other hand, if the user is in a negative emotional state, the server will adjust the information list to include positive information to improve the user's mood.

[0779] An example of a prompt sentence to input to the generative AI model could be, "If the user is interested in entertainment and is currently in a positive emotional state, generate an optimistic news title. For example, 'The latest movie is a huge hit!'"

[0780] This system provides information that takes into account the user's preferences and emotional state, thereby reducing stress caused by information overload and helping to maintain the user's mental health.

[0781] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0782] Step 1:

[0783] When a user accesses the application, a new user registration screen appears. At this point, the user enters information such as their name, email address, password, genres and topics of interest, font size, color, preferred language, region, number and length of news characters, etc. This information is sent from the device to the server as the user's individual setting data.

[0784] Input: User's personal information (name, email address, password, genre, topic, font size, color, language, region, number of characters and length of news)

[0785] Output: Sending configuration information from the device to the server

[0786] Step 2:

[0787] The server receives the user's individual setting information sent from the terminal and stores it in a database. This database is used to centrally manage the individual setting information of all users.

[0788] Input: User personalized information sent from the device

[0789] Output: User personalization information stored in the database

[0790] Step 3:

[0791] The server accesses multiple news sources (e.g., news sites, RSS feeds, news APIs) at regular intervals to automatically collect new news data, which is then stored in a database in a specific format (e.g., JSON, XML).

[0792] Input: Latest news data from news sources

[0793] Output: Latest news data stored in a database

[0794] Step 4:

[0795] The server retrieves user preferences and settings from the database, and uses this information to filter the collected news data and extract only news that matches the user's interests and settings.

[0796] Input: User preferences and settings information and latest news data from a database

[0797] Output: Filtered news data

[0798] Step 5:

[0799] The server uses AI algorithms (e.g., natural language processing models, generative AI models) to summarize the filtered news data. The summary is a concise representation of the main points, and may also include related news and other perspectives.

[0800] Input: Filtered news data

[0801] Output: Summarized news data and related information

[0802] Step 6:

[0803] The device's built-in emotion recognition engine uses the camera and microphone to analyze the user's facial expressions and tone of voice, and then uses machine learning models to identify the user's emotional state.

[0804] Input: User facial and voice data via camera and microphone

[0805] Output: Analyzed sentiment data

[0806] Step 7:

[0807] The device sends the acquired emotional data to the server, which then adjusts the content and priority of the news list based on this data. For example, if the user is in a positive emotional state, news with positive content will be displayed first.

[0808] Input: Emotion data sent from the device

[0809] Output: Adjusted news list

[0810] Step 8:

[0811] The server generates a news list based on the user's preferences and sentiment data, which is customized for each user.

[0812] Input: User preferences, settings, and emotional data

[0813] Output: A personalized news list

[0814] Step 9:

[0815] The server sends the generated news list to the terminal using a secure protocol (e.g. HTTPS, WebSocket).

[0816] Input: personalized news list

[0817] Output: News list delivered to the device

[0818] Step 10:

[0819] The terminal displays the received news list on the user interface and provides it to the user, who then checks the news list and provides feedback.

[0820] Input: News list sent from the server

[0821] Output: Display the news list in a user interface

[0822] Step 11:

[0823] Users provide feedback such as "like" or "not interested" to the displayed news, which is then sent from the device to the server.

[0824] Input: User feedback

[0825] Output: Sending feedback from the device to the server

[0826] Step 12:

[0827] The server collects user feedback and stores it in a database, which is used to retrain the AI ​​algorithm to improve the accuracy of generating news lists.

[0828] Input: User feedback

[0829] Output: Retrained AI algorithm and improved news list generation accuracy

[0830] (Application example 2)

[0831] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0832] Conventional news delivery systems only consider the user's preferences and interests, ignoring the user's emotional state. As a result, users may feel stressed due to information overload, or the news provided may not match their mood at the time. Furthermore, when news is provided in an autonomous vehicle, passengers may not be able to relax while driving. To solve these problems, a personalized news delivery system that considers both the user's preferences and emotional state is needed.

[0833] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting information related to preferences and interests input by the user; means for collecting information data from multiple information sources; means for filtering the collected information data based on the user's preferences and interests and generating a summary; means for generating an information list personalized for each user and distributing it to the device; means for collecting user feedback and relearning to improve the accuracy of generating the information list; means for recognizing the user's emotional state based on facial expressions and tone of voice; and means for adjusting the priority and content of the information list based on the user's emotional state. This enables an optimal news experience that takes into account the user's preferences and emotional state.

[0834] A "user" is a person who uses the system.

[0835] "Information about preferences and interests" includes information such as the genres and topics, visual style, language, and region in which the user is interested.

[0836] "Sources" are sources that provide news data, such as news sites, RSS feeds, and news APIs.

[0837] "Information data" is data collected from information sources such as news, articles, and reports.

[0838] "Filtering" is the process of selecting appropriate data from collected information data based on the user's preferences and interests.

[0839] The "summary" is a concise summary of the filtered information data.

[0840] An "information list" is a list of news and articles that has been filtered and summarized and is provided to the user.

[0841] "Devices" refer to devices such as smartphones, tablets, and head-mounted displays installed inside autonomous vehicles.

[0842] "Feedback" refers to ratings and comments such as "like" or "not interested" that users make about the displayed news.

[0843] "Retraining" is the process of using collected feedback information to refine the system's algorithms and improve the accuracy of the information list.

[0844] "Emotional state" refers to the psychological state of the user, which is analyzed from facial expressions and tone of voice.

[0845] "Priority and content adjustment" is the process of adapting the display order and content of news and articles in an information list based on the user's emotional state.

[0846] This invention combines an emotion engine with a system that provides news tailored to the user's preferences and interests to provide an optimal news experience that matches the emotional state of each individual user. The following describes the processing content of the program and the hardware and software used to realize this system.

[0847] Registering users and setting preferences

[0848] When a user accesses the application, a new user registration screen is displayed. The user enters basic information such as name, email address, and password, as well as genres and topics of interest (e.g., politics, economics, entertainment). The user also sets visual styles such as font size, color, preferred language, region, and number and length of news characters. This information is sent from the device to the server, where it is stored in a database.

[0849] News gathering

[0850] The server periodically accesses multiple news sources (e.g., news sites, RSS feeds, news APIs) to collect the latest news data, which is then stored in the server's database.

[0851] News analysis based on user preferences

[0852] The server retrieves user preferences and settings from the database and filters the collected news data based on the user's preferences. It considers criteria such as genre, topic, language, region, and word count, and then uses an AI algorithm to summarize the filtered news. In some cases, related news and information from multiple perspectives are also added.

[0853] Introducing the Emotion Engine

[0854] The device's built-in emotion engine analyzes the user's facial expressions and tone of voice to recognize their emotional state. This emotion data is sent from the device to a server, which then adjusts the priority and content of the news list based on the emotion data.

[0855] Personalized news generation

[0856] The server generates an optimized news list based on the user's preferences and sentiment data, which is stored in a database and linked to the user's account.

[0857] News distribution to users

[0858] The server transmits the news list to the user's terminal, which displays the news list on a user interface.

[0859] User feedback and retraining

[0860] Users provide feedback on the displayed news, such as "like" or "not interested," which is then sent from the device to the server and stored in a database. The server then uses the feedback to retrain the AI ​​algorithm and improve the accuracy of generating news lists.

[0861] For example, if a user is interested in entertainment in an autonomous vehicle, the emotion engine will recognize the user's positive emotional state and the server will prioritize entertainment news with optimistic content to add to the list. Conversely, if the user is in a negative emotional state, the server will include positive news articles to improve the user's mood.

[0862] Example prompt sentence:

[0863] Generate sample code for a system that takes user preferences into account and uses an emotion engine to provide the most appropriate news articles. This system is intended for use in self-driving cars. It uses the in-car camera and microphone to analyze passenger emotions in real time and prioritizes the display of news articles according to their emotional state. The system continuously optimizes the news suggestions based on passenger feedback.

[0864] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0865] Step 1: Register and set your preferences

[0866] When a user logs in to the application, a new user registration screen is displayed. The user enters basic information such as name, email address, and password, as well as the genres and topics they are interested in. They also set visual styles such as font size and color, preferred language, region, and number and length of news characters. This input data is sent from the device to the server, where it is stored in a database.

[0867] Step 2: Gathering news

[0868] The server periodically accesses multiple news sources to collect the latest news data. This input data is obtained from various news sites, RSS feeds, news APIs, etc. and stored in a database on the server. The server analyzes the news title, content, publication time, images, etc., and stores them in a structured database.

[0869] Step 3: Analyzing and filtering news based on user preferences

[0870] The server retrieves user preferences and settings from the database and uses them as input to filter the collected news data. In this step, it considers criteria such as genre, topic, language, region, and word count to select news that matches the user's interests. The filtered news data is output and then sent to the summarization process.

[0871] Step 4: Generate news summaries and add related news

[0872] The server uses AI algorithms to summarize the filtered news and also adds related news and information from multiple perspectives. The input data is the filtered news data, and from this it generates summaries and related information. The output is a summarized news list.

[0873] Step 5: Analyze the user's emotional state with the emotion engine

[0874] The device uses a camera and microphone to capture the user's facial expressions and tone of voice. This captured data is analyzed on the device to recognize the user's emotional state. The emotional data is generated as output and sent to the server.

[0875] Step 6: Adjusting the news list based on emotional state

[0876] The server obtains the emotional data and adjusts the ranking and content of the news list based on it. The input data are the emotional data and the summarized news list, and the adjustment is made based on these. The output is a news list optimized based on the emotional state.

[0877] Step 7: Generate and deliver personalized news

[0878] The server generates an optimized news list for each user and stores it in a database. The news list is then delivered to the autonomous vehicle's terminal for display. The input data is the adjusted news list, and the output is the news list displayed on the device.

[0879] Step 8: User feedback and retraining

[0880] Users provide feedback on the displayed news, such as "like" or "not interested." This feedback data is sent from the device to the server, which stores it in a database. The server then retrains the AI ​​algorithm based on the collected feedback to improve the accuracy of news list generation. The input data is the feedback information, and the output is an improved algorithm.

[0881] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0882] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0883] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0884] [Third embodiment]

[0885] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0886] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0887] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0888] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0889] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0890] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0891] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0892] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0893] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0894] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0895] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0896] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0897] The present invention is a system that customizes news based on a user's preferences and interests, providing a personalized news experience. Below, we will create a program for this system and explain each processing step in natural language.

[0898] Registering users and setting preferences

[0899] 1. When a user accesses the application for the first time, a new user registration screen is displayed.

[0900] 2. Users enter basic information such as their name, email address, and password, and also select genres and topics of interest (e.g., politics, economics, entertainment).

[0901] 3. Users set visual styles such as font size, color, preferred language, region, word count and length of news.

[0902] 4. The above information is sent from the user's device to the server, which stores it in a database.

[0903] News gathering

[0904] 1. The server periodically accesses multiple predefined news sources (e.g., news sites, RSS feeds, news APIs) to collect the latest news data.

[0905] 2. The collected news data is stored in a database on the server.

[0906] News analysis based on user preferences

[0907] 1. The server retrieves user preferences and settings from a database.

[0908] 2. The server filters the collected news data based on the user's preferences and interests, using criteria such as genre, topic, language, region, and word count.

[0909] 3. The server uses AI algorithms to generate filtered news summaries, sometimes supplemented with related news and perspectives.

[0910] Personalized news generation

[0911] 1. The server generates a news list optimized for each user.

[0912] 2. This news list is stored in a database on the server and linked to the user's account.

[0913] News distribution to users

[0914] 1. The server sends a personalized news list to the user's device.

[0915] 2. The user's device displays this news list on the user interface so that the user can check it.

[0916] User feedback and retraining

[0917] 1. Users can provide feedback on the displayed news, such as "like" or "not interested."

[0918] 2. This feedback information is sent from the device to the server, where it is stored in a database.

[0919] 3. The server uses this feedback to retrain its AI algorithms to improve the accuracy of future news list generation.

[0920] For example, if a user prefers the "Economy" genre and selects a "long-form" and "image and video-focused" style, the server will collect relevant economic news, analyze it in detail, and provide an optimized news list. The user can review this on their device and provide feedback on articles they find interesting. This feedback will then be reflected in the next news list generation.

[0921] In this way, the system provides a news experience optimized to the user's preferences, reducing the stress and time wasted caused by information overload.

[0922] The processing flow will be explained below.

[0923] Step 1:

[0924] A user accesses the application and is presented with a new user registration screen.

[0925] Step 2:

[0926] Users enter basic information such as their name, email address, and password, as well as genres and topics of interest (e.g., politics, economics, entertainment), and set visual styles such as font size, color, preferred language, region, and word count and length of news.

[0927] Step 3:

[0928] The terminal collects this information and sends it to the server.

[0929] Step 4:

[0930] The server stores the received user information and setting information in a database.

[0931] Step 5:

[0932] The server periodically accesses multiple predefined news sources (e.g., news sites, RSS feeds, news APIs) to collect news data.

[0933] Step 6:

[0934] The collected news data is stored in a database on the server.

[0935] Step 7:

[0936] The server retrieves user preferences and settings from a database.

[0937] Step 8:

[0938] The server filters the news data based on the user's preferences, such as genre, topic, language, region, and word count.

[0939] Step 9:

[0940] The server uses AI algorithms to generate filtered news summaries, adding related news and perspectives as needed.

[0941] Step 10:

[0942] The server aggregates the summarized news and generates a personalized news list for each user.

[0943] Step 11:

[0944] The generated news list is stored in a database on the server and linked to the user's account.

[0945] Step 12:

[0946] The server sends the news list to the user's terminal.

[0947] Step 13:

[0948] The terminal displays the received news list on the user interface.

[0949] Step 14:

[0950] Users provide feedback on the displayed news, such as "like" or "not interested."

[0951] Step 15:

[0952] The terminal transmits the feedback information to the server.

[0953] Step 16:

[0954] The server stores the feedback information in a database and uses it to retrain the AI ​​algorithm.

[0955] Step 17:

[0956] The retrained AI algorithm will improve the accuracy of the next news list generation.

[0957] Example 1

[0958] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0959] In today's information society, users are faced with a vast amount of news information, making it difficult to find useful information. This information overload can be stressful and time-consuming for users. Furthermore, providing news tailored to users' preferences and interests requires collecting, filtering, personalizing, and incorporating feedback from news data, but efficient methods for doing so are lacking. Therefore, the present invention aims to solve these problems and provide a news experience optimized for users' preferences.

[0960] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0961] In this invention, the server includes means for collecting information on preferences and interests input by the user, means for collecting news data from multiple information sources, means for filtering the collected news data based on the user's preferences and interests and generating summaries, means for generating a news list personalized for each user and distributing it to the terminal, and means for collecting user feedback, relearning, and improving the accuracy of generating the news list. This makes it possible to provide a news experience optimized for the user's preferences and reduce stress and time wasted due to information overload.

[0962] A "user" is an individual or organization that uses the system to view news and enter information about their preferences and interests.

[0963] "Preferences and interests" refers to preferences such as genres and topics that interest the user, visual style, language, region, etc.

[0964] "Sources" refers to digital media such as multiple websites, data feeds, and news APIs that provide news data.

[0965] "News data" refers to data collected from various sources, including news articles, reports, and media content.

[0966] "Filtering" is the process of selecting highly relevant information from collected news data based on the user's preferences and interests.

[0967] A "summary" refers to a text or media that compactly summarizes filtered news data and succinctly expresses the main content.

[0968] A "personalized news list" is a list of news presented in a way that is optimized for each user, and is generated based on the user's preferences and feedback.

[0969] "Feedback" refers to opinions and thoughts about news provided by users, such as "like" or "not interested."

[0970] "Relearning" is the process of updating the AI ​​algorithm based on collected feedback to improve the accuracy of generating news lists in future.

[0971] The present invention is a system that customizes news based on a user's preferences and interests, providing a personalized news experience. Below, we will explain in natural language the means for generating programs for this system and the processing based on them.

[0972] First, this system is composed of multiple components and has three main actors: the server, the terminal, and the user. The server is responsible for collecting data, filtering, generating summaries, generating and distributing news lists, and collecting feedback and relearning. The terminal provides the user interface, sending input from the user to the server and displaying responses from the server. The user interacts with the system, inputting required information and providing feedback.

[0973] 1. User Registration and Preferences

[0974] When a user accesses the application for the first time, a new user registration screen is displayed. The user enters basic information such as name, email address, and password, and also selects the genres and topics they are interested in. They also set visual style preferences (font size, color, preferred language, region, number of characters and length of news). This information is sent from the user's device to the server, which stores it in a database. In terms of specific hardware, the server is a computer with a high-performance CPU, while the device can be a smartphone or PC. In terms of software, Python and SQL are used on the server side, and JavaScript, HTML, and CSS are used on the device side.

[0975] 2. News gathering

[0976] The server periodically accesses multiple predefined news sources (e.g., news websites, RSS feeds, news APIs) to collect the latest news data using web scraping techniques (Python libraries Beautiful Soup and Selenium) and API calls, and stores the collected news data in a database on the server.

[0977] 3. Analyzing news based on user preferences

[0978] The server retrieves user preferences and settings from the database and filters the collected news data based on them. Filtering criteria include genre, topic, language, region, and word count. Furthermore, it uses AI algorithms (e.g., natural language processing models such as GPT-3 and BERT) to generate summaries of the filtered news. Related news and information from multiple perspectives are also added.

[0979] 4. Personalized news generation and delivery

[0980] The server generates a news list optimized for each user, stores it in a database, and associates it with the user's account. This news list is periodically sent to the user's device, which displays it on the user interface. The user can then review the list, select articles of interest, and view them.

[0981] 5. User Feedback and Retraining

[0982] Users provide feedback on the displayed news, such as "Like" or "Not Interested." This feedback information is sent from the device to the server and stored in a database. The server uses the received feedback to retrain the AI ​​algorithm and improve the accuracy of news list generation.

[0983] Specific examples

[0984] For example, if a user prefers the "Economy" genre and selects "Long Text" and "Image and Video Focused" styles, the server will collect relevant economic news, analyze it in detail, and provide it as an optimized news list. The user can check this on their device and provide feedback on articles that interest them. Specific examples of prompts include the following:

[0985] "Please create a news list that displays long economic news articles with images and videos as the main content."

[0986] In this way, the system can provide a news experience that is optimized to the user's preferences, reducing the stress and time wasted caused by information overload.

[0987] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0988] Step 1: Registering a user

[0989] Input: The user enters their name, email address, password, genres and topics of interest, and visual style (font size, color, language, region, number and length of news).

[0990] Operation: The user enters the information they provided into the input form and clicks the submit button. At this time, validation checks are performed on the input data (e.g., checking that required fields are entered, checking the format of the email address).

[0991] Output: Data about the user's basic information and preferences is sent from the device to the server, which stores this data in a database.

[0992] Step 2: Gathering news

[0993] Input: The server is pre-configured with a list of news source URLs and API information.

[0994] How it works: The server periodically contacts predefined news sources (news sites, RSS feeds, news APIs, etc.) and uses web scraping techniques and API calls to gather the latest news data.

[0995] Output: The collected news data is stored in a database on the server.

[0996] Step 3: Analyzing news based on user preferences

[0997] Input: The server retrieves user preferences and settings from the database, and also inputs collected news data.

[0998] How it works: The server filters news data based on user preferences and settings (genre, topic, language, region, word count, etc.), extracts news based on the conditions using Python's Pandas library, and then generates a summary of the filtered news using an AI algorithm (e.g., GPT-3 or BERT).

[0999] Output: Filtered and summarized news data.

[1000] Step 4: Generate a personalized news list

[1001] Input: Filtered and summarized news data.

[1002] How it works: The server generates a news list optimized for each user. News items are tagged and ranked to reflect the user's preferences. The generated news list is saved in JSON format.

[1003] Output: The generated news list is stored in the server's database and associated with the user's account.

[1004] Step 5: Delivering news to users

[1005] Input: The generated personalized news list.

[1006] How it works: The server periodically delivers news lists to the user's device, sending data via GET requests using the REST API.

[1007] Output: The news list is sent to the terminal, which displays the received news list on its user interface.

[1008] Step 6: User feedback and retraining

[1009] Input: Feedback provided by the user regarding the news displayed (e.g. "Like" or "Not interested").

[1010] How it works: Users provide feedback on the displayed news by clicking or tapping. The device sends the feedback information to the server, which stores it in a database. The server then retrains the AI ​​algorithm and processes the results in a batch process to improve the accuracy of the next news list generation.

[1011] Output: An updated AI model and improved accuracy of news list generation based on it.

[1012] (Application example 1)

[1013] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1014] Currently, many news platforms are unable to provide news based on users' individual preferences and interests, resulting in stress and time wasted due to information overload. Furthermore, the news provided is not optimized for users' preferences, resulting in differences in how users perceive and value the information. Furthermore, insufficient news summaries and related information mean users are unable to quickly grasp the information they need.

[1015] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1016] In this invention, the server includes means for collecting information on preferences and interests input by the user, means for collecting news data from multiple news sources, means for filtering the collected news data based on the user's preferences and interests and generating summaries, means for generating a news list personalized for each user and distributing it to the terminal, means for collecting user feedback and relearning to improve the accuracy of generating the news list, and means for summarizing the collected news data using an artificial intelligence model. This makes it possible to reduce stress caused by information overload and provide news optimized to the user's preferences.

[1017] "User" refers to a person who uses the news application.

[1018] "Preferences and interests" refers to personal preferences such as the genres and topics that interest a user, visual style, language, and region.

[1019] "News source" refers to an external source of news data, including news sites, RSS feeds, news APIs, etc.

[1020] "News data" refers to a collection of information, such as articles and reports, collected from news sources.

[1021] "Filtering" refers to the process of selecting collected news data based on the user's preferences and interests.

[1022] A "summary" is a concise summary of the main points or content of a news article.

[1023] A "personalized news list" refers to a list of news articles optimized for each user.

[1024] "Device" refers to the device used to receive the personalized news list, including a smartphone, tablet, or computer.

[1025] "Feedback" refers to user-provided ratings and opinions on news articles.

[1026] "Retraining" refers to the process of using collected feedback information to retrain the algorithm to improve the accuracy of the system.

[1027] "Artificial intelligence model" refers to the machine learning algorithms and models used to generate summaries for collected news data.

[1028] This invention is a system that customizes news based on a user's preferences and interests, providing a personalized news experience. The program and processing of this system are described below.

[1029] Registering users and setting preferences

[1030] Users first enter their basic information into the news application, along with personal preferences such as genres and topics of interest, visual style, language, and region. This information is sent from the user's device to the server and stored in a database. This information collection allows the system to understand the user's individual preferences and use them for subsequent processing.

[1031] News gathering

[1032] The server periodically collects news data from multiple predefined news sources, including news websites, RSS feeds, and news APIs. This collected news data is then stored in the server's database. During this process, technologies such as APIs are used to ensure that the collected data is up-to-date and abundant.

[1033] News analysis based on user preferences

[1034] The server retrieves user preferences and settings from the database and filters the collected news data based on the user's preferences, using criteria such as genre, topic, language, region, and word count. During this process, artificial intelligence models and machine learning algorithms are used to filter and summarize the news.

[1035] Personalized news generation

[1036] Based on the filtered news data, the server generates a news list optimized for each user. This news list is stored in the server's database and linked to the user's account. The generated news list efficiently provides information that the user is interested in.

[1037] News distribution to users

[1038] The server sends the personalized news list to the user's device, which displays it. This process can be carried out on devices such as smartphones or tablets.

[1039] User feedback and retraining

[1040] Users can provide feedback on the displayed news, such as "Like" or "Not Interested." This feedback information is sent from the device to the server and stored in a database. The server uses this feedback to retrain the AI ​​algorithm and improve the accuracy of future news list generation.

[1041] Program processing

[1042] The system is implemented using Python, Flask, the Requests library, and a news API. For example, the news API is used to collect news data, Flask is used for user registration and feedback processing, and an artificial intelligence model (e.g., OpenAI's GPT model) is used to generate news summaries.

[1043] As a concrete example, the following prompt sentence will be used.

[1044] Prompt Sentence Examples

[1045] Generate a summary of the following news article:

[1046] The content of the news article goes here.

[1047] summary:

[1048] In this way, the system can provide a news experience optimized to the user's preferences, reducing stress and time wasted due to information overload.

[1049] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1050] Step 1:

[1051] Sign up and set your preferences

[1052] When a user first accesses the application, they launch it and enter information such as their name, email address, password, genres and topics of interest, visual style, preferred language, and region.

[1053] The terminal transmits this input information to the server.

[1054] The server stores the received information in a database.

[1055] Input: Name, Email, Password, Genre, Topic, Visual Style, Language, Region

[1056] Data processing: The server formats this information into structured data and stores it in a database.

[1057] Output: User profile stored in the database

[1058] Step 2:

[1059] News gathering

[1060] The server periodically accesses multiple news sources such as news APIs to collect news data.

[1061] The news data is stored in a database on the server.

[1062] Input: News API endpoint

[1063] Data processing: The server converts the acquired news data into the required structure and records it in the database.

[1064] Output: News data stored in a database

[1065] Step 3:

[1066] News analysis based on user preferences

[1067] The server retrieves user preferences and settings from a database.

[1068] The server filters the collected news data based on user settings, such as genre, topic, language, region, and word count.

[1069] Generate summaries of filtered news data using artificial intelligence models.

[1070] Input: User profiles and news data in a database

[1071] Data processing: filtering, summarization

[1072] Output: filtered and summarized news data

[1073] Step 4:

[1074] Personalized news generation

[1075] The server generates a news list optimized for each user based on the filtered and summarized news data.

[1076] This news list is stored in a database on the server and linked to the user's account.

[1077] Input: filtered and summarized news data

[1078] Data processing: News list generation, linking to user accounts

[1079] Output: A personalized news list

[1080] Step 5:

[1081] News distribution to users

[1082] The server sends a personalized news list to the user's terminal.

[1083] The terminal displays the received news list on the user interface.

[1084] Input: personalized news list

[1085] Data processing: Data transmission via communication

[1086] Output: A personalized news list displayed on the device.

[1087] Step 6:

[1088] User feedback and retraining

[1089] Users provide feedback on news lists (such as "like" or "not interested").

[1090] The terminal transmits the feedback information to the server.

[1091] The server stores the feedback information in a database and retrains the AI ​​algorithm.

[1092] Input: User feedback

[1093] Data processing: saving feedback information and re-learning process

[1094] Output: Updated AI model and improved accuracy of future news list generation

[1095] In this way, through a series of processing steps, the system provides a personalized news experience tailored to the user's preferences.

[1096] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1097] The present invention is a system that provides news tailored to the user's preferences and interests, and also combines an emotion engine to provide an optimal news experience according to the emotional state of each individual user. Below, we will explain the program processing and specific examples of this system.

[1098] Registering users and setting preferences

[1099] 1. A user accesses the application and is presented with a new user registration screen.

[1100] 2. Users enter basic information such as their name, email address, and password, as well as their preferred genres and topics (e.g., politics, economics, entertainment), and set visual styles such as font size, color, preferred language, region, and number and length of news characters.

[1101] 3. The information provided by the user is sent from the device to the server, where it is stored in a database.

[1102] News gathering

[1103] 1. The server periodically accesses multiple news sources (e.g., news sites, RSS feeds, news APIs) to collect the latest news data.

[1104] 2. The collected news data is stored in a database on the server.

[1105] News analysis based on user preferences

[1106] 1. The server retrieves user preferences and settings from a database.

[1107] 2. The server filters the collected news data based on the user's preferences, taking into account criteria such as genre, topic, language, region, and word count.

[1108] 3. The server uses AI algorithms to summarize the filtered news, sometimes adding related news and other perspectives.

[1109] Introducing the Emotion Engine

[1110] 1. The emotion engine installed on the device uses the user's camera and microphone to analyze facial expressions and tone of voice to recognize the user's emotional state.

[1111] 2. The recognized emotion data is sent from the device to the server.

[1112] 3. The server adjusts the priority and content of the news list based on the emotion data.

[1113] Personalized news generation

[1114] 1. The server generates an optimized news list based on the user's preferences and sentiment data.

[1115] 2. This news list is stored in a database and linked to the user's account.

[1116] News distribution to users

[1117] 1. The server sends the news list to the user's terminal.

[1118] 2. The terminal displays the news list on the user interface so that the user can check it.

[1119] User feedback and retraining

[1120] 1. Users provide feedback on the displayed news, such as "like" or "not interested."

[1121] 2. The feedback information is sent from the device to the server and stored in a database.

[1122] 3. The server uses the feedback to retrain the AI ​​algorithm to improve the accuracy of generating news lists.

[1123] For example, if a user likes the "Entertainment" genre and the emotion engine recognizes the user's positive emotional state, the server will prioritize filtering entertainment news containing optimistic content and add it to the news list along with summaries. On the other hand, if the user is in a negative emotional state, the server will include positive news articles to improve the user's mood.

[1124] In this way, the system provides a personalized news experience that takes into account the user's preferences and emotional state, reducing stress and time wasted due to information overload and promoting the user's mental health.

[1125] The processing flow will be explained below.

[1126] Step 1:

[1127] A user accesses the application and is presented with a new user registration screen.

[1128] Step 2:

[1129] Users enter basic information such as their name, email address, and password, as well as their preferred genres and topics (e.g., politics, economics, entertainment), and set visual styles such as font size, color, language, region, and word count and length of news.

[1130] Step 3:

[1131] The terminal collects this information and sends it to the server.

[1132] Step 4:

[1133] The server stores the received user information and setting information in a database.

[1134] Step 5:

[1135] The server periodically accesses multiple predefined news sources (e.g., news sites, RSS feeds, news APIs) to collect the latest news data.

[1136] Step 6:

[1137] The collected news data is stored in a database on the server.

[1138] Step 7:

[1139] The server retrieves user preferences and settings from a database.

[1140] Step 8:

[1141] The server filters the news data based on the user's preferences, such as genre, topic, language, region, and word count.

[1142] Step 9:

[1143] The server uses AI algorithms to generate filtered news summaries, adding related news and perspectives as needed.

[1144] Step 10:

[1145] The emotion engine installed on the device uses the user's camera and microphone to analyze facial expressions and tone of voice to recognize the user's emotional state.

[1146] Step 11:

[1147] The recognized emotion data is transmitted from the terminal to the server.

[1148] Step 12:

[1149] The server adjusts the priority and content of the news list based on the emotional data, selecting news according to the user's emotional state, such as positive or negative emotions.

[1150] Step 13:

[1151] The server generates a personalized news list taking into account the emotional data and user preferences.

[1152] Step 14:

[1153] The generated news list is stored in a database on the server and linked to the user's account.

[1154] Step 15:

[1155] The server sends the news list to the user's terminal.

[1156] Step 16:

[1157] The terminal displays the news list on the user interface so that the user can check it.

[1158] Step 17:

[1159] Users provide feedback on the displayed news, such as "like" or "not interested."

[1160] Step 18:

[1161] The feedback information is sent from the terminal to the server.

[1162] Step 19:

[1163] The server stores the feedback information in a database and uses it to retrain the AI ​​algorithm.

[1164] Step 20:

[1165] The retrained AI algorithm will improve the accuracy of the next news list generation.

[1166] Example 2

[1167] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1168] Current news delivery systems primarily provide news based on users' preferences and interests, but few systems consider the user's emotional state when providing news. This can result in users receiving news that is inappropriate for their current emotional state, potentially adversely affecting how they receive and understand information. Furthermore, there are insufficient mechanisms for reducing stress and fatigue caused by information overload, making it difficult to maintain users' mental health.

[1169] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting information on preferences and interests input by the user, means for collecting data from multiple information sources, means for filtering the collected data based on the user's preferences and interests and generating a summary, means for analyzing the user's emotional state using an emotion recognition engine of the terminal and adjusting the data based on this information, means for generating a list personalized for each user and delivering it to the terminal, and means for collecting user feedback, re-learning, and improving the accuracy of list generation. This enables personalized news delivery that takes into account not only the user's preferences and interests but also their emotional state.

[1170] "User-entered preference and interest information" refers to personal preference information provided by individual users, such as genres, topics, types of news, and visual styles that interest them.

[1171] "Multiple sources" refers to various news sources, such as news sites, RSS feeds, and news APIs.

[1172] "Data filtering" is the process of selecting collected news data based on the user's preferences and interests.

[1173] "Generating a summary" is the process of shortening the filtered news data into a concise format that includes the main points.

[1174] An "emotion recognition engine" is software that uses the device's built-in camera and microphone to analyze the user's facial expressions and tone of voice and recognize their emotional state.

[1175] "Adjusting data" is a process of changing the contents and priorities of the news list based on the emotion data obtained from the emotion recognition engine.

[1176] A "personalized list" is a collection of news articles that is customized based on an individual user's preferences and emotional state.

[1177] "Delivering to terminal" refers to the process of sending the generated news list to the device used by the user.

[1178] "Feedback" refers to user-provided ratings and reactions to news articles, such as "like" or "not interested."

[1179] "Retraining" is the process of improving the AI ​​algorithm based on collected feedback to improve the accuracy of generating news lists.

[1180] This invention is a system that provides optimal information experiences according to the emotional state of each individual user by combining a system that provides information tailored to the user's preferences and interests with an emotion recognition engine. The specific configuration and operating procedures for implementing this system are described below.

[1181] Registering users and setting preferences

[1182] 1. When a user accesses the application, a new user registration screen appears, where the user enters basic information such as name, email address, and password, as well as the genres and topics of interest.

[1183] 2. The user further configures the visual style, such as font size, color, language, region, and length and character count of the information.

[1184] 3. The information entered from the device is sent to the server. For security reasons, an encrypted protocol (e.g., HTTPS) is used for this transmission.

[1185] 4. The server stores the received information in a database.

[1186] Collection of information

[1187] 1. The server automatically collects data from multiple sources (e.g., websites, RSS feeds, APIs) and this collection is configured to occur periodically.

[1188] 2. Data from each source is collected on the server in a standard format (e.g., JSON, XML).

[1189] 3. The server stores the collected data in a database and keeps the information up to date.

[1190] Analyzing information based on user preferences

[1191] 1. The server retrieves user preferences and settings from a database, including information about genre, topic, language, region, and character count.

[1192] 2. The server filters the collected data based on the user's preferences. For example, if a user is interested in the entertainment genre, it will only show articles in that genre.

[1193] 3. The server uses AI algorithms (e.g., natural language processing models, generative AI models) to summarize the filtered data and add relevant information and multifaceted perspectives.

[1194] Introducing the Emotion Engine

[1195] 1. The device's built-in emotion recognition engine uses the camera and microphone to analyze the user's facial expressions and tone of voice to recognize their emotional state. This analysis uses machine learning models (e.g., facial expression recognition model, voice emotion recognition model).

[1196] 2. The recognized emotion data is sent from the device to the server.

[1197] 3. The server adjusts the priority and content of the information list based on the emotional data. For example, when the user is in a positive emotional state, information with positive content is displayed preferentially.

[1198] Generate personalized information

[1199] 1. The server generates an optimal information list based on the user's preferences and emotional data. This list is customized for each user.

[1200] 2. The generated information list is stored in a database and linked to each user's account.

[1201] Information distribution to users

[1202] 1. The server sends the optimized information list to the device using a secure communication protocol (e.g., HTTPS, WebSocket).

[1203] 2. The terminal displays the received information list on the user interface for easy access by the user.

[1204] User feedback and retraining

[1205] 1. The user provides feedback on the displayed information, such as "like" or "not interested."

[1206] 2. The device sends user feedback to the server and receives real-time ratings.

[1207] 3. The server retrains the AI ​​algorithm based on the feedback to improve the accuracy of generating information lists.

[1208] For example, if a user likes the "Entertainment" genre and the emotion engine recognizes the user's positive emotional state, the server will prioritize filtering entertainment information containing optimistic content and add it to the information list along with a summary. On the other hand, if the user is in a negative emotional state, the server will adjust the information list to include positive information to improve the user's mood.

[1209] An example of a prompt sentence to input to the generative AI model could be, "If the user is interested in entertainment and is currently in a positive emotional state, generate an optimistic news title. For example, 'The latest movie is a huge hit!'"

[1210] This system provides information that takes into account the user's preferences and emotional state, thereby reducing stress caused by information overload and helping to maintain the user's mental health.

[1211] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1212] Step 1:

[1213] When a user accesses the application, a new user registration screen appears. At this point, the user enters information such as their name, email address, password, genres and topics of interest, font size, color, preferred language, region, number and length of news characters, etc. This information is sent from the device to the server as the user's individual setting data.

[1214] Input: User's personal information (name, email address, password, genre, topic, font size, color, language, region, number of characters and length of news)

[1215] Output: Sending configuration information from the device to the server

[1216] Step 2:

[1217] The server receives the user's individual setting information sent from the terminal and stores it in a database. This database is used to centrally manage the individual setting information of all users.

[1218] Input: User personalized information sent from the device

[1219] Output: User personalization information stored in the database

[1220] Step 3:

[1221] The server accesses multiple news sources (e.g., news sites, RSS feeds, news APIs) at regular intervals to automatically collect new news data, which is then stored in a database in a specific format (e.g., JSON, XML).

[1222] Input: Latest news data from news sources

[1223] Output: Latest news data stored in a database

[1224] Step 4:

[1225] The server retrieves user preferences and settings from the database, and uses this information to filter the collected news data and extract only news that matches the user's interests and settings.

[1226] Input: User preferences and settings information and latest news data from a database

[1227] Output: Filtered news data

[1228] Step 5:

[1229] The server uses AI algorithms (e.g., natural language processing models, generative AI models) to summarize the filtered news data. The summary is a concise representation of the main points, and may also include related news and other perspectives.

[1230] Input: Filtered news data

[1231] Output: Summarized news data and related information

[1232] Step 6:

[1233] The device's built-in emotion recognition engine uses the camera and microphone to analyze the user's facial expressions and tone of voice, and then uses machine learning models to identify the user's emotional state.

[1234] Input: User facial and voice data via camera and microphone

[1235] Output: Analyzed sentiment data

[1236] Step 7:

[1237] The device sends the acquired emotional data to the server, which then adjusts the content and priority of the news list based on this data. For example, if the user is in a positive emotional state, news with positive content will be displayed first.

[1238] Input: Emotion data sent from the device

[1239] Output: Adjusted news list

[1240] Step 8:

[1241] The server generates a news list based on the user's preferences and sentiment data, which is customized for each user.

[1242] Input: User preferences, settings, and emotional data

[1243] Output: A personalized news list

[1244] Step 9:

[1245] The server sends the generated news list to the terminal using a secure protocol (e.g. HTTPS, WebSocket).

[1246] Input: personalized news list

[1247] Output: News list delivered to the device

[1248] Step 10:

[1249] The terminal displays the received news list on the user interface and provides it to the user, who then checks the news list and provides feedback.

[1250] Input: News list sent from the server

[1251] Output: Display the news list in a user interface

[1252] Step 11:

[1253] Users provide feedback such as "like" or "not interested" to the displayed news, which is then sent from the device to the server.

[1254] Input: User feedback

[1255] Output: Sending feedback from the device to the server

[1256] Step 12:

[1257] The server collects user feedback and stores it in a database, which is used to retrain the AI ​​algorithm to improve the accuracy of generating news lists.

[1258] Input: User feedback

[1259] Output: Retrained AI algorithm and improved news list generation accuracy

[1260] (Application example 2)

[1261] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1262] Conventional news delivery systems only consider the user's preferences and interests, ignoring the user's emotional state. As a result, users may feel stressed due to information overload, or the news provided may not match their mood at the time. Furthermore, when news is provided in an autonomous vehicle, passengers may not be able to relax while driving. To solve these problems, a personalized news delivery system that considers both the user's preferences and emotional state is needed.

[1263] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting information related to preferences and interests input by the user; means for collecting information data from multiple information sources; means for filtering the collected information data based on the user's preferences and interests and generating a summary; means for generating an information list personalized for each user and distributing it to the device; means for collecting user feedback and relearning to improve the accuracy of generating the information list; means for recognizing the user's emotional state based on facial expressions and tone of voice; and means for adjusting the priority and content of the information list based on the user's emotional state. This enables an optimal news experience that takes into account the user's preferences and emotional state.

[1264] A "user" is a person who uses the system.

[1265] "Information about preferences and interests" includes information such as the genres and topics, visual style, language, and region in which the user is interested.

[1266] "Sources" are sources that provide news data, such as news sites, RSS feeds, and news APIs.

[1267] "Information data" is data collected from information sources such as news, articles, and reports.

[1268] "Filtering" is the process of selecting appropriate data from collected information data based on the user's preferences and interests.

[1269] The "summary" is a concise summary of the filtered information data.

[1270] An "information list" is a list of news and articles that has been filtered and summarized and is provided to the user.

[1271] "Devices" refer to devices such as smartphones, tablets, and head-mounted displays installed inside autonomous vehicles.

[1272] "Feedback" refers to ratings and comments such as "like" or "not interested" that users make about the displayed news.

[1273] "Retraining" is the process of using collected feedback information to refine the system's algorithms and improve the accuracy of the information list.

[1274] "Emotional state" refers to the psychological state of the user, which is analyzed from facial expressions and tone of voice.

[1275] "Priority and content adjustment" is the process of adapting the display order and content of news and articles in an information list based on the user's emotional state.

[1276] This invention combines an emotion engine with a system that provides news tailored to the user's preferences and interests to provide an optimal news experience that matches the emotional state of each individual user. The following describes the processing content of the program and the hardware and software used to realize this system.

[1277] Registering users and setting preferences

[1278] When a user accesses the application, a new user registration screen is displayed. The user enters basic information such as name, email address, and password, as well as genres and topics of interest (e.g., politics, economics, entertainment). The user also sets visual styles such as font size, color, preferred language, region, and number and length of news characters. This information is sent from the device to the server, where it is stored in a database.

[1279] News gathering

[1280] The server periodically accesses multiple news sources (e.g., news sites, RSS feeds, news APIs) to collect the latest news data, which is then stored in the server's database.

[1281] News analysis based on user preferences

[1282] The server retrieves user preferences and settings from the database and filters the collected news data based on the user's preferences. It considers criteria such as genre, topic, language, region, and word count, and then uses an AI algorithm to summarize the filtered news. In some cases, related news and information from multiple perspectives are also added.

[1283] Introducing the Emotion Engine

[1284] The device's built-in emotion engine analyzes the user's facial expressions and tone of voice to recognize their emotional state. This emotion data is sent from the device to a server, which then adjusts the priority and content of the news list based on the emotion data.

[1285] Personalized news generation

[1286] The server generates an optimized news list based on the user's preferences and sentiment data, which is stored in a database and linked to the user's account.

[1287] News distribution to users

[1288] The server transmits the news list to the user's terminal, which displays the news list on a user interface.

[1289] User feedback and retraining

[1290] Users provide feedback on the displayed news, such as "like" or "not interested," which is then sent from the device to the server and stored in a database. The server then uses the feedback to retrain the AI ​​algorithm and improve the accuracy of generating news lists.

[1291] For example, if a user is interested in entertainment in an autonomous vehicle, the emotion engine will recognize the user's positive emotional state and the server will prioritize entertainment news with optimistic content to add to the list. Conversely, if the user is in a negative emotional state, the server will include positive news articles to improve the user's mood.

[1292] Example prompt sentence:

[1293] Generate sample code for a system that takes user preferences into account and uses an emotion engine to provide the most appropriate news articles. This system is intended for use in self-driving cars. It uses the in-car camera and microphone to analyze passenger emotions in real time and prioritizes the display of news articles according to their emotional state. The system continuously optimizes the news suggestions based on passenger feedback.

[1294] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1295] Step 1: Register and set your preferences

[1296] When a user logs in to the application, a new user registration screen is displayed. The user enters basic information such as name, email address, and password, as well as the genres and topics they are interested in. They also set visual styles such as font size and color, preferred language, region, and number and length of news characters. This input data is sent from the device to the server, where it is stored in a database.

[1297] Step 2: Gathering news

[1298] The server periodically accesses multiple news sources to collect the latest news data. This input data is obtained from various news sites, RSS feeds, news APIs, etc. and stored in a database on the server. The server analyzes the news title, content, publication time, images, etc., and stores them in a structured database.

[1299] Step 3: Analyzing and filtering news based on user preferences

[1300] The server retrieves user preferences and settings from the database and uses them as input to filter the collected news data. In this step, it considers criteria such as genre, topic, language, region, and word count to select news that matches the user's interests. The filtered news data is output and then sent to the summarization process.

[1301] Step 4: Generate news summaries and add related news

[1302] The server uses AI algorithms to summarize the filtered news and also adds related news and information from multiple perspectives. The input data is the filtered news data, and from this it generates summaries and related information. The output is a summarized news list.

[1303] Step 5: Analyze the user's emotional state with the emotion engine

[1304] The device uses a camera and microphone to capture the user's facial expressions and tone of voice. This captured data is analyzed on the device to recognize the user's emotional state. The emotional data is generated as output and sent to the server.

[1305] Step 6: Adjusting the news list based on emotional state

[1306] The server obtains the emotional data and adjusts the ranking and content of the news list based on it. The input data are the emotional data and the summarized news list, and the adjustment is made based on these. The output is a news list optimized based on the emotional state.

[1307] Step 7: Generate and deliver personalized news

[1308] The server generates an optimized news list for each user and stores it in a database. The news list is then delivered to the autonomous vehicle's terminal for display. The input data is the adjusted news list, and the output is the news list displayed on the device.

[1309] Step 8: User feedback and retraining

[1310] Users provide feedback on the displayed news, such as "like" or "not interested." This feedback data is sent from the device to the server, which stores it in a database. The server then retrains the AI ​​algorithm based on the collected feedback to improve the accuracy of news list generation. The input data is the feedback information, and the output is an improved algorithm.

[1311] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1312] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1313] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1314] [Fourth embodiment]

[1315] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1316] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1317] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1318] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1319] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1320] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1321] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1322] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1323] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1324] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1325] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1326] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1327] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1328] The present invention is a system that customizes news based on a user's preferences and interests, providing a personalized news experience. Below, we will create a program for this system and explain each processing step in natural language.

[1329] Registering users and setting preferences

[1330] 1. When a user accesses the application for the first time, a new user registration screen is displayed.

[1331] 2. Users enter basic information such as their name, email address, and password, and also select genres and topics of interest (e.g., politics, economics, entertainment).

[1332] 3. Users set visual styles such as font size, color, preferred language, region, word count and length of news.

[1333] 4. The above information is sent from the user's device to the server, which stores it in a database.

[1334] News gathering

[1335] 1. The server periodically accesses multiple predefined news sources (e.g., news sites, RSS feeds, news APIs) to collect the latest news data.

[1336] 2. The collected news data is stored in a database on the server.

[1337] News analysis based on user preferences

[1338] 1. The server retrieves user preferences and settings from a database.

[1339] 2. The server filters the collected news data based on the user's preferences and interests, using criteria such as genre, topic, language, region, and word count.

[1340] 3. The server uses AI algorithms to generate filtered news summaries, sometimes supplemented with related news and perspectives.

[1341] Personalized news generation

[1342] 1. The server generates a news list optimized for each user.

[1343] 2. This news list is stored in a database on the server and linked to the user's account.

[1344] News distribution to users

[1345] 1. The server sends a personalized news list to the user's device.

[1346] 2. The user's device displays this news list on the user interface so that the user can check it.

[1347] User feedback and retraining

[1348] 1. Users can provide feedback on the displayed news, such as "like" or "not interested."

[1349] 2. This feedback information is sent from the device to the server, where it is stored in a database.

[1350] 3. The server uses this feedback to retrain its AI algorithms to improve the accuracy of future news list generation.

[1351] For example, if a user prefers the "Economy" genre and selects a "long-form" and "image and video-focused" style, the server will collect relevant economic news, analyze it in detail, and provide an optimized news list. The user can review this on their device and provide feedback on articles they find interesting. This feedback will then be reflected in the next news list generation.

[1352] In this way, the system provides a news experience optimized to the user's preferences, reducing the stress and time wasted caused by information overload.

[1353] The processing flow will be explained below.

[1354] Step 1:

[1355] A user accesses the application and is presented with a new user registration screen.

[1356] Step 2:

[1357] Users enter basic information such as their name, email address, and password, as well as genres and topics of interest (e.g., politics, economics, entertainment), and set visual styles such as font size, color, preferred language, region, and word count and length of news.

[1358] Step 3:

[1359] The terminal collects this information and sends it to the server.

[1360] Step 4:

[1361] The server stores the received user information and setting information in a database.

[1362] Step 5:

[1363] The server periodically accesses multiple predefined news sources (e.g., news sites, RSS feeds, news APIs) to collect news data.

[1364] Step 6:

[1365] The collected news data is stored in a database on the server.

[1366] Step 7:

[1367] The server retrieves user preferences and settings from a database.

[1368] Step 8:

[1369] The server filters the news data based on the user's preferences, such as genre, topic, language, region, and word count.

[1370] Step 9:

[1371] The server uses AI algorithms to generate filtered news summaries, adding related news and perspectives as needed.

[1372] Step 10:

[1373] The server aggregates the summarized news and generates a personalized news list for each user.

[1374] Step 11:

[1375] The generated news list is stored in a database on the server and linked to the user's account.

[1376] Step 12:

[1377] The server sends the news list to the user's terminal.

[1378] Step 13:

[1379] The terminal displays the received news list on the user interface.

[1380] Step 14:

[1381] Users provide feedback on the displayed news, such as "like" or "not interested."

[1382] Step 15:

[1383] The terminal transmits the feedback information to the server.

[1384] Step 16:

[1385] The server stores the feedback information in a database and uses it to retrain the AI ​​algorithm.

[1386] Step 17:

[1387] The retrained AI algorithm will improve the accuracy of the next news list generation.

[1388] Example 1

[1389] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1390] In today's information society, users are faced with a vast amount of news information, making it difficult to find useful information. This information overload can be stressful and time-consuming for users. Furthermore, providing news tailored to users' preferences and interests requires collecting, filtering, personalizing, and incorporating feedback from news data, but efficient methods for doing so are lacking. Therefore, the present invention aims to solve these problems and provide a news experience optimized for users' preferences.

[1391] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1392] In this invention, the server includes means for collecting information on preferences and interests input by the user, means for collecting news data from multiple information sources, means for filtering the collected news data based on the user's preferences and interests and generating summaries, means for generating a news list personalized for each user and distributing it to the terminal, and means for collecting user feedback, relearning, and improving the accuracy of generating the news list. This makes it possible to provide a news experience optimized for the user's preferences and reduce stress and time wasted due to information overload.

[1393] A "user" is an individual or organization that uses the system to view news and enter information about their preferences and interests.

[1394] "Preferences and interests" refers to preferences such as genres and topics that interest the user, visual style, language, region, etc.

[1395] "Sources" refers to digital media such as multiple websites, data feeds, and news APIs that provide news data.

[1396] "News data" refers to data collected from various sources, including news articles, reports, and media content.

[1397] "Filtering" is the process of selecting highly relevant information from collected news data based on the user's preferences and interests.

[1398] A "summary" refers to a text or media that compactly summarizes filtered news data and succinctly expresses the main content.

[1399] A "personalized news list" is a list of news presented in a way that is optimized for each user, and is generated based on the user's preferences and feedback.

[1400] "Feedback" refers to opinions and thoughts about news provided by users, such as "like" or "not interested."

[1401] "Relearning" is the process of updating the AI ​​algorithm based on collected feedback to improve the accuracy of generating news lists in future.

[1402] The present invention is a system that customizes news based on a user's preferences and interests, providing a personalized news experience. Below, we will explain in natural language the means for generating programs for this system and the processing based on them.

[1403] First, this system is composed of multiple components and has three main actors: the server, the terminal, and the user. The server is responsible for collecting data, filtering, generating summaries, generating and distributing news lists, and collecting feedback and relearning. The terminal provides the user interface, sending input from the user to the server and displaying responses from the server. The user interacts with the system, inputting required information and providing feedback.

[1404] 1. User Registration and Preferences

[1405] When a user accesses the application for the first time, a new user registration screen is displayed. The user enters basic information such as name, email address, and password, and also selects the genres and topics they are interested in. They also set visual style preferences (font size, color, preferred language, region, number of characters and length of news). This information is sent from the user's device to the server, which stores it in a database. In terms of specific hardware, the server is a computer with a high-performance CPU, while the device can be a smartphone or PC. In terms of software, Python and SQL are used on the server side, and JavaScript, HTML, and CSS are used on the device side.

[1406] 2. News gathering

[1407] The server periodically accesses multiple predefined news sources (e.g., news websites, RSS feeds, news APIs) to collect the latest news data using web scraping techniques (Python libraries Beautiful Soup and Selenium) and API calls, and stores the collected news data in a database on the server.

[1408] 3. Analyzing news based on user preferences

[1409] The server retrieves user preferences and settings from the database and filters the collected news data based on them. Filtering criteria include genre, topic, language, region, and word count. Furthermore, it uses AI algorithms (e.g., natural language processing models such as GPT-3 and BERT) to generate summaries of the filtered news. Related news and information from multiple perspectives are also added.

[1410] 4. Personalized news generation and delivery

[1411] The server generates a news list optimized for each user, stores it in a database, and associates it with the user's account. This news list is periodically sent to the user's device, which displays it on the user interface. The user can then review the list, select articles of interest, and view them.

[1412] 5. User Feedback and Retraining

[1413] Users provide feedback on the displayed news, such as "Like" or "Not Interested." This feedback information is sent from the device to the server and stored in a database. The server uses the received feedback to retrain the AI ​​algorithm and improve the accuracy of news list generation.

[1414] Specific examples

[1415] For example, if a user prefers the "Economy" genre and selects "Long Text" and "Image and Video Focused" styles, the server will collect relevant economic news, analyze it in detail, and provide it as an optimized news list. The user can check this on their device and provide feedback on articles that interest them. Specific examples of prompts include the following:

[1416] "Please create a news list that displays long economic news articles with images and videos as the main content."

[1417] In this way, the system can provide a news experience that is optimized to the user's preferences, reducing the stress and time wasted caused by information overload.

[1418] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1419] Step 1: Registering a user

[1420] Input: The user enters their name, email address, password, genres and topics of interest, and visual style (font size, color, language, region, number and length of news).

[1421] Operation: The user enters the information they provided into the input form and clicks the submit button. At this time, validation checks are performed on the input data (e.g., checking that required fields are entered, checking the format of the email address).

[1422] Output: Data about the user's basic information and preferences is sent from the device to the server, which stores this data in a database.

[1423] Step 2: Gathering news

[1424] Input: The server is pre-configured with a list of news source URLs and API information.

[1425] How it works: The server periodically contacts predefined news sources (news sites, RSS feeds, news APIs, etc.) and uses web scraping techniques and API calls to gather the latest news data.

[1426] Output: The collected news data is stored in a database on the server.

[1427] Step 3: Analyzing news based on user preferences

[1428] Input: The server retrieves user preferences and settings from the database, and also inputs collected news data.

[1429] How it works: The server filters news data based on user preferences and settings (genre, topic, language, region, word count, etc.), extracts news based on the conditions using Python's Pandas library, and then generates a summary of the filtered news using an AI algorithm (e.g., GPT-3 or BERT).

[1430] Output: Filtered and summarized news data.

[1431] Step 4: Generate a personalized news list

[1432] Input: Filtered and summarized news data.

[1433] How it works: The server generates a news list optimized for each user. News items are tagged and ranked to reflect the user's preferences. The generated news list is saved in JSON format.

[1434] Output: The generated news list is stored in the server's database and associated with the user's account.

[1435] Step 5: Delivering news to users

[1436] Input: The generated personalized news list.

[1437] How it works: The server periodically delivers news lists to the user's device, sending data via GET requests using the REST API.

[1438] Output: The news list is sent to the terminal, which displays the received news list on its user interface.

[1439] Step 6: User feedback and retraining

[1440] Input: Feedback provided by the user regarding the news displayed (e.g. "Like" or "Not interested").

[1441] How it works: Users provide feedback on the displayed news by clicking or tapping. The device sends the feedback information to the server, which stores it in a database. The server then retrains the AI ​​algorithm and processes the results in a batch process to improve the accuracy of the next news list generation.

[1442] Output: An updated AI model and improved accuracy of news list generation based on it.

[1443] (Application example 1)

[1444] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1445] Currently, many news platforms are unable to provide news based on users' individual preferences and interests, resulting in stress and time wasted due to information overload. Furthermore, the news provided is not optimized for users' preferences, resulting in differences in how users perceive and value the information. Furthermore, insufficient news summaries and related information mean users are unable to quickly grasp the information they need.

[1446] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1447] In this invention, the server includes means for collecting information on preferences and interests input by the user, means for collecting news data from multiple news sources, means for filtering the collected news data based on the user's preferences and interests and generating summaries, means for generating a news list personalized for each user and distributing it to the terminal, means for collecting user feedback and relearning to improve the accuracy of generating the news list, and means for summarizing the collected news data using an artificial intelligence model. This makes it possible to reduce stress caused by information overload and provide news optimized to the user's preferences.

[1448] "User" refers to a person who uses the news application.

[1449] "Preferences and interests" refers to personal preferences such as the genres and topics that interest a user, visual style, language, and region.

[1450] "News source" refers to an external source of news data, including news sites, RSS feeds, news APIs, etc.

[1451] "News data" refers to a collection of information, such as articles and reports, collected from news sources.

[1452] "Filtering" refers to the process of selecting collected news data based on the user's preferences and interests.

[1453] A "summary" is a concise summary of the main points or content of a news article.

[1454] A "personalized news list" refers to a list of news articles optimized for each user.

[1455] "Device" refers to the device used to receive the personalized news list, including a smartphone, tablet, or computer.

[1456] "Feedback" refers to user-provided ratings and opinions on news articles.

[1457] "Retraining" refers to the process of using collected feedback information to retrain the algorithm to improve the accuracy of the system.

[1458] "Artificial intelligence model" refers to the machine learning algorithms and models used to generate summaries for collected news data.

[1459] This invention is a system that customizes news based on a user's preferences and interests, providing a personalized news experience. The program and processing of this system are described below.

[1460] Registering users and setting preferences

[1461] Users first enter their basic information into the news application, along with personal preferences such as genres and topics of interest, visual style, language, and region. This information is sent from the user's device to the server and stored in a database. This information collection allows the system to understand the user's individual preferences and use them for subsequent processing.

[1462] News gathering

[1463] The server periodically collects news data from multiple predefined news sources, including news websites, RSS feeds, and news APIs. This collected news data is then stored in the server's database. During this process, technologies such as APIs are used to ensure that the collected data is up-to-date and abundant.

[1464] News analysis based on user preferences

[1465] The server retrieves user preferences and settings from the database and filters the collected news data based on the user's preferences, using criteria such as genre, topic, language, region, and word count. During this process, artificial intelligence models and machine learning algorithms are used to filter and summarize the news.

[1466] Personalized news generation

[1467] Based on the filtered news data, the server generates a news list optimized for each user. This news list is stored in the server's database and linked to the user's account. The generated news list efficiently provides information that the user is interested in.

[1468] News distribution to users

[1469] The server sends the personalized news list to the user's device, which displays it. This process can be carried out on devices such as smartphones or tablets.

[1470] User feedback and retraining

[1471] Users can provide feedback on the displayed news, such as "Like" or "Not Interested." This feedback information is sent from the device to the server and stored in a database. The server uses this feedback to retrain the AI ​​algorithm and improve the accuracy of future news list generation.

[1472] Program processing

[1473] The system is implemented using Python, Flask, the Requests library, and a news API. For example, the news API is used to collect news data, Flask is used for user registration and feedback processing, and an artificial intelligence model (e.g., OpenAI's GPT model) is used to generate news summaries.

[1474] As a concrete example, the following prompt sentence will be used.

[1475] Prompt Sentence Examples

[1476] Generate a summary of the following news article:

[1477] The content of the news article goes here.

[1478] summary:

[1479] In this way, the system can provide a news experience optimized to the user's preferences, reducing stress and time wasted due to information overload.

[1480] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1481] Step 1:

[1482] Sign up and set your preferences

[1483] When a user first accesses the application, they launch it and enter information such as their name, email address, password, genres and topics of interest, visual style, preferred language, and region.

[1484] The terminal transmits this input information to the server.

[1485] The server stores the received information in a database.

[1486] Input: Name, Email, Password, Genre, Topic, Visual Style, Language, Region

[1487] Data processing: The server formats this information into structured data and stores it in a database.

[1488] Output: User profile stored in the database

[1489] Step 2:

[1490] News gathering

[1491] The server periodically accesses multiple news sources such as news APIs to collect news data.

[1492] The news data is stored in a database on the server.

[1493] Input: News API endpoint

[1494] Data processing: The server converts the acquired news data into the required structure and records it in the database.

[1495] Output: News data stored in a database

[1496] Step 3:

[1497] News analysis based on user preferences

[1498] The server retrieves user preferences and settings from a database.

[1499] The server filters the collected news data based on user settings, such as genre, topic, language, region, and word count.

[1500] Generate summaries of filtered news data using artificial intelligence models.

[1501] Input: User profiles and news data in a database

[1502] Data processing: filtering, summarization

[1503] Output: filtered and summarized news data

[1504] Step 4:

[1505] Personalized news generation

[1506] The server generates a news list optimized for each user based on the filtered and summarized news data.

[1507] This news list is stored in a database on the server and linked to the user's account.

[1508] Input: filtered and summarized news data

[1509] Data processing: News list generation, linking to user accounts

[1510] Output: A personalized news list

[1511] Step 5:

[1512] News distribution to users

[1513] The server sends a personalized news list to the user's terminal.

[1514] The terminal displays the received news list on the user interface.

[1515] Input: personalized news list

[1516] Data processing: Data transmission via communication

[1517] Output: A personalized news list displayed on the device.

[1518] Step 6:

[1519] User feedback and retraining

[1520] Users provide feedback on news lists (such as "like" or "not interested").

[1521] The terminal transmits the feedback information to the server.

[1522] The server stores the feedback information in a database and retrains the AI ​​algorithm.

[1523] Input: User feedback

[1524] Data processing: saving feedback information and re-learning process

[1525] Output: Updated AI model and improved accuracy of future news list generation

[1526] In this way, through a series of processing steps, the system provides a personalized news experience tailored to the user's preferences.

[1527] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1528] The present invention is a system that provides news tailored to the user's preferences and interests, and also combines an emotion engine to provide an optimal news experience according to the emotional state of each individual user. Below, we will explain the program processing and specific examples of this system.

[1529] Registering users and setting preferences

[1530] 1. A user accesses the application and is presented with a new user registration screen.

[1531] 2. Users enter basic information such as their name, email address, and password, as well as their preferred genres and topics (e.g., politics, economics, entertainment), and set visual styles such as font size, color, preferred language, region, and number and length of news characters.

[1532] 3. The information provided by the user is sent from the device to the server, where it is stored in a database.

[1533] News gathering

[1534] 1. The server periodically accesses multiple news sources (e.g., news sites, RSS feeds, news APIs) to collect the latest news data.

[1535] 2. The collected news data is stored in a database on the server.

[1536] News analysis based on user preferences

[1537] 1. The server retrieves user preferences and settings from a database.

[1538] 2. The server filters the collected news data based on the user's preferences, taking into account criteria such as genre, topic, language, region, and word count.

[1539] 3. The server uses AI algorithms to summarize the filtered news, sometimes adding related news and other perspectives.

[1540] Introducing the Emotion Engine

[1541] 1. The emotion engine installed on the device uses the user's camera and microphone to analyze facial expressions and tone of voice to recognize the user's emotional state.

[1542] 2. The recognized emotion data is sent from the device to the server.

[1543] 3. The server adjusts the priority and content of the news list based on the emotion data.

[1544] Personalized news generation

[1545] 1. The server generates an optimized news list based on the user's preferences and sentiment data.

[1546] 2. This news list is stored in a database and linked to the user's account.

[1547] News distribution to users

[1548] 1. The server sends the news list to the user's terminal.

[1549] 2. The terminal displays the news list on the user interface so that the user can check it.

[1550] User feedback and retraining

[1551] 1. Users provide feedback on the displayed news, such as "like" or "not interested."

[1552] 2. The feedback information is sent from the device to the server and stored in a database.

[1553] 3. The server uses the feedback to retrain the AI ​​algorithm to improve the accuracy of generating news lists.

[1554] For example, if a user likes the "Entertainment" genre and the emotion engine recognizes the user's positive emotional state, the server will prioritize filtering entertainment news containing optimistic content and add it to the news list along with summaries. On the other hand, if the user is in a negative emotional state, the server will include positive news articles to improve the user's mood.

[1555] In this way, the system provides a personalized news experience that takes into account the user's preferences and emotional state, reducing stress and time wasted due to information overload and promoting the user's mental health.

[1556] The processing flow will be explained below.

[1557] Step 1:

[1558] A user accesses the application and is presented with a new user registration screen.

[1559] Step 2:

[1560] Users enter basic information such as their name, email address, and password, as well as their preferred genres and topics (e.g., politics, economics, entertainment), and set visual styles such as font size, color, language, region, and word count and length of news.

[1561] Step 3:

[1562] The terminal collects this information and sends it to the server.

[1563] Step 4:

[1564] The server stores the received user information and setting information in a database.

[1565] Step 5:

[1566] The server periodically accesses multiple predefined news sources (e.g., news sites, RSS feeds, news APIs) to collect the latest news data.

[1567] Step 6:

[1568] The collected news data is stored in a database on the server.

[1569] Step 7:

[1570] The server retrieves user preferences and settings from a database.

[1571] Step 8:

[1572] The server filters the news data based on the user's preferences, such as genre, topic, language, region, and word count.

[1573] Step 9:

[1574] The server uses AI algorithms to generate filtered news summaries, adding related news and perspectives as needed.

[1575] Step 10:

[1576] The emotion engine installed on the device uses the user's camera and microphone to analyze facial expressions and tone of voice to recognize the user's emotional state.

[1577] Step 11:

[1578] The recognized emotion data is transmitted from the terminal to the server.

[1579] Step 12:

[1580] The server adjusts the priority and content of the news list based on the emotional data, selecting news according to the user's emotional state, such as positive or negative emotions.

[1581] Step 13:

[1582] The server generates a personalized news list taking into account the emotional data and user preferences.

[1583] Step 14:

[1584] The generated news list is stored in a database on the server and linked to the user's account.

[1585] Step 15:

[1586] The server sends the news list to the user's terminal.

[1587] Step 16:

[1588] The terminal displays the news list on the user interface so that the user can check it.

[1589] Step 17:

[1590] Users provide feedback on the displayed news, such as "like" or "not interested."

[1591] Step 18:

[1592] The feedback information is sent from the terminal to the server.

[1593] Step 19:

[1594] The server stores the feedback information in a database and uses it to retrain the AI ​​algorithm.

[1595] Step 20:

[1596] The retrained AI algorithm will improve the accuracy of the next news list generation.

[1597] Example 2

[1598] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1599] Current news delivery systems primarily provide news based on users' preferences and interests, but few systems consider the user's emotional state when providing news. This can result in users receiving news that is inappropriate for their current emotional state, potentially adversely affecting how they receive and understand information. Furthermore, there are insufficient mechanisms for reducing stress and fatigue caused by information overload, making it difficult to maintain users' mental health.

[1600] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting information on preferences and interests input by the user, means for collecting data from multiple information sources, means for filtering the collected data based on the user's preferences and interests and generating a summary, means for analyzing the user's emotional state using an emotion recognition engine of the terminal and adjusting the data based on this information, means for generating a list personalized for each user and delivering it to the terminal, and means for collecting user feedback, re-learning, and improving the accuracy of list generation. This enables personalized news delivery that takes into account not only the user's preferences and interests but also their emotional state.

[1601] "User-entered preference and interest information" refers to personal preference information provided by individual users, such as genres, topics, types of news, and visual styles that interest them.

[1602] "Multiple sources" refers to various news sources, such as news sites, RSS feeds, and news APIs.

[1603] "Data filtering" is the process of selecting collected news data based on the user's preferences and interests.

[1604] "Generating a summary" is the process of shortening the filtered news data into a concise format that includes the main points.

[1605] An "emotion recognition engine" is software that uses the device's built-in camera and microphone to analyze the user's facial expressions and tone of voice and recognize their emotional state.

[1606] "Adjusting data" is a process of changing the contents and priorities of the news list based on the emotion data obtained from the emotion recognition engine.

[1607] A "personalized list" is a collection of news articles that is customized based on an individual user's preferences and emotional state.

[1608] "Delivering to terminal" refers to the process of sending the generated news list to the device used by the user.

[1609] "Feedback" refers to user-provided ratings and reactions to news articles, such as "like" or "not interested."

[1610] "Retraining" is the process of improving the AI ​​algorithm based on collected feedback to improve the accuracy of generating news lists.

[1611] This invention is a system that provides optimal information experiences according to the emotional state of each individual user by combining a system that provides information tailored to the user's preferences and interests with an emotion recognition engine. The specific configuration and operating procedures for implementing this system are described below.

[1612] Registering users and setting preferences

[1613] 1. When a user accesses the application, a new user registration screen appears, where the user enters basic information such as name, email address, and password, as well as the genres and topics of interest.

[1614] 2. The user further configures the visual style, such as font size, color, language, region, and length and character count of the information.

[1615] 3. The information entered from the device is sent to the server. For security reasons, an encrypted protocol (e.g., HTTPS) is used for this transmission.

[1616] 4. The server stores the received information in a database.

[1617] Collection of information

[1618] 1. The server automatically collects data from multiple sources (e.g., websites, RSS feeds, APIs) and this collection is configured to occur periodically.

[1619] 2. Data from each source is collected on the server in a standard format (e.g., JSON, XML).

[1620] 3. The server stores the collected data in a database and keeps the information up to date.

[1621] Analyzing information based on user preferences

[1622] 1. The server retrieves user preferences and settings from a database, including information about genre, topic, language, region, and character count.

[1623] 2. The server filters the collected data based on the user's preferences. For example, if a user is interested in the entertainment genre, it will only show articles in that genre.

[1624] 3. The server uses AI algorithms (e.g., natural language processing models, generative AI models) to summarize the filtered data and add relevant information and multifaceted perspectives.

[1625] Introducing the Emotion Engine

[1626] 1. The device's built-in emotion recognition engine uses the camera and microphone to analyze the user's facial expressions and tone of voice to recognize their emotional state. This analysis uses machine learning models (e.g., facial expression recognition model, voice emotion recognition model).

[1627] 2. The recognized emotion data is sent from the device to the server.

[1628] 3. The server adjusts the priority and content of the information list based on the emotional data. For example, when the user is in a positive emotional state, information with positive content is displayed preferentially.

[1629] Generate personalized information

[1630] 1. The server generates an optimal information list based on the user's preferences and emotional data. This list is customized for each user.

[1631] 2. The generated information list is stored in a database and linked to each user's account.

[1632] Information distribution to users

[1633] 1. The server sends the optimized information list to the device using a secure communication protocol (e.g., HTTPS, WebSocket).

[1634] 2. The terminal displays the received information list on the user interface for easy access by the user.

[1635] User feedback and retraining

[1636] 1. The user provides feedback on the displayed information, such as "like" or "not interested."

[1637] 2. The device sends user feedback to the server and receives real-time ratings.

[1638] 3. The server retrains the AI ​​algorithm based on the feedback to improve the accuracy of generating information lists.

[1639] For example, if a user likes the "Entertainment" genre and the emotion engine recognizes the user's positive emotional state, the server will prioritize filtering entertainment information containing optimistic content and add it to the information list along with a summary. On the other hand, if the user is in a negative emotional state, the server will adjust the information list to include positive information to improve the user's mood.

[1640] An example of a prompt sentence to input to the generative AI model could be, "If the user is interested in entertainment and is currently in a positive emotional state, generate an optimistic news title. For example, 'The latest movie is a huge hit!'"

[1641] This system provides information that takes into account the user's preferences and emotional state, thereby reducing stress caused by information overload and helping to maintain the user's mental health.

[1642] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1643] Step 1:

[1644] When a user accesses the application, a new user registration screen appears. At this point, the user enters information such as their name, email address, password, genres and topics of interest, font size, color, preferred language, region, number and length of news characters, etc. This information is sent from the device to the server as the user's individual setting data.

[1645] Input: User's personal information (name, email address, password, genre, topic, font size, color, language, region, number of characters and length of news)

[1646] Output: Sending configuration information from the device to the server

[1647] Step 2:

[1648] The server receives the user's individual setting information sent from the terminal and stores it in a database. This database is used to centrally manage the individual setting information of all users.

[1649] Input: User personalized information sent from the device

[1650] Output: User personalization information stored in the database

[1651] Step 3:

[1652] The server accesses multiple news sources (e.g., news sites, RSS feeds, news APIs) at regular intervals to automatically collect new news data, which is then stored in a database in a specific format (e.g., JSON, XML).

[1653] Input: Latest news data from news sources

[1654] Output: Latest news data stored in a database

[1655] Step 4:

[1656] The server retrieves user preferences and settings from the database, and uses this information to filter the collected news data and extract only news that matches the user's interests and settings.

[1657] Input: User preferences and settings information and latest news data from a database

[1658] Output: Filtered news data

[1659] Step 5:

[1660] The server uses AI algorithms (e.g., natural language processing models, generative AI models) to summarize the filtered news data. The summary is a concise representation of the main points, and may also include related news and other perspectives.

[1661] Input: Filtered news data

[1662] Output: Summarized news data and related information

[1663] Step 6:

[1664] The device's built-in emotion recognition engine uses the camera and microphone to analyze the user's facial expressions and tone of voice, and then uses machine learning models to identify the user's emotional state.

[1665] Input: User facial and voice data via camera and microphone

[1666] Output: Analyzed sentiment data

[1667] Step 7:

[1668] The device sends the acquired emotional data to the server, which then adjusts the content and priority of the news list based on this data. For example, if the user is in a positive emotional state, news with positive content will be displayed first.

[1669] Input: Emotion data sent from the device

[1670] Output: Adjusted news list

[1671] Step 8:

[1672] The server generates a news list based on the user's preferences and sentiment data, which is customized for each user.

[1673] Input: User preferences, settings, and emotional data

[1674] Output: A personalized news list

[1675] Step 9:

[1676] The server sends the generated news list to the terminal using a secure protocol (e.g. HTTPS, WebSocket).

[1677] Input: personalized news list

[1678] Output: News list delivered to the device

[1679] Step 10:

[1680] The terminal displays the received news list on the user interface and provides it to the user, who then checks the news list and provides feedback.

[1681] Input: News list sent from the server

[1682] Output: Display the news list in a user interface

[1683] Step 11:

[1684] Users provide feedback such as "like" or "not interested" to the displayed news, which is then sent from the device to the server.

[1685] Input: User feedback

[1686] Output: Sending feedback from the device to the server

[1687] Step 12:

[1688] The server collects user feedback and stores it in a database, which is used to retrain the AI ​​algorithm to improve the accuracy of generating news lists.

[1689] Input: User feedback

[1690] Output: Retrained AI algorithm and improved news list generation accuracy

[1691] (Application example 2)

[1692] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1693] Conventional news delivery systems only consider the user's preferences and interests, ignoring the user's emotional state. As a result, users may feel stressed due to information overload, or the news provided may not match their mood at the time. Furthermore, when news is provided in an autonomous vehicle, passengers may not be able to relax while driving. To solve these problems, a personalized news delivery system that considers both the user's preferences and emotional state is needed.

[1694] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting information related to preferences and interests input by the user; means for collecting information data from multiple information sources; means for filtering the collected information data based on the user's preferences and interests and generating a summary; means for generating an information list personalized for each user and distributing it to the device; means for collecting user feedback and relearning to improve the accuracy of generating the information list; means for recognizing the user's emotional state based on facial expressions and tone of voice; and means for adjusting the priority and content of the information list based on the user's emotional state. This enables an optimal news experience that takes into account the user's preferences and emotional state.

[1695] A "user" is a person who uses the system.

[1696] "Information about preferences and interests" includes information such as the genres and topics, visual style, language, and region in which the user is interested.

[1697] "Sources" are sources that provide news data, such as news sites, RSS feeds, and news APIs.

[1698] "Information data" is data collected from information sources such as news, articles, and reports.

[1699] "Filtering" is the process of selecting appropriate data from collected information data based on the user's preferences and interests.

[1700] The "summary" is a concise summary of the filtered information data.

[1701] An "information list" is a list of news and articles that has been filtered and summarized and is provided to the user.

[1702] "Devices" refer to devices such as smartphones, tablets, and head-mounted displays installed inside autonomous vehicles.

[1703] "Feedback" refers to ratings and comments such as "like" or "not interested" that users make about the displayed news.

[1704] "Retraining" is the process of using collected feedback information to refine the system's algorithms and improve the accuracy of the information list.

[1705] "Emotional state" refers to the psychological state of the user, which is analyzed from facial expressions and tone of voice.

[1706] "Priority and content adjustment" is the process of adapting the display order and content of news and articles in an information list based on the user's emotional state.

[1707] This invention combines an emotion engine with a system that provides news tailored to the user's preferences and interests to provide an optimal news experience that matches the emotional state of each individual user. The following describes the processing content of the program and the hardware and software used to realize this system.

[1708] Registering users and setting preferences

[1709] When a user accesses the application, a new user registration screen is displayed. The user enters basic information such as name, email address, and password, as well as genres and topics of interest (e.g., politics, economics, entertainment). The user also sets visual styles such as font size, color, preferred language, region, and number and length of news characters. This information is sent from the device to the server, where it is stored in a database.

[1710] News gathering

[1711] The server periodically accesses multiple news sources (e.g., news sites, RSS feeds, news APIs) to collect the latest news data, which is then stored in the server's database.

[1712] News analysis based on user preferences

[1713] The server retrieves user preferences and settings from the database and filters the collected news data based on the user's preferences. It considers criteria such as genre, topic, language, region, and word count, and then uses an AI algorithm to summarize the filtered news. In some cases, related news and information from multiple perspectives are also added.

[1714] Introducing the Emotion Engine

[1715] The device's built-in emotion engine analyzes the user's facial expressions and tone of voice to recognize their emotional state. This emotion data is sent from the device to a server, which then adjusts the priority and content of the news list based on the emotion data.

[1716] Personalized news generation

[1717] The server generates an optimized news list based on the user's preferences and sentiment data, which is stored in a database and linked to the user's account.

[1718] News distribution to users

[1719] The server transmits the news list to the user's terminal, which displays the news list on a user interface.

[1720] User feedback and retraining

[1721] Users provide feedback on the displayed news, such as "like" or "not interested," which is then sent from the device to the server and stored in a database. The server then uses the feedback to retrain the AI ​​algorithm and improve the accuracy of generating news lists.

[1722] For example, if a user is interested in entertainment in an autonomous vehicle, the emotion engine will recognize the user's positive emotional state and the server will prioritize entertainment news with optimistic content to add to the list. Conversely, if the user is in a negative emotional state, the server will include positive news articles to improve the user's mood.

[1723] Example prompt sentence:

[1724] Generate sample code for a system that takes user preferences into account and uses an emotion engine to provide the most appropriate news articles. This system is intended for use in self-driving cars. It uses the in-car camera and microphone to analyze passenger emotions in real time and prioritizes the display of news articles according to their emotional state. The system continuously optimizes the news suggestions based on passenger feedback.

[1725] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1726] Step 1: Register and set your preferences

[1727] When a user logs in to the application, a new user registration screen is displayed. The user enters basic information such as name, email address, and password, as well as the genres and topics they are interested in. They also set visual styles such as font size and color, preferred language, region, and number and length of news characters. This input data is sent from the device to the server, where it is stored in a database.

[1728] Step 2: Gathering news

[1729] The server periodically accesses multiple news sources to collect the latest news data. This input data is obtained from various news sites, RSS feeds, news APIs, etc. and stored in a database on the server. The server analyzes the news title, content, publication time, images, etc., and stores them in a structured database.

[1730] Step 3: Analyzing and filtering news based on user preferences

[1731] The server retrieves user preferences and settings from the database and uses them as input to filter the collected news data. In this step, it considers criteria such as genre, topic, language, region, and word count to select news that matches the user's interests. The filtered news data is output and then sent to the summarization process.

[1732] Step 4: Generate news summaries and add related news

[1733] The server uses AI algorithms to summarize the filtered news and also adds related news and information from multiple perspectives. The input data is the filtered news data, and from this it generates summaries and related information. The output is a summarized news list.

[1734] Step 5: Analyze the user's emotional state with the emotion engine

[1735] The device uses a camera and microphone to capture the user's facial expressions and tone of voice. This captured data is analyzed on the device to recognize the user's emotional state. The emotional data is generated as output and sent to the server.

[1736] Step 6: Adjusting the news list based on emotional state

[1737] The server obtains the emotional data and adjusts the ranking and content of the news list based on it. The input data are the emotional data and the summarized news list, and the adjustment is made based on these. The output is a news list optimized based on the emotional state.

[1738] Step 7: Generate and deliver personalized news

[1739] The server generates an optimized news list for each user and stores it in a database. The news list is then delivered to the autonomous vehicle's terminal for display. The input data is the adjusted news list, and the output is the news list displayed on the device.

[1740] Step 8: User feedback and retraining

[1741] Users provide feedback on the displayed news, such as "like" or "not interested." This feedback data is sent from the device to the server, which stores it in a database. The server then retrains the AI ​​algorithm based on the collected feedback to improve the accuracy of news list generation. The input data is the feedback information, and the output is an improved algorithm.

[1742] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1743] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1744] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1745] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1746] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1747] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1748] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1749] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1750] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1751] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1752] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1753] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1754] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1755] 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.

[1756] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1757] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1758] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1759] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1760] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1761] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1762] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1763] The following is further disclosed regarding the above embodiment.

[1764] (Claim 1)

[1765] a means of collecting information about user input preferences and interests;

[1766] a means for collecting news data from multiple news sources;

[1767] means for filtering the collected news data based on a user's preferences and interests and generating summaries;

[1768] means for generating a news list personalized for each user and delivering it to the terminal;

[1769] A means for collecting user feedback and re-learning to improve the accuracy of generating news lists;

[1770] A system including:

[1771] (Claim 2)

[1772] 10. The system of claim 1, including means for taking into account language, region, and visual style when collecting and filtering news data.

[1773] (Claim 3)

[1774] 10. The system of claim 1, further comprising means for adding related news and multi-perspective information when generating a news summary.

[1775] "Example 1"

[1776] (Claim 1)

[1777] a means of collecting information about user input preferences and interests;

[1778] A means of collecting news data from multiple sources;

[1779] means for filtering the collected news data based on a user's preferences and interests and generating summaries;

[1780] means for generating a news list personalized for each user and delivering it to the terminal;

[1781] A means for collecting user feedback and re-learning to improve the accuracy of generating news lists;

[1782] A system including:

[1783] (Claim 2)

[1784] 10. The system of claim 1, including means for taking into account language, region, and visual style when collecting and filtering news data.

[1785] (Claim 3)

[1786] 10. The system of claim 1, further comprising means for adding related news and multi-perspective information when generating a news summary.

[1787] "Application Example 1"

[1788] (Claim 1)

[1789] a means of collecting information about user input preferences and interests;

[1790] a means for collecting news data from multiple news sources;

[1791] means for filtering the collected news data based on a user's preferences and interests and generating summaries;

[1792] means for generating a news list personalized for each user and delivering it to the terminal;

[1793] A means for collecting user feedback and re-learning to improve the accuracy of generating news lists;

[1794] A means for summarizing the collected news data using an artificial intelligence model;

[1795] A system including:

[1796] (Claim 2)

[1797] 10. The system of claim 1, including means for taking into account language, region, and visual style when collecting and filtering news data.

[1798] (Claim 3)

[1799] 10. The system of claim 1, further comprising means for adding related news and multi-perspective information when generating a news summary.

[1800] "Example 2: Combining Emotion Engines"

[1801] (Claim 1)

[1802] a means of collecting information about user input preferences and interests;

[1803] a means of collecting data from multiple sources;

[1804] means for filtering the collected data based on user preferences and interests and generating summaries;

[1805] means for analyzing the user's emotional state using an emotion recognition engine in the device and adjusting the data based on this information;

[1806] A means for generating a personalized list for each user and delivering it to the terminal;

[1807] A means for collecting user feedback and re-learning to improve the accuracy of list generation;

[1808] A system including:

[1809] (Claim 2)

[1810] 10. The system of claim 1, including means for taking language, region, and visual style into account when collecting and filtering data.

[1811] (Claim 3)

[1812] 10. The system of claim 1, further comprising means for adding related information and multi-perspective information when generating a summary of the data.

[1813] "Application example 2 when combining emotion engines"

[1814] (Claim 1)

[1815] a means of collecting information about user input preferences and interests;

[1816] a means for collecting information data from a plurality of information sources;

[1817] means for filtering the collected information data based on user preferences and interests and generating summaries;

[1818] means for generating a personalized information list for each user and delivering it to the device;

[1819] A means for collecting user feedback and re-learning to improve the accuracy of generating the information list;

[1820] means for recognizing a user's emotional state based on facial expressions and tone of voice;

[1821] means for adjusting the priority and content of the information list based on the user's emotional state;

[1822] A system including:

[1823] (Claim 2)

[1824] 10. The system of claim 1, including means for taking into account language, region, and visual style when collecting and filtering information data.

[1825] (Claim 3)

[1826] 10. The system of claim 1, further comprising means for adding related information and information from multiple perspectives when generating a summary of information. [Explanation of symbols]

[1827] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means of collecting information about user input preferences and interests; a means for collecting news data from multiple news sources; means for filtering the collected news data based on a user's preferences and interests and generating summaries; means for generating a news list personalized for each user and delivering it to the terminal; A means for collecting user feedback and re-learning to improve the accuracy of generating news lists; A system including:

2. 10. The system of claim 1, further comprising means for taking into account language, region, and visual style when collecting and filtering news data.

3. 10. The system of claim 1, further comprising means for adding related news and multi-perspective information when generating a news summary.

Images