System

Abstract

A system is provided.SOLUTION: A system including means for collecting article data from a plurality of reliable information sources, means for storing the collected article data, means for performing natural language processing on the stored article data to extract important information, means for generating an article summary based on the extracted information using a generated AI model, means for storing the generated summary, means for trend-analyzing the summary data to identify a trend, and means for searching and displaying the summary based on conditions specified by a user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In modern society, the amount of information is increasing, making it difficult to keep up with the latest trends and news. It is particularly difficult for busy people and those who are not particularly interested in news to efficiently obtain the information they need from reliable sources. In such situations, the risk of missing important information or making decisions based on incorrect information increases. Therefore, there is a need for a system that allows users to easily and accurately understand trends and news. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for collecting article data from multiple reliable sources, a means for saving the collected article data, and a means for performing natural language processing on the saved article data to extract important information. The system also includes a means for generating article summaries based on information extracted using a generative AI model, a means for saving the generated summaries, and a means for analyzing trends in the summary data to identify trends. The system further includes a means for searching and displaying summaries based on user-specified criteria, allowing users to easily grasp the latest trend information. The system further includes a means for saving trend analysis results and providing them for user access, and a means for users to view detailed information based on the summary data, thereby more effectively supporting users in gathering information.

[0006] "Trusted sources" refers to widely recognized news sites, official organizations, and trusted third-party organizations that provide accurate and trustworthy information.

[0007] "Article Data" refers to data containing textual information about a particular topic, such as news articles or reports.

[0008] "Storage means" refers to a mechanism for storing collected article data and generated summaries in a database or file system, and keeping them accessible as needed.

[0009] "Natural language processing" refers to the technology of analyzing text to understand its meaning and structure and extract information, including tokenization, part-of-speech tagging, and sentence segmentation.

[0010] "Means for extracting important information" refers to a system that uses natural language processing technology to find key keywords and sentences from article data and extract them as necessary information.

[0011] "Generative AI model" refers to an artificial intelligence model that automatically generates text based on existing data, including models specifically trained for summary generation.

[0012] "Means for generating article summaries" refers to a mechanism that uses a generative AI model to summarize key information and present it in a short form.

[0013] "Trend analysis" refers to an analytical method that extracts frequently occurring keywords and topics from multiple summary data sets and identifies themes and trends that are currently attracting attention.

[0014] "User-specified criteria" refers to criteria that allow a user to filter information based on news type, country, category, time period, etc.

[0015] "Means for searching and displaying" refers to a mechanism for searching summary data based on conditions specified by the user and visually presenting the results to the user.

[0016] "Means for viewing detailed information" refers to a mechanism that allows users to access and view the original article and additional analysis results based on the generated summary. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] This invention is a system that uses a generative AI model to automatically generate summaries based on article data collected from multiple reliable sources, allowing users to easily grasp the latest trend information. This system includes the following main elements:

[0039] 1. News gathering

[0040] The server collects news articles from multiple reliable sources, using RSS feeds and APIs to periodically retrieve the latest article data, which is then stored in a database for easy access later.

[0041] 2. Natural Language Processing (NLP)

[0042] The server performs natural language processing on the collected news articles, tokenizing the text, tagging parts of speech, segmenting sentences, and extracting important keywords and phrases, which helps clarify key information within the articles.

[0043] 3. Summary Generation

[0044] The server uses the extracted information to generate a summary of the article using a generative AI model, which is pre-trained on a large amount of data to provide an appropriately summarized text. The generated summary is stored in a database for later retrieval and display.

[0045] 4. Trend Analysis

[0046] The server analyzes the generated summary data and identifies trends by extracting frequently occurring keywords and topics. The results of this trend analysis provide the basis for users to quickly grasp the latest trends.

[0047] 5. User Interaction

[0048] Users can access the system from their smartphones or PCs and view news summaries. They can enter search criteria and filtering options to narrow down news for specific countries or categories. For example, they can select "Global Economic Trends" or "Japanese Political News."

[0049] Based on user input, the terminal sends a request to the server to search for the relevant news summary. The server receives the request, searches for the relevant summary from its database, and sends it to the terminal. The terminal displays a list of the received summaries to the user. When the user clicks on a specific news summary, the terminal requests more information from the server, displaying the original article and additional analysis results. In this way, users can quickly and easily grasp the latest trend information.

[0050] Specific examples

[0051] During the morning commute, a user launches the app on their smartphone and checks the latest news summaries. If the user is interested in economic news, they set the category to "Economy" and retrieve the latest summaries. The server searches the summary database based on the set criteria and sends the relevant summaries to the device. The user scrolls through the displayed summaries and clicks on interesting news to obtain more information.

[0052] Furthermore, when users return home and want to read more about the news on their PC, they can select the important news summary of the day and view more detailed analysis results and the original article, allowing users to quickly gather a wide range of information and gain a deeper understanding.

[0053] Thus, the present invention is a system that allows users to efficiently and effectively stay up to date with the latest news and trends.

[0054] The processing flow will be explained below.

[0055] Step 1:

[0056] The server collects the latest article data from multiple reliable sources. Specifically, it periodically retrieves news articles using RSS feeds and APIs. The retrieved article data is stored in a database along with metadata such as the article title, text, and publication date.

[0057] Step 2:

[0058] The server performs natural language processing (NLP) on the stored article data, tokenizing the article text, tagging it by part of speech, and segmenting it into sentences. It also analyzes the article content to extract important keywords and phrases.

[0059] Step 3:

[0060] The server uses a generative AI model to generate a summary of the article based on the information extracted by the NLP process. The generative AI model has been trained on a large amount of summary data in advance, and it creates a short summary of the main points of the article. This generated summary is stored in a database.

[0061] Step 4:

[0062] The server performs trend analysis on the generated summary data, extracting frequently occurring keywords and topics from the summary data to identify themes and trends that are currently attracting attention. The results of this trend analysis are also stored in a database.

[0063] Step 5:

[0064] Users access the system from their smartphones or PCs to view news summaries, set filtering options (e.g., country, category, time period), and enter search criteria.

[0065] Step 6:

[0066] The terminal sends a request to the server based on the search criteria entered by the user, including any filtering options set by the user.

[0067] Step 7:

[0068] The server searches the database for relevant news summaries based on the received search criteria, finds the appropriate summary data, and sends it to the terminal.

[0069] Step 8:

[0070] The terminal displays the news summaries received from the server to the user, who can scroll through the displayed list of summaries to check them.

[0071] Step 9:

[0072] If a user wants to select a particular news summary and view more detailed information, he or she clicks on the summary.

[0073] Step 10:

[0074] The terminal sends a detailed information request to the server based on the user's selection.

[0075] Step 11:

[0076] The server receives a request for detailed information, searches the database for the relevant original article and additional analysis results, and sends them to the terminal.

[0077] Step 12:

[0078] The device displays the detailed information received from the server to the user, who can then view the full text of the original article and additional analysis results.

[0079] Example 1

[0080] 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."

[0081] In recent years, the diversification of information and the vast amount of news articles available on the Internet have made it difficult for users to efficiently grasp important information and the latest trend information. Furthermore, manually collecting news articles, summarizing them, and analyzing trends requires a great deal of time and effort. Therefore, there is a need for a system that automates the process from article collection to summarization and trend analysis, allowing users to quickly obtain the information they need.

[0082] 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.

[0083] In this invention, the server includes means for collecting article data from multiple reliable information sources, means for saving the collected article data in a database, means for performing natural language processing on the saved article data and extracting important information, means for generating article summaries based on prompt sentences using a generative AI model, means for saving the generated summaries in a database, means for performing trend analysis on the summary data to identify trends, and means for searching for and displaying summaries based on user-specified conditions. This automates the collection, summarization, and trend analysis of news articles, enabling users to efficiently and quickly grasp important information and the latest trends.

[0084] "Reliable sources" refers to multiple sources and services that provide accurate and trustworthy news and articles.

[0085] "Article data" refers to content data including news, blogs, release information, etc.

[0086] A "database" refers to an information system that systematically stores collected data and generated information and enables it to be searched and managed.

[0087] "Natural language processing" refers to the technologies and methods that allow computers to understand, analyze, and process human language.

[0088] A "generative AI model" is an artificial intelligence model that learns from existing data and has the ability to generate new information.

[0089] A "prompt sentence" refers to an input sentence provided to an AI model to perform a specific task.

[0090] "Summary" refers to summary information that briefly summarizes the content of the original article.

[0091] "Trend analysis" refers to the process of analyzing frequently occurring keywords and topics within data to identify current trends and themes that are attracting attention.

[0092] "User-specified criteria" refers to the parameters and options that a user specifically sets for searching or filtering.

[0093] "Request" refers to a request sent by a user to a system to obtain specific data or information.

[0094] "Searching" refers to the process of locating information in a database based on specific criteria.

[0095] "Display" refers to presenting search results and related information on the screen in a format that is easy for the user to see.

[0096] This invention is a system that uses a generative AI model to automatically generate summaries based on article data collected from multiple reliable sources, allowing users to easily grasp the latest trend information. This system includes several main processes, each of which is implemented using specific hardware and software.

[0097] Hardware and Software Configuration

[0098] The server plays a central role in collecting news articles from multiple reliable sources and storing, analyzing, and generating them. The server stores data using a database (e.g., MySQL (registered trademark) or PostgreSQL) and analyzes the article data using a natural language processing (NLP) library (e.g., SpaCy or NLTK). The generative AI model can be, for example, GPT-3 (registered trademark) from OpenAI (registered trademark).

[0099] The terminal provides an interface for users to access the system. Terminals include smartphones and PCs, and send user input to the server and display information obtained from the server.

[0100] Process example

[0101] News gathering

[0102] The server configures RSS feeds or APIs to aggregate news articles from multiple reliable sources and periodically retrieves the latest article data, for example, using the RSS feed URL or API endpoint.

[0103] Natural Language Processing

[0104] The server performs natural language processing on the collected news articles, tokenizing the text, tagging parts of speech, splitting sentences, and extracting important keywords and phrases. For example, it uses the SpaCy library to tokenize and tag articles.

[0105] Summary Generation

[0106] The server uses the extracted information to generate a summary of the article using a generative AI model (e.g., OpenAI GPT-3), inputting a prompt to the model. For example, the following prompt can be used:

[0107] "Please summarize the following news article:"

[0108] Trend Analysis

[0109] The server analyzes the generated summary data, extracts frequently occurring keywords and topics, and identifies trends, for example by using the TF-IDF algorithm to select important keywords.

[0110] User Interaction

[0111] Users can access the system from their smartphones or PCs, search for summaries based on specified criteria, and view the displayed summaries. For example, if a user searches for "economic news," the server retrieves the relevant summaries from the database and sends them to the device.

[0112] Specific example explanation

[0113] Consider a scenario in which a user launches a smartphone app during their morning commute to check the latest news summaries. If the user is interested in "economic news," they set the category to "economics" and retrieve the latest summaries. The server searches the summary database based on the set criteria and sends the relevant summaries to the device. The user scrolls through the displayed summaries and clicks on interesting news to obtain more information. In this way, users can quickly and easily grasp the latest trending information.

[0114] As a result, the present invention is a system that allows users to efficiently and effectively stay up to date with the latest news and trends.

[0115] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0116] Step 1: Gather news articles

[0117] The server collects news articles from multiple reliable sources. Specifically, it periodically obtains the latest article data using RSS feeds or APIs. For example, the RSS feed URL or API endpoint is set on the server and an HTTP request is sent to obtain the latest article data. The input is the RSS feed or API endpoint, and the output is the collected news article data. This data is temporarily stored and used in the next step.

[0118] Step 2: Saving to the database

[0119] The server stores the collected news article data in a database. Specifically, it stores metadata such as article title, body text, and publication date in a database (e.g., MySQL or PostgreSQL). The input is the collected news article data, and the output is formatted data stored in the database. This stored data can be easily accessed in later processes.

[0120] Step 3: Natural Language Processing (NLP)

[0121] The server performs natural language processing on the stored news article data. Specifically, it tokenizes the article text, tags it with parts of speech, splits sentences, and extracts important keywords and phrases. This is done using a natural language processing library (e.g., SpaCy or NLTK). The input is the news article data stored in the database, and the output is tokens, part-of-speech tags, sentence split information, and a list of keywords. This processing clarifies important information within the article.

[0122] Step 4: Summary generation

[0123] The server uses the extracted information to generate a summary of the article using a generative AI model. Specifically, it generates a prompt, "Please summarize the following news article:," and inputs the prompt and article data into an AI model (e.g., OpenAI GPT-3). The AI ​​model generates a summary and returns the result to the server. The input is the prompt and article data, and the output is the generated summary text. This summary text is stored in a database.

[0124] Step 5: Save the summary to the database

[0125] The server stores the generated summary in a database. Specifically, it associates the generated summary with the article's metadata and stores it in the database. The input is the generated summary text, and the output is the summary data stored in the database. This stored summary is used for later trend analysis and user searches.

[0126] Step 6: Trend analysis

[0127] The server analyzes the generated summary data and identifies trends by extracting frequently occurring keywords and topics. Specifically, it extracts important keywords based on the summary text using TF-IDF (Term Frequency-Inverse Document Frequency) and other statistical methods. The input is the saved summary data, and the output is the extracted trend keywords and topics. This trend information is stored in a separate database.

[0128] Step 7: User interaction

[0129] Users access the system from their smartphones or PCs and browse news summaries. Specifically, users enter search criteria and filtering options to narrow down news from specific countries or categories. The device sends a request to the server based on the user's input. The input is the user's search criteria, and the output is a request to the server.

[0130] Step 8: Search and view the summary

[0131] The server receives a user request, searches for the relevant summary from the database, and sends it to the terminal. The terminal displays a list of the received summaries to the user. When the user clicks on a specific news summary, the terminal requests more information from the server and displays the original article and additional analysis results. The input is a request for more information from the user, and the output is the display of the detailed information. This allows the user to quickly and easily grasp the latest trend information.

[0132] (Application example 1)

[0133] 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."

[0134] In modern society, it is difficult for users to efficiently obtain reliable information from the news and articles provided by many sources. Furthermore, checking multiple sources individually is time-consuming, making it difficult to quickly grasp the latest trend information. Furthermore, there are few systems that can easily obtain the latest news summaries for a target category or topic, and that have the functionality to analyze trends and display frequently occurring keywords.

[0135] 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.

[0136] In this invention, the server includes means for collecting article data from multiple reliable information sources, means for saving the collected article data, means for performing natural language processing on the saved article data and extracting important information, means for generating article summaries based on the information extracted using a generative AI model, means for saving the generated summaries, means for performing trend analysis on the summary data to identify trends, means for searching and displaying summaries based on user-specified conditions, means for generating and distributing the latest news summaries for specified categories or topics, and means for automatically analyzing frequently occurring keywords from the news summaries and displaying trend information. This allows users to easily obtain the latest news summaries for specified categories or topics and quickly grasp trend information.

[0137] A "reliable source" refers to a trusted source that provides news and articles with high legitimacy and accuracy.

[0138] "Article data" refers to data that includes sentences or text information related to news or topics.

[0139] "Natural language processing" refers to the technology that enables computers to understand, interpret, and manipulate human language.

[0140] "Important information" refers to information contained within an article or text that is useful and meaningful to the user.

[0141] A "generative AI model" refers to a model in which artificial intelligence uses machine learning algorithms to generate new information from given data.

[0142] An "article summary" is a text that summarizes the content of the original article and briefly summarizes the main points.

[0143] "Summary data" refers to data containing text information of the generated summary.

[0144] "Trend analysis" refers to the process of analyzing frequently occurring keywords and topics within data to identify current trends and fads.

[0145] "User-specified conditions" refers to the filtering or search criteria set by the user for information extraction.

[0146] A "category" refers to a broad theme or field for classifying information.

[0147] A "topic" refers to a specific theme or subject of information.

[0148] "Latest News Summary" refers to text generated from collected news articles that summarizes the most current situations and events.

[0149] "Frequent keywords" refer to important words or phrases that appear frequently within the data being analyzed.

[0150] "Trend Information" refers to information about current trends and fads obtained as a result of trend analysis.

[0151] This invention is a system that uses a generative AI model to automatically generate summaries based on article data collected from multiple reliable sources, allowing users to easily grasp the latest trend information. The system includes the following main components:

[0152] 1. News gathering

[0153] The server collects news articles from multiple reliable sources, using RSS feeds and APIs to periodically retrieve the latest article data, which is then stored in a database for easy access later.

[0154] 2. Natural Language Processing (NLP)

[0155] The server performs natural language processing on the collected news articles, tokenizing the text, tagging parts of speech, segmenting sentences, and extracting important keywords and phrases, which helps clarify key information within the articles.

[0156] 3. Summary Generation

[0157] The server uses the extracted information to generate a summary of the article using a generative AI model, which is pre-trained on a large amount of data to provide an appropriately summarized text. The generated summary is stored in a database for later retrieval and display.

[0158] 4. Trend Analysis

[0159] The server analyzes the generated summary data and identifies trends by extracting frequently occurring keywords and topics. The trend analysis results serve as the basis for users to quickly grasp the latest trends. Trend information automatically analyzed from the summary data is also displayed.

[0160] 5. User Interaction

[0161] Users can access the system from their smartphones or PCs and view news summaries. They can enter search criteria and filtering options to narrow down news to specific categories or topics. For example, they can select "economic news" or "latest technology trends." The device sends a request to the server based on the user's input to search for relevant news summaries. The server receives the request, searches the database for relevant summaries, and sends them to the device. The device displays a list of received summaries to the user. When the user clicks on a specific news summary, the device requests more information from the server, displaying the original article and additional analysis results. In this way, users can quickly and easily grasp the latest trend information.

[0162] Specific examples

[0163] During the morning commute, a user launches the app on their smartphone and checks the latest news summaries. If the user is interested in economic news, they set the category to "Economy" and retrieve the latest summaries. The server searches the summary database based on the set criteria and sends the relevant summaries to the device. The user scrolls through the displayed summaries and clicks on interesting news to obtain more information. After returning home, if the user wants to read more about the news on their PC, they can select the important news summaries of the day and view more detailed analysis results and original articles. This allows users to quickly gather a wide range of information and gain a deeper understanding.

[0164] Prompt Sentence Examples

[0165] Example prompts to be input to the generative AI model:

[0166] "Summarize an article from a current, reliable news source. The text of the article is below: {article text}"

[0167] Thus, the present invention is a system that allows users to efficiently and effectively stay up to date with the latest news and trends.

[0168] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0169] Step 1:

[0170] The server collects news article data from multiple reliable sources, and periodically retrieves the latest article links using RSS feeds and APIs. As input, it uses the RSS feed URL or API endpoint, and as output, it gets a list of article URLs.

[0171] Step 2:

[0172] The server retrieves the text of each article based on the URL of the collected article. Specifically, it downloads the HTML data of the article using an HTTP request and extracts the article text using an HTML parsing library (e.g., BeautifulSoup). The article URL is used as input, and the article text is obtained as output.

[0173] Step 3:

[0174] The server performs natural language processing on the retrieved article text. Specifically, it tokenizes the text, tags parts of speech, splits sentences, and extracts important keywords and phrases. The article text is used as input, and the extracted important keywords and phrases are obtained as output. This processing uses an NLP library (e.g., NLTK or spaCy).

[0175] Step 4:

[0176] The server generates a summary of the article based on the extracted information using a generative AI model. Specifically, the article text is input into a generative AI model (e.g., BERT or GPT) to generate a summary text. The article text and extracted important keywords are used as input, and the summarized text is obtained as output.

[0177] Step 5:

[0178] The server stores the generated summaries in a database, specifically, it saves the summary data and metadata about the original article. It uses the summary text and article metadata as input and obtains the summary data stored in the database as output.

[0179] Step 6:

[0180] The server performs trend analysis on the stored summary data to identify trends. Specifically, it aggregates frequently occurring keywords and topics and extracts trend information. It uses the contents of the summary database as input and obtains the trend analysis results as output.

[0181] Step 7:

[0182] It searches and displays summaries based on user-specified criteria from the terminal. Specifically, the user enters a search filter (e.g., "economic news" or "technology") and sends a request to the server. The search criteria specified by the user are used as input, and a list of corresponding summaries is obtained as output.

[0183] Step 8:

[0184] The device requests and displays detailed information about the specific news summary selected by the user from the server. Specifically, it retrieves the original article and additional analysis results from the server and displays them to the user. The news summary clicked by the user is used as input, and the detailed information is obtained as output.

[0185] Step 9:

[0186] The server periodically updates the trend analysis results and makes them available for users to access. Specifically, it performs trend analysis again based on newly collected article data and makes the results available for users to view via a web interface or other means. The latest summary data is used as input, and updated trend analysis results are obtained as output.

[0187] As described above, this system is able to efficiently collect, summarize, analyze, and provide reliable, up-to-date information to users through each step.

[0188] 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.

[0189] This system uses a generative AI model to automatically generate summaries based on article data collected from multiple reliable sources, allowing users to easily grasp the latest trend information. Furthermore, it is equipped with an emotion engine that recognizes user emotions, and adds a function to adjust article summaries and recommendations according to the user's emotions. This system includes the following main components:

[0190] 1. News gathering

[0191] The server collects news articles from multiple reliable sources, using RSS feeds and APIs to periodically retrieve the latest article data, which is then stored in a database for easy access later.

[0192] 2. Natural Language Processing (NLP)

[0193] The server performs natural language processing on the stored news articles, tokenizing the text, tagging parts of speech, segmenting sentences, and extracting important keywords and phrases, which helps clarify key information within the article.

[0194] 3. Summary Generation

[0195] The server generates article summaries using a generative AI model based on the information extracted through NLP processing. The generative AI model is pre-trained with a large amount of data and provides appropriately summarized text. The generated summaries are stored in a database for later retrieval and display.

[0196] 4. Trend Analysis

[0197] The server analyzes the generated summary data and identifies trends by extracting frequently occurring keywords and topics. The results of this trend analysis provide the basis for users to quickly grasp the latest trends.

[0198] 5. Emotion Recognition by Emotion Engine

[0199] When a user accesses the system, the terminal activates an emotion engine to recognize the user's emotional state, for example, through analysis of the user's facial expressions or emotion analysis during text input.

[0200] 6. Utilizing Emotional Data

[0201] The server stores and analyzes the emotional data acquired by the emotion engine. Based on this data, the server adjusts the article summary and recommended articles according to the user's emotional state. For example, if the user is feeling stressed, articles about relaxation will be displayed preferentially.

[0202] 7. User Interaction

[0203] Users access the system from their smartphones or PCs and view news summaries. They can enter search criteria and filtering options to narrow down news from specific countries or categories. For example, they can select "Global Economic Trends" or "Japanese Political News."

[0204] Based on user input, the terminal sends a request to the server to search for the relevant news summary. The server receives the request, searches for the relevant summary from its database, and sends it to the terminal. The terminal displays a list of the received summaries to the user. When the user clicks on a specific news summary, the terminal requests more information from the server, displaying the original article and additional analysis results. In this way, users can quickly and easily grasp the latest trend information.

[0205] Specific examples

[0206] 1. Emotion Recognition and News Recommendation Example

[0207] During the morning commute, a user launches the app on their smartphone and checks the latest news summary. The emotion engine recognizes the user's emotions and detects that they are feeling stressed. The system prioritizes displaying articles related to relaxation, which can help reduce stress. The user can then click on an article of interest to continue reading.

[0208] 2. Example of adjusting news summaries according to sentiment

[0209] When the user returns home and wants to read more news on their PC, the emotion engine measures the user's emotions again and detects a relaxed state. While the system displays the usual trending news, it also provides summaries tailored to the user's emotions, ensuring the user receives the information most suited to their mood at the time.

[0210] Thus, the present invention is a system that allows users to efficiently and effectively grasp the latest news and trends while taking into account their emotions.

[0211] The processing flow will be explained below.

[0212] Step 1:

[0213] The server collects the latest article data from multiple reliable sources. Specifically, it periodically retrieves news articles using RSS feeds and APIs. The retrieved article data is stored in a database along with metadata such as the article title, text, and publication date.

[0214] Step 2:

[0215] The server performs natural language processing (NLP) on the stored article data, tokenizing the article text, tagging it by part of speech, and segmenting it into sentences. It also analyzes the article content to extract important keywords and phrases.

[0216] Step 3:

[0217] The server uses a generative AI model to generate a summary of the article based on the information extracted by the NLP process. The generative AI model is pre-trained with a large amount of data and creates a short summary of the main points of the article. The generated summary is then stored in a database.

[0218] Step 4:

[0219] The server performs trend analysis on the generated summary data, extracting frequently occurring keywords and topics from the summary data to identify themes and trends that are currently attracting attention. The results of this trend analysis are also stored in a database.

[0220] Step 5:

[0221] When a user accesses the system, the terminal activates an emotion engine to recognize the user's emotional state, for example, through analysis of the user's facial expressions or emotion analysis during text input.

[0222] Step 6:

[0223] The server stores and analyzes the emotion data acquired by the emotion engine, and adjusts article summaries and recommendations based on the emotion data according to the user's emotional state.

[0224] Step 7:

[0225] Users access the system from their smartphones or PCs to view news summaries, and can enter search criteria and filtering options to narrow down news from specific countries or categories.

[0226] Step 8:

[0227] The terminal sends a request to the server based on the search criteria entered by the user, including any filtering options set by the user.

[0228] Step 9:

[0229] The server searches the database for relevant news summaries based on the received search criteria, finds the appropriate summary data, and sends it to the terminal.

[0230] Step 10:

[0231] The terminal displays the news summaries received from the server to the user, who can scroll through the displayed list of summaries to check them.

[0232] Step 11:

[0233] If a user wants to select a particular news summary and view more detailed information, he or she clicks on the summary.

[0234] Step 12:

[0235] The terminal sends a detailed information request to the server based on the user's selection.

[0236] Step 13:

[0237] The server receives a request for detailed information, searches the database for the relevant original article and additional analysis results, and sends them to the terminal.

[0238] Step 14:

[0239] The device displays the detailed information received from the server to the user, who can then view the full text of the original article and additional analysis results.

[0240] Example 2

[0241] 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."

[0242] Currently, to stay up to date on new news and trending information, users must individually check numerous information sources, which takes time and effort. Furthermore, there is no system that provides appropriate information based on the user's emotional state, making it difficult to provide content that matches the user's mood and interests. This leads to a problem of reduced user satisfaction.

[0243] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting article data from multiple reliable information sources, means for saving the collected article data, means for performing natural language processing on the saved article data and extracting important information, means for generating article summaries based on the information extracted using a generative AI model, means for saving the generated summaries, means for performing trend analysis on the summary data to identify trends, means for searching and displaying summaries based on conditions specified by the user, means for recognizing the user's emotional state, and means for adjusting article summaries and recommended articles based on the recognized emotional state. This allows users to efficiently grasp the latest news and trend information and further obtain appropriate information according to their emotions at that time.

[0244] A "source" is a reliable source of news articles or data.

[0245] "Article data" is a collection of text and metadata containing news or specific information.

[0246] A "gathering means" is a method or device for automatically acquiring article data from multiple sources.

[0247] "Storage means" refers to a method or device for storing collected article data in a database or the like so that it can be used for later processing.

[0248] "Natural language processing" is a process that involves tokenizing text data, tagging parts of speech, dividing sentences, and extracting important keywords and phrases.

[0249] A "generative AI model" is an artificial intelligence model that is trained in advance on large amounts of data and generates summaries and inferences from new data.

[0250] A "summary" is a concise summary of important information extracted from the original article data.

[0251] "Trend analysis" is the process of analyzing summary data to identify frequently occurring keywords and topics.

[0252] "Emotional state" indicates the user's emotions and is recognized through facial expression analysis and emotion analysis during text entry.

[0253] A "means for recognizing" is a method or device for detecting the emotional state of a user.

[0254] The "adjusting means" refers to a method or device that appropriately changes the article summary or recommended articles based on the user's emotional state.

[0255] The "search and display means" refers to a method or device that searches for summary data based on conditions specified by the user and displays the results to the user.

[0256] This invention is a system that uses a generative AI model to automatically generate article summaries based on article data collected from multiple reliable sources, allowing users to easily grasp the latest trend information. It also includes an emotion engine that recognizes the user's emotions, and has the ability to adjust article summaries and recommendations according to the user's emotional state. This system uses the following combination of major hardware and software:

[0257] First, the server collects news articles from multiple reliable sources. Specifically, it uses a web server (e.g., Apache (registered trademark), Nginx) to periodically obtain the latest article data through an RSS feed reader or the API of a news site. For example, articles are periodically obtained from the RSS feed URL "example-rss.com / rss / latest-news" and stored in a database (e.g., MySQL, PostgreSQL).

[0258] The server then performs natural language processing on the stored news articles, using NLP libraries (e.g., SpaCy, NLTK) to tokenize the article text, tag parts of speech, split sentences, and extract important keywords and phrases, thereby clarifying key information within the article.

[0259] The server then uses a generative AI model (e.g., GPT-4 (registered trademark)) to generate a summary of the article based on the information extracted by the NLP process. The generative AI model is pre-trained with a large amount of data and provides an appropriately summarized text using the prompt, "Please create a summary of this article." The generated summary is stored in a database for later retrieval and display.

[0260] The server also analyzes the generated summary data and identifies trends by extracting frequently occurring keywords and topics. This analysis is performed using data analysis tools (e.g., Pandas, NumPy). For example, if there are many articles containing keywords such as "AI," "economy," or "new virus," the server recognizes that the topic is currently trending.

[0261] When a user accesses the system, the device activates an emotion engine to recognize the user's emotional state. This emotion recognition uses a facial expression analysis library (e.g., OpenCV, DeepFace) and an emotion analysis tool for text input (e.g., VADER, TextBlob). Specifically, the device captures the user's facial expression with a camera and analyzes features such as "smiling" or "frowning."

[0262] The server stores and analyzes the emotional data acquired by the emotion engine. Based on this data, the server adjusts the article summary and recommended articles according to the user's emotional state. For example, if the server recognizes that the user is "feeling stressed," it will prioritize displaying articles related to relaxation.

[0263] Finally, users access the system from their smartphones or PCs to view news summaries. They input search criteria and filtering options to narrow down news for specific countries or categories. The device sends a request to the server based on the user's input, searches for relevant news summaries, and sends them to the device. The device displays a list of received summaries to the user, and when the user clicks on a specific news summary, detailed information is displayed.

[0264] In this way, users can quickly and efficiently grasp the latest trend information, and are provided with information that best suits their emotions at the time, thereby improving the user experience.

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

[0266] Step 1:

[0267] The server collects article data from multiple reliable sources. The input is an RSS feed URL or API endpoint. Specifically, it uses an RSS feed reader library (e.g., feedparser) to periodically retrieve the latest article data from the URL "example-rss.com / rss / latest-news". The output is the retrieved raw news article data.

[0268] Step 2:

[0269] The server stores the collected article data in a database. The input is the news article data obtained in step 1. Specifically, using a database management system (e.g., MySQL, PostgreSQL), the data is stored in a table with fields such as article title, body text, author, and publication date and time. The output is a record of the article stored in the database.

[0270] Step 3:

[0271] The server performs natural language processing (NLP) on the stored news articles. The input is the article data stored in the database. To do this, an NLP library (e.g., SpaCy, NLTK) is used to tokenize the text, tag parts of speech, segment sentences, and extract important keywords and phrases. The output is processed NLP feature data.

[0272] Step 4:

[0273] The server generates a summary of the article using a generative AI model (e.g., GPT-4) based on the information extracted by the NLP process. The input is the NLP feature data. The prompt sentence "Please create a summary of this article" is input to the generative AI model, and summary text is generated. The output is the generated summary text.

[0274] Step 5:

[0275] The server saves the generated summary data in a database. The input is the summary text. The specific operation is to save the summary text in a separate table in the database. The output is a summary record saved in the database.

[0276] Step 6:

[0277] The server analyzes the generated summary data and identifies trends by extracting frequently occurring keywords and topics. The input is the summary data. Data analysis tools (e.g., Pandas, NumPy) are used to aggregate frequently occurring keywords and topics and create graphs and lists to identify trends. The output is the identified trend data.

[0278] Step 7:

[0279] When a user accesses the system, the device activates the emotion engine to recognize the user's emotional state. The input is the user's facial expression and text input. Specifically, the device uses a facial expression analysis library (e.g., OpenCV, DeepFace) to analyze the user's facial expression. The output is the recognized emotion data.

[0280] Step 8:

[0281] The server stores and analyzes the emotion data acquired by the emotion engine. The input is the recognized emotion data. Specifically, the server stores the emotion data in a database and generates statistical data based on the user's emotion history. The output is the stored emotion data and the analysis results.

[0282] Step 9:

[0283] The server adjusts the summary content of articles and recommended articles based on the analyzed emotional data according to the user's emotional state. The inputs are emotional data and summary data. Specifically, the algorithm is adjusted to prioritize articles related to relaxation for users who are feeling stressed. The output is the adjusted summary and recommended articles.

[0284] Step 10:

[0285] Users access the system from their smartphones or PCs and view news summaries. Inputs include search criteria and filtering options. For example, the user might select "Japanese economic news." The terminal sends a request to the server based on this input, and the server searches the database for the corresponding news summary and sends it to the terminal. The output is the news summary that is displayed to the user.

[0286] Step 11:

[0287] The terminal sends a request to the server based on the user's input and receives news summaries. The input is the user's filtering conditions. The server receives the request, searches the database for the relevant summary, and sends it to the terminal. The output is the received summary information.

[0288] Step 12:

[0289] The terminal displays a list of received news summaries to the user, and when the user clicks on a particular news summary, it requests detailed information from the server. The input is the received summary information. The output is the displayed news summary and a request for detailed information.

[0290] In this way, the user can quickly and efficiently grasp the latest trend information and can obtain information that best suits his or her feelings at the time.

[0291] (Application example 2)

[0292] 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."

[0293] In today's world, news and trend information from reliable sources is extremely important. However, especially in self-driving vehicles, passengers have limited access to the information they need in real time. Furthermore, information provided does not take into account the emotional state of passengers, preventing passenger satisfaction. There is a need to develop a system that can solve these issues and provide more appropriate and comfortable information.

[0294] 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 article data from multiple reliable information sources, means for saving the collected article data, means for performing natural language processing on the saved article data and extracting important information, means for generating article summaries based on the extracted information using a generative AI model, means for saving the generated summaries, means for performing trend analysis on the summary data to identify trends, means for searching for and displaying summaries based on conditions specified by the user, means for recognizing the user's emotional state in an on-board system of an autonomous vehicle, and means for adjusting article summaries and recommendations based on the recognized emotional state. This allows users to access appropriate news summaries and trend information in real time while in an autonomous vehicle, and further allows them to receive information provided according to their emotional state.

[0295] "Reliable sources" refer to news sites and databases whose content is guaranteed to be accurate and fair and that are widely recognized.

[0296] "Article data" refers to information content such as text and images provided by news and media organizations.

[0297] "Collection means" refers to the methods and techniques used to continuously obtain the required data from a particular source.

[0298] "Storage means" refers to the mechanism by which collected data is persistently stored for later use.

[0299] "Natural language processing" refers to a set of techniques that enable computers to understand and analyze human language.

[0300] "Important information" refers to valuable content that is particularly needed among the collected data.

[0301] A "generative AI model" refers to an artificial intelligence model that learns using large amounts of data and generates appropriate outputs for specific inputs.

[0302] A "summary" is a concise summary of long data or information.

[0303] "Trend analysis" refers to an analytical technique for discovering specific patterns or trends in data.

[0304] A "trend" refers to movement in data that shows a particular direction or pattern.

[0305] "User-specified criteria" refers to the particular criteria or filtering options that a user is interested in or concerned with.

[0306] "In-vehicle system" refers to an electronic device installed in an autonomous vehicle that provides information and entertainment functions.

[0307] "Emotional state" refers to the psychological state recognized from the user's facial expressions and voice.

[0308] "Means for adjusting recommendations" refers to a mechanism that dynamically changes the selection and ranking of content provided based on the user's emotional state.

[0309] This invention is a system that utilizes the infotainment system of an autonomous vehicle to provide users with optimal news summaries and trend information in real time. The system is composed of the following main elements:

[0310] 1. News gathering

[0311] The server collects news articles from multiple reliable sources, using RSS feeds and APIs to periodically retrieve the latest article data, which is then stored in a database for easy access later.

[0312] 2. Natural Language Processing (NLP)

[0313] The server performs natural language processing on the stored news articles, tokenizing the text, tagging parts of speech, segmenting sentences, and extracting important keywords and phrases, which helps clarify key information within the article.

[0314] 3. Summary Generation

[0315] The server generates article summaries using a generative AI model based on the information extracted through NLP processing. The generative AI model is pre-trained with a large amount of data and provides appropriately summarized text. The generated summaries are stored in a database for later retrieval and display.

[0316] 4. Trend Analysis

[0317] The server analyzes the generated summary data and identifies trends by extracting frequently occurring keywords and topics. The results of this trend analysis provide the basis for users to quickly grasp the latest trends.

[0318] 5. Emotion Recognition by Emotion Engine

[0319] The in-car system activates an emotion engine when the user is in the car to recognize the user's emotional state through facial expression analysis using an in-car camera and voice analysis via a microphone.

[0320] 6. Utilizing Emotional Data

[0321] The server stores and analyzes the emotional data acquired by the emotion engine. Based on this data, the server adjusts the article summary and recommended articles according to the user's emotional state. For example, if the user is feeling stressed, articles about relaxation will be displayed preferentially.

[0322] 7. User Interaction

[0323] The user browses news summaries through the in-car infotainment system. The user can use voice commands or the touchscreen to select a specific news category or topic, for example, "Latest Technology Trends" or "Today's Top News." Based on the user's input, the in-car system sends a request to the server to search for relevant news summaries. The server receives the request, searches for relevant summaries in its database, and sends them to the in-car system. The in-car system displays the received summaries to the user. When the user clicks on a particular news summary, it requests more information from the server, displaying the original article and additional analysis results.

[0324] Specific hardware and software

[0325] Hardware: In-car cameras, microphones, in-car infotainment systems

[0326] Software: OpenCV (image analysis), speech recognition library, NLP library, generative AI models (e.g., GPT-3.5), database management system

[0327] Specific examples

[0328] Usage example:

[0329] As passengers enter the vehicle, the in-vehicle system begins facial expression analysis to recognize the user's emotional state.

[0330] The emotion engine determines that the user is relaxed and displays a news summary that matches their current mood.

[0331] When a user issues the voice command "Tell me today's top news stories," the in-car system will display a list of the most important news summaries for the user to view in more detail.

[0332] Example prompt sentence:

[0333] "Please summarize this article: {article_text}"

[0334] In this way, the present invention makes it possible to provide comfortable and personalized news in an autonomous vehicle, thereby improving user satisfaction.

[0335] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0336] Step 1:

[0337] News gathering:

[0338] The server retrieves article data from multiple reliable sources, using RSS feeds and API keys as input, to aggregate the latest news articles. The aggregated article data is then stored in a database for easy access in future processing.

[0339] Step 2:

[0340] Natural Language Processing:

[0341] The server applies natural language processing (NLP) to the stored news articles. Using the stored article data as input, it tokenizes the text, tags parts of speech, splits sentences, and extracts important keywords and phrases. This uncovers important information within the article and passes the extracted data on for further processing.

[0342] Step 3:

[0343] Summary generation:

[0344] The server generates a summary of the article using a generative AI model based on the information extracted by the NLP process. It uses key information from the extracted text as input to generate a prompt (e.g., "Please summarize this article: {article_text}"). As output, the generated summary text is stored in a database.

[0345] Step 4:

[0346] Trend analysis:

[0347] The server analyzes the generated summary data and identifies trends by extracting frequently occurring keywords and topics. Using the summary data as input, it applies data analysis algorithms, which generate trend information that is stored in a database for later retrieval and display.

[0348] Step 5:

[0349] Emotion recognition:

[0350] The in-vehicle system activates the emotion engine when the user is in the car to recognize the user's emotional state. As input, it uses facial expression data captured by an in-vehicle camera and voice data collected by an in-vehicle microphone. As output, analyzed emotion data is generated and sent to the server.

[0351] Step 6:

[0352] Leveraging sentiment data:

[0353] The server stores and analyzes the emotion data obtained from the emotion recognition engine. Using the emotion data as input, it applies an algorithm that adjusts article summary content and recommendations based on the user's emotional state. This results in appropriate news summaries and articles being selected and prepared for display to the user.

[0354] Step 7:

[0355] User interaction:

[0356] Users browse news summaries through their in-car infotainment system. They can use voice commands or the touchscreen as input to select a specific news category or topic, such as "Latest Technology Trends" or "Today's Top News." The server then searches for relevant news summaries based on the user's request and sends them to the in-car system. The in-car system displays the received summaries, and users can click on a specific news summary to view more information about it.

[0357] The above is the overall processing flow from news gathering to emotion recognition and article display.

[0358] 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.

[0359] 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.

[0360] 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.

[0361] [Second embodiment]

[0362] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0363] 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.

[0364] 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).

[0365] 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.

[0366] 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.

[0367] 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).

[0368] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0369] 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.

[0370] 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.

[0371] 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.

[0372] 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.

[0373] 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."

[0374] This invention is a system that uses a generative AI model to automatically generate summaries based on article data collected from multiple reliable sources, allowing users to easily grasp the latest trend information. This system includes the following main elements:

[0375] 1. News gathering

[0376] The server collects news articles from multiple reliable sources, using RSS feeds and APIs to periodically retrieve the latest article data, which is then stored in a database for easy access later.

[0377] 2. Natural Language Processing (NLP)

[0378] The server performs natural language processing on the collected news articles, tokenizing the text, tagging parts of speech, segmenting sentences, and extracting important keywords and phrases, which helps clarify key information within the articles.

[0379] 3. Summary Generation

[0380] The server uses the extracted information to generate a summary of the article using a generative AI model, which is pre-trained on a large amount of data to provide an appropriately summarized text. The generated summary is stored in a database for later retrieval and display.

[0381] 4. Trend Analysis

[0382] The server analyzes the generated summary data and identifies trends by extracting frequently occurring keywords and topics. The results of this trend analysis provide the basis for users to quickly grasp the latest trends.

[0383] 5. User Interaction

[0384] Users can access the system from their smartphones or PCs and view news summaries. They can enter search criteria and filtering options to narrow down news for specific countries or categories. For example, they can select "Global Economic Trends" or "Japanese Political News."

[0385] Based on user input, the terminal sends a request to the server to search for the relevant news summary. The server receives the request, searches for the relevant summary from its database, and sends it to the terminal. The terminal displays a list of the received summaries to the user. When the user clicks on a specific news summary, the terminal requests more information from the server, displaying the original article and additional analysis results. In this way, users can quickly and easily grasp the latest trend information.

[0386] Specific examples

[0387] During the morning commute, a user launches the app on their smartphone and checks the latest news summaries. If the user is interested in economic news, they set the category to "Economy" and retrieve the latest summaries. The server searches the summary database based on the set criteria and sends the relevant summaries to the device. The user scrolls through the displayed summaries and clicks on interesting news to obtain more information.

[0388] Furthermore, when users return home and want to read more about the news on their PC, they can select the important news summary of the day and view more detailed analysis results and the original article, allowing users to quickly gather a wide range of information and gain a deeper understanding.

[0389] Thus, the present invention is a system that allows users to efficiently and effectively stay up to date with the latest news and trends.

[0390] The processing flow will be explained below.

[0391] Step 1:

[0392] The server collects the latest article data from multiple reliable sources. Specifically, it periodically retrieves news articles using RSS feeds and APIs. The retrieved article data is stored in a database along with metadata such as the article title, text, and publication date.

[0393] Step 2:

[0394] The server performs natural language processing (NLP) on the stored article data, tokenizing the article text, tagging it by part of speech, and segmenting it into sentences. It also analyzes the article content to extract important keywords and phrases.

[0395] Step 3:

[0396] The server uses a generative AI model to generate a summary of the article based on the information extracted by the NLP process. The generative AI model has been trained on a large amount of summary data in advance, and it creates a short summary of the main points of the article. This generated summary is stored in a database.

[0397] Step 4:

[0398] The server performs trend analysis on the generated summary data, extracting frequently occurring keywords and topics from the summary data to identify themes and trends that are currently attracting attention. The results of this trend analysis are also stored in a database.

[0399] Step 5:

[0400] Users access the system from their smartphones or PCs to view news summaries, set filtering options (e.g., country, category, time period), and enter search criteria.

[0401] Step 6:

[0402] The terminal sends a request to the server based on the search criteria entered by the user, including any filtering options set by the user.

[0403] Step 7:

[0404] The server searches the database for relevant news summaries based on the received search criteria, finds the appropriate summary data, and sends it to the terminal.

[0405] Step 8:

[0406] The terminal displays the news summaries received from the server to the user, who can scroll through the displayed list of summaries to check them.

[0407] Step 9:

[0408] If a user wants to select a particular news summary and view more detailed information, he or she clicks on the summary.

[0409] Step 10:

[0410] The terminal sends a detailed information request to the server based on the user's selection.

[0411] Step 11:

[0412] The server receives a request for detailed information, searches the database for the relevant original article and additional analysis results, and sends them to the terminal.

[0413] Step 12:

[0414] The device displays the detailed information received from the server to the user, who can then view the full text of the original article and additional analysis results.

[0415] Example 1

[0416] 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."

[0417] In recent years, the diversification of information and the vast amount of news articles available on the Internet have made it difficult for users to efficiently grasp important information and the latest trend information. Furthermore, manually collecting news articles, summarizing them, and analyzing trends requires a great deal of time and effort. Therefore, there is a need for a system that automates the process from article collection to summarization and trend analysis, allowing users to quickly obtain the information they need.

[0418] 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.

[0419] In this invention, the server includes means for collecting article data from multiple reliable information sources, means for saving the collected article data in a database, means for performing natural language processing on the saved article data and extracting important information, means for generating article summaries based on prompt sentences using a generative AI model, means for saving the generated summaries in a database, means for performing trend analysis on the summary data to identify trends, and means for searching for and displaying summaries based on user-specified conditions. This automates the collection, summarization, and trend analysis of news articles, enabling users to efficiently and quickly grasp important information and the latest trends.

[0420] "Reliable sources" refers to multiple sources and services that provide accurate and trustworthy news and articles.

[0421] "Article data" refers to content data including news, blogs, release information, etc.

[0422] A "database" refers to an information system that systematically stores collected data and generated information and enables it to be searched and managed.

[0423] "Natural language processing" refers to the technologies and methods that allow computers to understand, analyze, and process human language.

[0424] A "generative AI model" is an artificial intelligence model that learns from existing data and has the ability to generate new information.

[0425] A "prompt sentence" refers to an input sentence provided to an AI model to perform a specific task.

[0426] "Summary" refers to summary information that briefly summarizes the content of the original article.

[0427] "Trend analysis" refers to the process of analyzing frequently occurring keywords and topics within data to identify current trends and themes that are attracting attention.

[0428] "User-specified criteria" refers to the parameters and options that a user specifically sets for searching or filtering.

[0429] "Request" refers to a request sent by a user to a system to obtain specific data or information.

[0430] "Searching" refers to the process of locating information in a database based on specific criteria.

[0431] "Display" refers to presenting search results and related information on the screen in a format that is easy for the user to see.

[0432] This invention is a system that uses a generative AI model to automatically generate summaries based on article data collected from multiple reliable sources, allowing users to easily grasp the latest trend information. This system includes several main processes, each of which is implemented using specific hardware and software.

[0433] Hardware and Software Configuration

[0434] The server plays a central role in collecting news articles from multiple reliable sources and storing, analyzing, and generating them. The server stores the data using a database (e.g., MySQL or PostgreSQL) and analyzes the article data using a natural language processing (NLP) library (e.g., SpaCy or NLTK). The generative AI model can be, for example, OpenAI's GPT-3.

[0435] The terminal provides an interface for users to access the system. Terminals include smartphones and PCs, and send user input to the server and display information obtained from the server.

[0436] Process example

[0437] News gathering

[0438] The server configures RSS feeds or APIs to aggregate news articles from multiple reliable sources and periodically retrieves the latest article data, for example, using the RSS feed URL or API endpoint.

[0439] Natural Language Processing

[0440] The server performs natural language processing on the collected news articles, tokenizing the text, tagging parts of speech, splitting sentences, and extracting important keywords and phrases. For example, it uses the SpaCy library to tokenize and tag articles.

[0441] Summary Generation

[0442] The server uses the extracted information to generate a summary of the article using a generative AI model (e.g., OpenAI GPT-3), inputting a prompt to the model. For example, the following prompt can be used:

[0443] "Please summarize the following news article:"

[0444] Trend Analysis

[0445] The server analyzes the generated summary data, extracts frequently occurring keywords and topics, and identifies trends, for example by using the TF-IDF algorithm to select important keywords.

[0446] User Interaction

[0447] Users can access the system from their smartphones or PCs, search for summaries based on specified criteria, and view the displayed summaries. For example, if a user searches for "economic news," the server retrieves the relevant summaries from the database and sends them to the device.

[0448] Specific example explanation

[0449] Consider a scenario in which a user launches a smartphone app during their morning commute to check the latest news summaries. If the user is interested in "economic news," they set the category to "economics" and retrieve the latest summaries. The server searches the summary database based on the set criteria and sends the relevant summaries to the device. The user scrolls through the displayed summaries and clicks on interesting news to obtain more information. In this way, users can quickly and easily grasp the latest trending information.

[0450] As a result, the present invention is a system that allows users to efficiently and effectively stay up to date with the latest news and trends.

[0451] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0452] Step 1: Gather news articles

[0453] The server collects news articles from multiple reliable sources. Specifically, it periodically obtains the latest article data using RSS feeds or APIs. For example, the RSS feed URL or API endpoint is set on the server and an HTTP request is sent to obtain the latest article data. The input is the RSS feed or API endpoint, and the output is the collected news article data. This data is temporarily stored and used in the next step.

[0454] Step 2: Saving to the database

[0455] The server stores the collected news article data in a database. Specifically, it stores metadata such as article title, body text, and publication date in a database (e.g., MySQL or PostgreSQL). The input is the collected news article data, and the output is formatted data stored in the database. This stored data can be easily accessed in later processes.

[0456] Step 3: Natural Language Processing (NLP)

[0457] The server performs natural language processing on the stored news article data. Specifically, it tokenizes the article text, tags it with parts of speech, splits sentences, and extracts important keywords and phrases. This is done using a natural language processing library (e.g., SpaCy or NLTK). The input is the news article data stored in the database, and the output is tokens, part-of-speech tags, sentence split information, and a list of keywords. This processing clarifies important information within the article.

[0458] Step 4: Summary generation

[0459] The server uses the extracted information to generate a summary of the article using a generative AI model. Specifically, it generates a prompt, "Please summarize the following news article:," and inputs the prompt and article data into an AI model (e.g., OpenAI GPT-3). The AI ​​model generates a summary and returns the result to the server. The input is the prompt and article data, and the output is the generated summary text. This summary text is stored in a database.

[0460] Step 5: Save the summary to the database

[0461] The server stores the generated summary in a database. Specifically, it associates the generated summary with the article's metadata and stores it in the database. The input is the generated summary text, and the output is the summary data stored in the database. This stored summary is used for later trend analysis and user searches.

[0462] Step 6: Trend analysis

[0463] The server analyzes the generated summary data and identifies trends by extracting frequently occurring keywords and topics. Specifically, it extracts important keywords based on the summary text using TF-IDF (Term Frequency-Inverse Document Frequency) and other statistical methods. The input is the saved summary data, and the output is the extracted trend keywords and topics. This trend information is stored in a separate database.

[0464] Step 7: User interaction

[0465] Users access the system from their smartphones or PCs and browse news summaries. Specifically, users enter search criteria and filtering options to narrow down news from specific countries or categories. The device sends a request to the server based on the user's input. The input is the user's search criteria, and the output is a request to the server.

[0466] Step 8: Search and view the summary

[0467] The server receives a user request, searches for the relevant summary from the database, and sends it to the terminal. The terminal displays a list of the received summaries to the user. When the user clicks on a specific news summary, the terminal requests more information from the server and displays the original article and additional analysis results. The input is a request for more information from the user, and the output is the display of the detailed information. This allows the user to quickly and easily grasp the latest trend information.

[0468] (Application example 1)

[0469] 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."

[0470] In modern society, it is difficult for users to efficiently obtain reliable information from the news and articles provided by many sources. Furthermore, checking multiple sources individually is time-consuming, making it difficult to quickly grasp the latest trend information. Furthermore, there are few systems that can easily obtain the latest news summaries for a target category or topic, and that have the functionality to analyze trends and display frequently occurring keywords.

[0471] 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.

[0472] In this invention, the server includes means for collecting article data from multiple reliable information sources, means for saving the collected article data, means for performing natural language processing on the saved article data and extracting important information, means for generating article summaries based on the information extracted using a generative AI model, means for saving the generated summaries, means for performing trend analysis on the summary data to identify trends, means for searching and displaying summaries based on user-specified conditions, means for generating and distributing the latest news summaries for specified categories or topics, and means for automatically analyzing frequently occurring keywords from the news summaries and displaying trend information. This allows users to easily obtain the latest news summaries for specified categories or topics and quickly grasp trend information.

[0473] A "reliable source" refers to a trusted source that provides news and articles with high legitimacy and accuracy.

[0474] "Article data" refers to data that includes sentences or text information related to news or topics.

[0475] "Natural language processing" refers to the technology that enables computers to understand, interpret, and manipulate human language.

[0476] "Important information" refers to information contained within an article or text that is useful and meaningful to the user.

[0477] A "generative AI model" refers to a model in which artificial intelligence uses machine learning algorithms to generate new information from given data.

[0478] An "article summary" is a text that summarizes the content of the original article and briefly summarizes the main points.

[0479] "Summary data" refers to data containing text information of the generated summary.

[0480] "Trend analysis" refers to the process of analyzing frequently occurring keywords and topics within data to identify current trends and fads.

[0481] "User-specified conditions" refers to the filtering or search criteria set by the user for information extraction.

[0482] A "category" refers to a broad theme or field for classifying information.

[0483] A "topic" refers to a specific theme or subject of information.

[0484] "Latest News Summary" refers to text generated from collected news articles that summarizes the most current situations and events.

[0485] "Frequent keywords" refer to important words or phrases that appear frequently within the data being analyzed.

[0486] "Trend Information" refers to information about current trends and fads obtained as a result of trend analysis.

[0487] This invention is a system that uses a generative AI model to automatically generate summaries based on article data collected from multiple reliable sources, allowing users to easily grasp the latest trend information. The system includes the following main components:

[0488] 1. News gathering

[0489] The server collects news articles from multiple reliable sources, using RSS feeds and APIs to periodically retrieve the latest article data, which is then stored in a database for easy access later.

[0490] 2. Natural Language Processing (NLP)

[0491] The server performs natural language processing on the collected news articles, tokenizing the text, tagging parts of speech, segmenting sentences, and extracting important keywords and phrases, which helps clarify key information within the articles.

[0492] 3. Summary Generation

[0493] The server uses the extracted information to generate a summary of the article using a generative AI model, which is pre-trained on a large amount of data to provide an appropriately summarized text. The generated summary is stored in a database for later retrieval and display.

[0494] 4. Trend Analysis

[0495] The server analyzes the generated summary data and identifies trends by extracting frequently occurring keywords and topics. The trend analysis results serve as the basis for users to quickly grasp the latest trends. Trend information automatically analyzed from the summary data is also displayed.

[0496] 5. User Interaction

[0497] Users can access the system from their smartphones or PCs and view news summaries. They can enter search criteria and filtering options to narrow down news to specific categories or topics. For example, they can select "economic news" or "latest technology trends." The device sends a request to the server based on the user's input to search for relevant news summaries. The server receives the request, searches the database for relevant summaries, and sends them to the device. The device displays a list of received summaries to the user. When the user clicks on a specific news summary, the device requests more information from the server, displaying the original article and additional analysis results. In this way, users can quickly and easily grasp the latest trend information.

[0498] Specific examples

[0499] During the morning commute, a user launches the app on their smartphone and checks the latest news summaries. If the user is interested in economic news, they set the category to "Economy" and retrieve the latest summaries. The server searches the summary database based on the set criteria and sends the relevant summaries to the device. The user scrolls through the displayed summaries and clicks on interesting news to obtain more information. After returning home, if the user wants to read more about the news on their PC, they can select the important news summaries of the day and view more detailed analysis results and original articles. This allows users to quickly gather a wide range of information and gain a deeper understanding.

[0500] Prompt Sentence Examples

[0501] Example prompts to be input to the generative AI model:

[0502] "Summarize an article from a current, reliable news source. The text of the article is below: {article text}"

[0503] Thus, the present invention is a system that allows users to efficiently and effectively stay up to date with the latest news and trends.

[0504] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0505] Step 1:

[0506] The server collects news article data from multiple reliable sources, and periodically retrieves the latest article links using RSS feeds and APIs. As input, it uses the RSS feed URL or API endpoint, and as output, it gets a list of article URLs.

[0507] Step 2:

[0508] The server retrieves the text of each article based on the URL of the collected article. Specifically, it downloads the HTML data of the article using an HTTP request and extracts the article text using an HTML parsing library (e.g., BeautifulSoup). The article URL is used as input, and the article text is obtained as output.

[0509] Step 3:

[0510] The server performs natural language processing on the retrieved article text. Specifically, it tokenizes the text, tags parts of speech, splits sentences, and extracts important keywords and phrases. The article text is used as input, and the extracted important keywords and phrases are obtained as output. This processing uses an NLP library (e.g., NLTK or spaCy).

[0511] Step 4:

[0512] The server generates a summary of the article based on the extracted information using a generative AI model. Specifically, the article text is input into a generative AI model (e.g., BERT or GPT) to generate a summary text. The article text and extracted important keywords are used as input, and the summarized text is obtained as output.

[0513] Step 5:

[0514] The server stores the generated summaries in a database, specifically, it saves the summary data and metadata about the original article. It uses the summary text and article metadata as input and obtains the summary data stored in the database as output.

[0515] Step 6:

[0516] The server performs trend analysis on the stored summary data to identify trends. Specifically, it aggregates frequently occurring keywords and topics and extracts trend information. It uses the contents of the summary database as input and obtains the trend analysis results as output.

[0517] Step 7:

[0518] It searches and displays summaries based on user-specified criteria from the terminal. Specifically, the user enters a search filter (e.g., "economic news" or "technology") and sends a request to the server. The search criteria specified by the user are used as input, and a list of corresponding summaries is obtained as output.

[0519] Step 8:

[0520] The device requests and displays detailed information about the specific news summary selected by the user from the server. Specifically, it retrieves the original article and additional analysis results from the server and displays them to the user. The news summary clicked by the user is used as input, and the detailed information is obtained as output.

[0521] Step 9:

[0522] The server periodically updates the trend analysis results and makes them available for users to access. Specifically, it performs trend analysis again based on newly collected article data and makes the results available for users to view via a web interface or other means. The latest summary data is used as input, and updated trend analysis results are obtained as output.

[0523] As described above, this system is able to efficiently collect, summarize, analyze, and provide reliable, up-to-date information to users through each step.

[0524] 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.

[0525] This system uses a generative AI model to automatically generate summaries based on article data collected from multiple reliable sources, allowing users to easily grasp the latest trend information. Furthermore, it is equipped with an emotion engine that recognizes user emotions, and adds a function to adjust article summaries and recommendations according to the user's emotions. This system includes the following main components:

[0526] 1. News gathering

[0527] The server collects news articles from multiple reliable sources, using RSS feeds and APIs to periodically retrieve the latest article data, which is then stored in a database for easy access later.

[0528] 2. Natural Language Processing (NLP)

[0529] The server performs natural language processing on the stored news articles, tokenizing the text, tagging parts of speech, segmenting sentences, and extracting important keywords and phrases, which helps clarify key information within the article.

[0530] 3. Summary Generation

[0531] The server generates article summaries using a generative AI model based on the information extracted through NLP processing. The generative AI model is pre-trained with a large amount of data and provides appropriately summarized text. The generated summaries are stored in a database for later retrieval and display.

[0532] 4. Trend Analysis

[0533] The server analyzes the generated summary data and identifies trends by extracting frequently occurring keywords and topics. The results of this trend analysis provide the basis for users to quickly grasp the latest trends.

[0534] 5. Emotion Recognition by Emotion Engine

[0535] When a user accesses the system, the terminal activates an emotion engine to recognize the user's emotional state, for example, through analysis of the user's facial expressions or emotion analysis during text input.

[0536] 6. Utilizing Emotional Data

[0537] The server stores and analyzes the emotional data acquired by the emotion engine. Based on this data, the server adjusts the article summary and recommended articles according to the user's emotional state. For example, if the user is feeling stressed, articles about relaxation will be displayed preferentially.

[0538] 7. User Interaction

[0539] Users access the system from their smartphones or PCs and view news summaries. They can enter search criteria and filtering options to narrow down news from specific countries or categories. For example, they can select "Global Economic Trends" or "Japanese Political News."

[0540] Based on user input, the terminal sends a request to the server to search for the relevant news summary. The server receives the request, searches for the relevant summary from its database, and sends it to the terminal. The terminal displays a list of the received summaries to the user. When the user clicks on a specific news summary, the terminal requests more information from the server, displaying the original article and additional analysis results. In this way, users can quickly and easily grasp the latest trend information.

[0541] Specific examples

[0542] 1. Emotion Recognition and News Recommendation Example

[0543] During the morning commute, a user launches the app on their smartphone and checks the latest news summary. The emotion engine recognizes the user's emotions and detects that they are feeling stressed. The system prioritizes displaying articles related to relaxation, which can help reduce stress. The user can then click on an article of interest to continue reading.

[0544] 2. Example of adjusting news summaries according to sentiment

[0545] When the user returns home and wants to read more news on their PC, the emotion engine measures the user's emotions again and detects a relaxed state. While the system displays the usual trending news, it also provides summaries tailored to the user's emotions, ensuring the user receives the information most suited to their mood at the time.

[0546] Thus, the present invention is a system that allows users to efficiently and effectively grasp the latest news and trends while taking into account their emotions.

[0547] The processing flow will be explained below.

[0548] Step 1:

[0549] The server collects the latest article data from multiple reliable sources. Specifically, it periodically retrieves news articles using RSS feeds and APIs. The retrieved article data is stored in a database along with metadata such as the article title, text, and publication date.

[0550] Step 2:

[0551] The server performs natural language processing (NLP) on the stored article data, tokenizing the article text, tagging it by part of speech, and segmenting it into sentences. It also analyzes the article content to extract important keywords and phrases.

[0552] Step 3:

[0553] The server uses a generative AI model to generate a summary of the article based on the information extracted by the NLP process. The generative AI model is pre-trained with a large amount of data and creates a short summary of the main points of the article. The generated summary is then stored in a database.

[0554] Step 4:

[0555] The server performs trend analysis on the generated summary data, extracting frequently occurring keywords and topics from the summary data to identify themes and trends that are currently attracting attention. The results of this trend analysis are also stored in a database.

[0556] Step 5:

[0557] When a user accesses the system, the terminal activates an emotion engine to recognize the user's emotional state, for example, through analysis of the user's facial expressions or emotion analysis during text input.

[0558] Step 6:

[0559] The server stores and analyzes the emotion data acquired by the emotion engine, and adjusts article summaries and recommendations based on the emotion data according to the user's emotional state.

[0560] Step 7:

[0561] Users access the system from their smartphones or PCs to view news summaries, and can enter search criteria and filtering options to narrow down news from specific countries or categories.

[0562] Step 8:

[0563] The terminal sends a request to the server based on the search criteria entered by the user, including any filtering options set by the user.

[0564] Step 9:

[0565] The server searches the database for relevant news summaries based on the received search criteria, finds the appropriate summary data, and sends it to the terminal.

[0566] Step 10:

[0567] The terminal displays the news summaries received from the server to the user, who can scroll through the displayed list of summaries to check them.

[0568] Step 11:

[0569] If a user wants to select a particular news summary and view more detailed information, he or she clicks on the summary.

[0570] Step 12:

[0571] The terminal sends a detailed information request to the server based on the user's selection.

[0572] Step 13:

[0573] The server receives a request for detailed information, searches the database for the relevant original article and additional analysis results, and sends them to the terminal.

[0574] Step 14:

[0575] The device displays the detailed information received from the server to the user, who can then view the full text of the original article and additional analysis results.

[0576] Example 2

[0577] 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."

[0578] Currently, to stay up to date on new news and trending information, users must individually check numerous information sources, which takes time and effort. Furthermore, there is no system that provides appropriate information based on the user's emotional state, making it difficult to provide content that matches the user's mood and interests. This leads to a problem of reduced user satisfaction.

[0579] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting article data from multiple reliable information sources, means for saving the collected article data, means for performing natural language processing on the saved article data and extracting important information, means for generating article summaries based on the information extracted using a generative AI model, means for saving the generated summaries, means for performing trend analysis on the summary data to identify trends, means for searching and displaying summaries based on conditions specified by the user, means for recognizing the user's emotional state, and means for adjusting article summaries and recommended articles based on the recognized emotional state. This allows users to efficiently grasp the latest news and trend information and further obtain appropriate information according to their emotions at that time.

[0580] A "source" is a reliable source of news articles or data.

[0581] "Article data" is a collection of text and metadata containing news or specific information.

[0582] A "gathering means" is a method or device for automatically acquiring article data from multiple sources.

[0583] "Storage means" refers to a method or device for storing collected article data in a database or the like so that it can be used for later processing.

[0584] "Natural language processing" is a process that involves tokenizing text data, tagging parts of speech, dividing sentences, and extracting important keywords and phrases.

[0585] A "generative AI model" is an artificial intelligence model that is trained in advance on large amounts of data and generates summaries and inferences from new data.

[0586] A "summary" is a concise summary of important information extracted from the original article data.

[0587] "Trend analysis" is the process of analyzing summary data to identify frequently occurring keywords and topics.

[0588] "Emotional state" indicates the user's emotions and is recognized through facial expression analysis and emotion analysis during text entry.

[0589] A "means for recognizing" is a method or device for detecting the emotional state of a user.

[0590] The "adjusting means" refers to a method or device that appropriately changes the article summary or recommended articles based on the user's emotional state.

[0591] The "search and display means" refers to a method or device that searches for summary data based on conditions specified by the user and displays the results to the user.

[0592] This invention is a system that uses a generative AI model to automatically generate article summaries based on article data collected from multiple reliable sources, allowing users to easily grasp the latest trend information. It also includes an emotion engine that recognizes the user's emotions, and has the ability to adjust article summaries and recommendations according to the user's emotional state. This system uses the following combination of major hardware and software:

[0593] First, the server collects news articles from multiple reliable sources. Specifically, it uses a web server (e.g., Apache or Nginx) to periodically obtain the latest article data through an RSS feed reader or the API of a news site. For example, articles are periodically obtained from the RSS feed URL "example-rss.com / rss / latest-news" and stored in a database (e.g., MySQL or PostgreSQL).

[0594] The server then performs natural language processing on the stored news articles, using NLP libraries (e.g., SpaCy, NLTK) to tokenize the article text, tag parts of speech, split sentences, and extract important keywords and phrases, thereby clarifying key information within the article.

[0595] Next, the server generates a summary of the article using a generative AI model (e.g., GPT-4) based on the information extracted by the NLP process. The generative AI model is pre-trained with a large amount of data and provides an appropriately summarized text using the prompt, "Please create a summary of this article." The generated summary is stored in a database for later retrieval and display.

[0596] The server also analyzes the generated summary data and identifies trends by extracting frequently occurring keywords and topics. This analysis is performed using data analysis tools (e.g., Pandas, NumPy). For example, if there are many articles containing keywords such as "AI," "economy," or "new virus," the server recognizes that the topic is currently trending.

[0597] When a user accesses the system, the device activates an emotion engine to recognize the user's emotional state. This emotion recognition uses a facial expression analysis library (e.g., OpenCV, DeepFace) and an emotion analysis tool for text input (e.g., VADER, TextBlob). Specifically, the device captures the user's facial expression with a camera and analyzes features such as "smiling" or "frowning."

[0598] The server stores and analyzes the emotional data acquired by the emotion engine. Based on this data, the server adjusts the article summary and recommended articles according to the user's emotional state. For example, if the server recognizes that the user is "feeling stressed," it will prioritize displaying articles related to relaxation.

[0599] Finally, users access the system from their smartphones or PCs to view news summaries. They input search criteria and filtering options to narrow down news for specific countries or categories. The device sends a request to the server based on the user's input, searches for relevant news summaries, and sends them to the device. The device displays a list of received summaries to the user, and when the user clicks on a specific news summary, detailed information is displayed.

[0600] In this way, users can quickly and efficiently grasp the latest trend information, and are provided with information that best suits their emotions at the time, thereby improving the user experience.

[0601] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0602] Step 1:

[0603] The server collects article data from multiple reliable sources. The input is an RSS feed URL or API endpoint. Specifically, it uses an RSS feed reader library (e.g., feedparser) to periodically retrieve the latest article data from the URL "example-rss.com / rss / latest-news". The output is the retrieved raw news article data.

[0604] Step 2:

[0605] The server stores the collected article data in a database. The input is the news article data obtained in step 1. Specifically, using a database management system (e.g., MySQL, PostgreSQL), the data is stored in a table with fields such as article title, body text, author, and publication date and time. The output is a record of the article stored in the database.

[0606] Step 3:

[0607] The server performs natural language processing (NLP) on the stored news articles. The input is the article data stored in the database. To do this, an NLP library (e.g., SpaCy, NLTK) is used to tokenize the text, tag parts of speech, segment sentences, and extract important keywords and phrases. The output is processed NLP feature data.

[0608] Step 4:

[0609] The server generates a summary of the article using a generative AI model (e.g., GPT-4) based on the information extracted by the NLP process. The input is the NLP feature data. The prompt sentence "Please create a summary of this article" is input to the generative AI model, and summary text is generated. The output is the generated summary text.

[0610] Step 5:

[0611] The server saves the generated summary data in a database. The input is the summary text. The specific operation is to save the summary text in a separate table in the database. The output is a summary record saved in the database.

[0612] Step 6:

[0613] The server analyzes the generated summary data and identifies trends by extracting frequently occurring keywords and topics. The input is the summary data. Data analysis tools (e.g., Pandas, NumPy) are used to aggregate frequently occurring keywords and topics and create graphs and lists to identify trends. The output is the identified trend data.

[0614] Step 7:

[0615] When a user accesses the system, the device activates the emotion engine to recognize the user's emotional state. The input is the user's facial expression and text input. Specifically, the device uses a facial expression analysis library (e.g., OpenCV, DeepFace) to analyze the user's facial expression. The output is the recognized emotion data.

[0616] Step 8:

[0617] The server stores and analyzes the emotion data acquired by the emotion engine. The input is the recognized emotion data. Specifically, the server stores the emotion data in a database and generates statistical data based on the user's emotion history. The output is the stored emotion data and the analysis results.

[0618] Step 9:

[0619] The server adjusts the summary content of articles and recommended articles based on the analyzed emotional data according to the user's emotional state. The inputs are emotional data and summary data. Specifically, the algorithm is adjusted to prioritize articles related to relaxation for users who are feeling stressed. The output is the adjusted summary and recommended articles.

[0620] Step 10:

[0621] Users access the system from their smartphones or PCs and view news summaries. Inputs include search criteria and filtering options. For example, the user might select "Japanese economic news." The terminal sends a request to the server based on this input, and the server searches the database for the corresponding news summary and sends it to the terminal. The output is the news summary that is displayed to the user.

[0622] Step 11:

[0623] The terminal sends a request to the server based on the user's input and receives news summaries. The input is the user's filtering conditions. The server receives the request, searches the database for the relevant summary, and sends it to the terminal. The output is the received summary information.

[0624] Step 12:

[0625] The terminal displays a list of received news summaries to the user, and when the user clicks on a particular news summary, it requests detailed information from the server. The input is the received summary information. The output is the displayed news summary and a request for detailed information.

[0626] In this way, the user can quickly and efficiently grasp the latest trend information and can obtain information that best suits his or her feelings at the time.

[0627] (Application example 2)

[0628] 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."

[0629] In today's world, news and trend information from reliable sources is extremely important. However, especially in self-driving vehicles, passengers have limited access to the information they need in real time. Furthermore, information provided does not take into account the emotional state of passengers, preventing passenger satisfaction. There is a need to develop a system that can solve these issues and provide more appropriate and comfortable information.

[0630] 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 article data from multiple reliable information sources, means for saving the collected article data, means for performing natural language processing on the saved article data and extracting important information, means for generating article summaries based on the extracted information using a generative AI model, means for saving the generated summaries, means for performing trend analysis on the summary data to identify trends, means for searching for and displaying summaries based on conditions specified by the user, means for recognizing the user's emotional state in an on-board system of an autonomous vehicle, and means for adjusting article summaries and recommendations based on the recognized emotional state. This allows users to access appropriate news summaries and trend information in real time while in an autonomous vehicle, and further allows them to receive information provided according to their emotional state.

[0631] "Reliable sources" refer to news sites and databases whose content is guaranteed to be accurate and fair and that are widely recognized.

[0632] "Article data" refers to information content such as text and images provided by news and media organizations.

[0633] "Collection means" refers to the methods and techniques used to continuously obtain the required data from a particular source.

[0634] "Storage means" refers to the mechanism by which collected data is persistently stored for later use.

[0635] "Natural language processing" refers to a set of techniques that enable computers to understand and analyze human language.

[0636] "Important information" refers to valuable content that is particularly needed among the collected data.

[0637] A "generative AI model" refers to an artificial intelligence model that learns using large amounts of data and generates appropriate outputs for specific inputs.

[0638] A "summary" is a concise summary of long data or information.

[0639] "Trend analysis" refers to an analytical technique for discovering specific patterns or trends in data.

[0640] A "trend" refers to movement in data that shows a particular direction or pattern.

[0641] "User-specified criteria" refers to the particular criteria or filtering options that a user is interested in or concerned with.

[0642] "In-vehicle system" refers to an electronic device installed in an autonomous vehicle that provides information and entertainment functions.

[0643] "Emotional state" refers to the psychological state recognized from the user's facial expressions and voice.

[0644] "Means for adjusting recommendations" refers to a mechanism that dynamically changes the selection and ranking of content provided based on the user's emotional state.

[0645] This invention is a system that utilizes the infotainment system of an autonomous vehicle to provide users with optimal news summaries and trend information in real time. The system is composed of the following main elements:

[0646] 1. News gathering

[0647] The server collects news articles from multiple reliable sources, using RSS feeds and APIs to periodically retrieve the latest article data, which is then stored in a database for easy access later.

[0648] 2. Natural Language Processing (NLP)

[0649] The server performs natural language processing on the stored news articles, tokenizing the text, tagging parts of speech, segmenting sentences, and extracting important keywords and phrases, which helps clarify key information within the article.

[0650] 3. Summary Generation

[0651] The server generates article summaries using a generative AI model based on the information extracted through NLP processing. The generative AI model is pre-trained with a large amount of data and provides appropriately summarized text. The generated summaries are stored in a database for later retrieval and display.

[0652] 4. Trend Analysis

[0653] The server analyzes the generated summary data and identifies trends by extracting frequently occurring keywords and topics. The results of this trend analysis provide the basis for users to quickly grasp the latest trends.

[0654] 5. Emotion Recognition by Emotion Engine

[0655] The in-car system activates an emotion engine when the user is in the car to recognize the user's emotional state through facial expression analysis using an in-car camera and voice analysis via a microphone.

[0656] 6. Utilizing Emotional Data

[0657] The server stores and analyzes the emotional data acquired by the emotion engine. Based on this data, the server adjusts the article summary and recommended articles according to the user's emotional state. For example, if the user is feeling stressed, articles about relaxation will be displayed preferentially.

[0658] 7. User Interaction

[0659] The user browses news summaries through the in-car infotainment system. The user can use voice commands or the touchscreen to select a specific news category or topic, for example, "Latest Technology Trends" or "Today's Top News." Based on the user's input, the in-car system sends a request to the server to search for relevant news summaries. The server receives the request, searches for relevant summaries in its database, and sends them to the in-car system. The in-car system displays the received summaries to the user. When the user clicks on a particular news summary, it requests more information from the server, displaying the original article and additional analysis results.

[0660] Specific hardware and software

[0661] Hardware: In-car cameras, microphones, in-car infotainment systems

[0662] Software: OpenCV (image analysis), speech recognition library, NLP library, generative AI models (e.g., GPT-3.5), database management system

[0663] Specific examples

[0664] Usage example:

[0665] As passengers enter the vehicle, the in-vehicle system begins facial expression analysis to recognize the user's emotional state.

[0666] The emotion engine determines that the user is relaxed and displays a news summary that matches their current mood.

[0667] When a user issues the voice command "Tell me today's top news stories," the in-car system will display a list of the most important news summaries for the user to view in more detail.

[0668] Example prompt sentence:

[0669] "Please summarize this article: {article_text}"

[0670] In this way, the present invention makes it possible to provide comfortable and personalized news in an autonomous vehicle, thereby improving user satisfaction.

[0671] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0672] Step 1:

[0673] News gathering:

[0674] The server retrieves article data from multiple reliable sources, using RSS feeds and API keys as input, to aggregate the latest news articles. The aggregated article data is then stored in a database for easy access in future processing.

[0675] Step 2:

[0676] Natural Language Processing:

[0677] The server applies natural language processing (NLP) to the stored news articles. Using the stored article data as input, it tokenizes the text, tags parts of speech, splits sentences, and extracts important keywords and phrases. This uncovers important information within the article and passes the extracted data on for further processing.

[0678] Step 3:

[0679] Summary generation:

[0680] The server generates a summary of the article using a generative AI model based on the information extracted by the NLP process. It uses key information from the extracted text as input to generate a prompt (e.g., "Please summarize this article: {article_text}"). As output, the generated summary text is stored in a database.

[0681] Step 4:

[0682] Trend analysis:

[0683] The server analyzes the generated summary data and identifies trends by extracting frequently occurring keywords and topics. Using the summary data as input, it applies data analysis algorithms, which generate trend information that is stored in a database for later retrieval and display.

[0684] Step 5:

[0685] Emotion recognition:

[0686] The in-vehicle system activates the emotion engine when the user is in the car to recognize the user's emotional state. As input, it uses facial expression data captured by an in-vehicle camera and voice data collected by an in-vehicle microphone. As output, analyzed emotion data is generated and sent to the server.

[0687] Step 6:

[0688] Leveraging sentiment data:

[0689] The server stores and analyzes the emotion data obtained from the emotion recognition engine. Using the emotion data as input, it applies an algorithm that adjusts article summary content and recommendations based on the user's emotional state. This results in appropriate news summaries and articles being selected and prepared for display to the user.

[0690] Step 7:

[0691] User interaction:

[0692] Users browse news summaries through their in-car infotainment system. They can use voice commands or the touchscreen as input to select a specific news category or topic, such as "Latest Technology Trends" or "Today's Top News." The server then searches for relevant news summaries based on the user's request and sends them to the in-car system. The in-car system displays the received summaries, and users can click on a specific news summary to view more information about it.

[0693] The above is the overall processing flow from news gathering to emotion recognition and article display.

[0694] 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.

[0695] 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.

[0696] 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.

[0697] [Third embodiment]

[0698] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0699] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0700] 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).

[0701] 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.

[0702] 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.

[0703] 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).

[0704] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0705] 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.

[0706] 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.

[0707] 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.

[0708] 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.

[0709] 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."

[0710] This invention is a system that uses a generative AI model to automatically generate summaries based on article data collected from multiple reliable sources, allowing users to easily grasp the latest trend information. This system includes the following main elements:

[0711] 1. News gathering

[0712] The server collects news articles from multiple reliable sources, using RSS feeds and APIs to periodically retrieve the latest article data, which is then stored in a database for easy access later.

[0713] 2. Natural Language Processing (NLP)

[0714] The server performs natural language processing on the collected news articles, tokenizing the text, tagging parts of speech, segmenting sentences, and extracting important keywords and phrases, which helps clarify key information within the articles.

[0715] 3. Summary Generation

[0716] The server uses the extracted information to generate a summary of the article using a generative AI model, which is pre-trained on a large amount of data to provide an appropriately summarized text. The generated summary is stored in a database for later retrieval and display.

[0717] 4. Trend Analysis

[0718] The server analyzes the generated summary data and identifies trends by extracting frequently occurring keywords and topics. The results of this trend analysis provide the basis for users to quickly grasp the latest trends.

[0719] 5. User Interaction

[0720] Users can access the system from their smartphones or PCs and view news summaries. They can enter search criteria and filtering options to narrow down news for specific countries or categories. For example, they can select "Global Economic Trends" or "Japanese Political News."

[0721] Based on user input, the terminal sends a request to the server to search for the relevant news summary. The server receives the request, searches for the relevant summary from its database, and sends it to the terminal. The terminal displays a list of the received summaries to the user. When the user clicks on a specific news summary, the terminal requests more information from the server, displaying the original article and additional analysis results. In this way, users can quickly and easily grasp the latest trend information.

[0722] Specific examples

[0723] During the morning commute, a user launches the app on their smartphone and checks the latest news summaries. If the user is interested in economic news, they set the category to "Economy" and retrieve the latest summaries. The server searches the summary database based on the set criteria and sends the relevant summaries to the device. The user scrolls through the displayed summaries and clicks on interesting news to obtain more information.

[0724] Furthermore, when users return home and want to read more about the news on their PC, they can select the important news summary of the day and view more detailed analysis results and the original article, allowing users to quickly gather a wide range of information and gain a deeper understanding.

[0725] Thus, the present invention is a system that allows users to efficiently and effectively stay up to date with the latest news and trends.

[0726] The processing flow will be explained below.

[0727] Step 1:

[0728] The server collects the latest article data from multiple reliable sources. Specifically, it periodically retrieves news articles using RSS feeds and APIs. The retrieved article data is stored in a database along with metadata such as the article title, text, and publication date.

[0729] Step 2:

[0730] The server performs natural language processing (NLP) on the stored article data, tokenizing the article text, tagging it by part of speech, and segmenting it into sentences. It also analyzes the article content to extract important keywords and phrases.

[0731] Step 3:

[0732] The server uses a generative AI model to generate a summary of the article based on the information extracted by the NLP process. The generative AI model has been trained on a large amount of summary data in advance, and it creates a short summary of the main points of the article. This generated summary is stored in a database.

[0733] Step 4:

[0734] The server performs trend analysis on the generated summary data, extracting frequently occurring keywords and topics from the summary data to identify themes and trends that are currently attracting attention. The results of this trend analysis are also stored in a database.

[0735] Step 5:

[0736] Users access the system from their smartphones or PCs to view news summaries, set filtering options (e.g., country, category, time period), and enter search criteria.

[0737] Step 6:

[0738] The terminal sends a request to the server based on the search criteria entered by the user, including any filtering options set by the user.

[0739] Step 7:

[0740] The server searches the database for relevant news summaries based on the received search criteria, finds the appropriate summary data, and sends it to the terminal.

[0741] Step 8:

[0742] The terminal displays the news summaries received from the server to the user, who can scroll through the displayed list of summaries to check them.

[0743] Step 9:

[0744] If a user wants to select a particular news summary and view more detailed information, he or she clicks on the summary.

[0745] Step 10:

[0746] The terminal sends a detailed information request to the server based on the user's selection.

[0747] Step 11:

[0748] The server receives a request for detailed information, searches the database for the relevant original article and additional analysis results, and sends them to the terminal.

[0749] Step 12:

[0750] The device displays the detailed information received from the server to the user, who can then view the full text of the original article and additional analysis results.

[0751] Example 1

[0752] 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."

[0753] In recent years, the diversification of information and the vast amount of news articles available on the Internet have made it difficult for users to efficiently grasp important information and the latest trend information. Furthermore, manually collecting news articles, summarizing them, and analyzing trends requires a great deal of time and effort. Therefore, there is a need for a system that automates the process from article collection to summarization and trend analysis, allowing users to quickly obtain the information they need.

[0754] 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.

[0755] In this invention, the server includes means for collecting article data from multiple reliable information sources, means for saving the collected article data in a database, means for performing natural language processing on the saved article data and extracting important information, means for generating article summaries based on prompt sentences using a generative AI model, means for saving the generated summaries in a database, means for performing trend analysis on the summary data to identify trends, and means for searching for and displaying summaries based on user-specified conditions. This automates the collection, summarization, and trend analysis of news articles, enabling users to efficiently and quickly grasp important information and the latest trends.

[0756] "Reliable sources" refers to multiple sources and services that provide accurate and trustworthy news and articles.

[0757] "Article data" refers to content data including news, blogs, release information, etc.

[0758] A "database" refers to an information system that systematically stores collected data and generated information and enables it to be searched and managed.

[0759] "Natural language processing" refers to the technologies and methods that allow computers to understand, analyze, and process human language.

[0760] A "generative AI model" is an artificial intelligence model that learns from existing data and has the ability to generate new information.

[0761] A "prompt sentence" refers to an input sentence provided to an AI model to perform a specific task.

[0762] "Summary" refers to summary information that briefly summarizes the content of the original article.

[0763] "Trend analysis" refers to the process of analyzing frequently occurring keywords and topics within data to identify current trends and themes that are attracting attention.

[0764] "User-specified criteria" refers to the parameters and options that a user specifically sets for searching or filtering.

[0765] "Request" refers to a request sent by a user to a system to obtain specific data or information.

[0766] "Searching" refers to the process of locating information in a database based on specific criteria.

[0767] "Display" refers to presenting search results and related information on the screen in a format that is easy for the user to see.

[0768] This invention is a system that uses a generative AI model to automatically generate summaries based on article data collected from multiple reliable sources, allowing users to easily grasp the latest trend information. This system includes several main processes, each of which is implemented using specific hardware and software.

[0769] Hardware and Software Configuration

[0770] The server plays a central role in collecting news articles from multiple reliable sources and storing, analyzing, and generating them. The server stores the data using a database (e.g., MySQL or PostgreSQL) and analyzes the article data using a natural language processing (NLP) library (e.g., SpaCy or NLTK). The generative AI model can be, for example, OpenAI's GPT-3.

[0771] The terminal provides an interface for users to access the system. Terminals include smartphones and PCs, and send user input to the server and display information obtained from the server.

[0772] Process example

[0773] News gathering

[0774] The server configures RSS feeds or APIs to aggregate news articles from multiple reliable sources and periodically retrieves the latest article data, for example, using the RSS feed URL or API endpoint.

[0775] Natural Language Processing

[0776] The server performs natural language processing on the collected news articles, tokenizing the text, tagging parts of speech, splitting sentences, and extracting important keywords and phrases. For example, it uses the SpaCy library to tokenize and tag articles.

[0777] Summary Generation

[0778] The server uses the extracted information to generate a summary of the article using a generative AI model (e.g., OpenAI GPT-3), inputting a prompt to the model. For example, the following prompt can be used:

[0779] "Please summarize the following news article:"

[0780] Trend Analysis

[0781] The server analyzes the generated summary data, extracts frequently occurring keywords and topics, and identifies trends, for example by using the TF-IDF algorithm to select important keywords.

[0782] User Interaction

[0783] Users can access the system from their smartphones or PCs, search for summaries based on specified criteria, and view the displayed summaries. For example, if a user searches for "economic news," the server retrieves the relevant summaries from the database and sends them to the device.

[0784] Specific example explanation

[0785] Consider a scenario in which a user launches a smartphone app during their morning commute to check the latest news summaries. If the user is interested in "economic news," they set the category to "economics" and retrieve the latest summaries. The server searches the summary database based on the set criteria and sends the relevant summaries to the device. The user scrolls through the displayed summaries and clicks on interesting news to obtain more information. In this way, users can quickly and easily grasp the latest trending information.

[0786] As a result, the present invention is a system that allows users to efficiently and effectively stay up to date with the latest news and trends.

[0787] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0788] Step 1: Gather news articles

[0789] The server collects news articles from multiple reliable sources. Specifically, it periodically obtains the latest article data using RSS feeds or APIs. For example, the RSS feed URL or API endpoint is set on the server and an HTTP request is sent to obtain the latest article data. The input is the RSS feed or API endpoint, and the output is the collected news article data. This data is temporarily stored and used in the next step.

[0790] Step 2: Saving to the database

[0791] The server stores the collected news article data in a database. Specifically, it stores metadata such as article title, body text, and publication date in a database (e.g., MySQL or PostgreSQL). The input is the collected news article data, and the output is formatted data stored in the database. This stored data can be easily accessed in later processes.

[0792] Step 3: Natural Language Processing (NLP)

[0793] The server performs natural language processing on the stored news article data. Specifically, it tokenizes the article text, tags it with parts of speech, splits sentences, and extracts important keywords and phrases. This is done using a natural language processing library (e.g., SpaCy or NLTK). The input is the news article data stored in the database, and the output is tokens, part-of-speech tags, sentence split information, and a list of keywords. This processing clarifies important information within the article.

[0794] Step 4: Summary generation

[0795] The server uses the extracted information to generate a summary of the article using a generative AI model. Specifically, it generates a prompt, "Please summarize the following news article:," and inputs the prompt and article data into an AI model (e.g., OpenAI GPT-3). The AI ​​model generates a summary and returns the result to the server. The input is the prompt and article data, and the output is the generated summary text. This summary text is stored in a database.

[0796] Step 5: Save the summary to the database

[0797] The server stores the generated summary in a database. Specifically, it associates the generated summary with the article's metadata and stores it in the database. The input is the generated summary text, and the output is the summary data stored in the database. This stored summary is used for later trend analysis and user searches.

[0798] Step 6: Trend analysis

[0799] The server analyzes the generated summary data and identifies trends by extracting frequently occurring keywords and topics. Specifically, it extracts important keywords based on the summary text using TF-IDF (Term Frequency-Inverse Document Frequency) and other statistical methods. The input is the saved summary data, and the output is the extracted trend keywords and topics. This trend information is stored in a separate database.

[0800] Step 7: User interaction

[0801] Users access the system from their smartphones or PCs and browse news summaries. Specifically, users enter search criteria and filtering options to narrow down news from specific countries or categories. The device sends a request to the server based on the user's input. The input is the user's search criteria, and the output is a request to the server.

[0802] Step 8: Search and view the summary

[0803] The server receives a user request, searches for the relevant summary from the database, and sends it to the terminal. The terminal displays a list of the received summaries to the user. When the user clicks on a specific news summary, the terminal requests more information from the server and displays the original article and additional analysis results. The input is a request for more information from the user, and the output is the display of the detailed information. This allows the user to quickly and easily grasp the latest trend information.

[0804] (Application example 1)

[0805] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0806] In modern society, it is difficult for users to efficiently obtain reliable information from the news and articles provided by many sources. Furthermore, checking multiple sources individually is time-consuming, making it difficult to quickly grasp the latest trend information. Furthermore, there are few systems that can easily obtain the latest news summaries for a target category or topic, and that have the functionality to analyze trends and display frequently occurring keywords.

[0807] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0808] In this invention, the server includes means for collecting article data from multiple reliable information sources, means for saving the collected article data, means for performing natural language processing on the saved article data and extracting important information, means for generating article summaries based on the information extracted using a generative AI model, means for saving the generated summaries, means for performing trend analysis on the summary data to identify trends, means for searching and displaying summaries based on user-specified conditions, means for generating and distributing the latest news summaries for specified categories or topics, and means for automatically analyzing frequently occurring keywords from the news summaries and displaying trend information. This allows users to easily obtain the latest news summaries for specified categories or topics and quickly grasp trend information.

[0809] A "reliable source" refers to a trusted source that provides news and articles with high legitimacy and accuracy.

[0810] "Article data" refers to data that includes sentences or text information related to news or topics.

[0811] "Natural language processing" refers to the technology that enables computers to understand, interpret, and manipulate human language.

[0812] "Important information" refers to information contained within an article or text that is useful and meaningful to the user.

[0813] A "generative AI model" refers to a model in which artificial intelligence uses machine learning algorithms to generate new information from given data.

[0814] An "article summary" is a text that summarizes the content of the original article and briefly summarizes the main points.

[0815] "Summary data" refers to data containing text information of the generated summary.

[0816] "Trend analysis" refers to the process of analyzing frequently occurring keywords and topics within data to identify current trends and fads.

[0817] "User-specified conditions" refers to the filtering or search criteria set by the user for information extraction.

[0818] A "category" refers to a broad theme or field for classifying information.

[0819] A "topic" refers to a specific theme or subject of information.

[0820] "Latest News Summary" refers to text generated from collected news articles that summarizes the most current situations and events.

[0821] "Frequent keywords" refer to important words or phrases that appear frequently within the data being analyzed.

[0822] "Trend Information" refers to information about current trends and fads obtained as a result of trend analysis.

[0823] This invention is a system that uses a generative AI model to automatically generate summaries based on article data collected from multiple reliable sources, allowing users to easily grasp the latest trend information. The system includes the following main components:

[0824] 1. News gathering

[0825] The server collects news articles from multiple reliable sources, using RSS feeds and APIs to periodically retrieve the latest article data, which is then stored in a database for easy access later.

[0826] 2. Natural Language Processing (NLP)

[0827] The server performs natural language processing on the collected news articles, tokenizing the text, tagging parts of speech, segmenting sentences, and extracting important keywords and phrases, which helps clarify key information within the articles.

[0828] 3. Summary Generation

[0829] The server uses the extracted information to generate a summary of the article using a generative AI model, which is pre-trained on a large amount of data to provide an appropriately summarized text. The generated summary is stored in a database for later retrieval and display.

[0830] 4. Trend Analysis

[0831] The server analyzes the generated summary data and identifies trends by extracting frequently occurring keywords and topics. The trend analysis results serve as the basis for users to quickly grasp the latest trends. Trend information automatically analyzed from the summary data is also displayed.

[0832] 5. User Interaction

[0833] Users can access the system from their smartphones or PCs and view news summaries. They can enter search criteria and filtering options to narrow down news to specific categories or topics. For example, they can select "economic news" or "latest technology trends." The device sends a request to the server based on the user's input to search for relevant news summaries. The server receives the request, searches the database for relevant summaries, and sends them to the device. The device displays a list of received summaries to the user. When the user clicks on a specific news summary, the device requests more information from the server, displaying the original article and additional analysis results. In this way, users can quickly and easily grasp the latest trend information.

[0834] Specific examples

[0835] During the morning commute, a user launches the app on their smartphone and checks the latest news summaries. If the user is interested in economic news, they set the category to "Economy" and retrieve the latest summaries. The server searches the summary database based on the set criteria and sends the relevant summaries to the device. The user scrolls through the displayed summaries and clicks on interesting news to obtain more information. After returning home, if the user wants to read more about the news on their PC, they can select the important news summaries of the day and view more detailed analysis results and original articles. This allows users to quickly gather a wide range of information and gain a deeper understanding.

[0836] Prompt Sentence Examples

[0837] Example prompts to be input to the generative AI model:

[0838] "Summarize an article from a current, reliable news source. The text of the article is below: {article text}"

[0839] Thus, the present invention is a system that allows users to efficiently and effectively stay up to date with the latest news and trends.

[0840] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0841] Step 1:

[0842] The server collects news article data from multiple reliable sources, and periodically retrieves the latest article links using RSS feeds and APIs. As input, it uses the RSS feed URL or API endpoint, and as output, it gets a list of article URLs.

[0843] Step 2:

[0844] The server retrieves the text of each article based on the URL of the collected article. Specifically, it downloads the HTML data of the article using an HTTP request and extracts the article text using an HTML parsing library (e.g., BeautifulSoup). The article URL is used as input, and the article text is obtained as output.

[0845] Step 3:

[0846] The server performs natural language processing on the retrieved article text. Specifically, it tokenizes the text, tags parts of speech, splits sentences, and extracts important keywords and phrases. The article text is used as input, and the extracted important keywords and phrases are obtained as output. This processing uses an NLP library (e.g., NLTK or spaCy).

[0847] Step 4:

[0848] The server generates a summary of the article based on the extracted information using a generative AI model. Specifically, the article text is input into a generative AI model (e.g., BERT or GPT) to generate a summary text. The article text and extracted important keywords are used as input, and the summarized text is obtained as output.

[0849] Step 5:

[0850] The server stores the generated summaries in a database, specifically, it saves the summary data and metadata about the original article. It uses the summary text and article metadata as input and obtains the summary data stored in the database as output.

[0851] Step 6:

[0852] The server performs trend analysis on the stored summary data to identify trends. Specifically, it aggregates frequently occurring keywords and topics and extracts trend information. It uses the contents of the summary database as input and obtains the trend analysis results as output.

[0853] Step 7:

[0854] It searches and displays summaries based on user-specified criteria from the terminal. Specifically, the user enters a search filter (e.g., "economic news" or "technology") and sends a request to the server. The search criteria specified by the user are used as input, and a list of corresponding summaries is obtained as output.

[0855] Step 8:

[0856] The device requests and displays detailed information about the specific news summary selected by the user from the server. Specifically, it retrieves the original article and additional analysis results from the server and displays them to the user. The news summary clicked by the user is used as input, and the detailed information is obtained as output.

[0857] Step 9:

[0858] The server periodically updates the trend analysis results and makes them available for users to access. Specifically, it performs trend analysis again based on newly collected article data and makes the results available for users to view via a web interface or other means. The latest summary data is used as input, and updated trend analysis results are obtained as output.

[0859] As described above, this system is able to efficiently collect, summarize, analyze, and provide reliable, up-to-date information to users through each step.

[0860] 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.

[0861] This system uses a generative AI model to automatically generate summaries based on article data collected from multiple reliable sources, allowing users to easily grasp the latest trend information. Furthermore, it is equipped with an emotion engine that recognizes user emotions, and adds a function to adjust article summaries and recommendations according to the user's emotions. This system includes the following main components:

[0862] 1. News gathering

[0863] The server collects news articles from multiple reliable sources, using RSS feeds and APIs to periodically retrieve the latest article data, which is then stored in a database for easy access later.

[0864] 2. Natural Language Processing (NLP)

[0865] The server performs natural language processing on the stored news articles, tokenizing the text, tagging parts of speech, segmenting sentences, and extracting important keywords and phrases, which helps clarify key information within the article.

[0866] 3. Summary Generation

[0867] The server generates article summaries using a generative AI model based on the information extracted through NLP processing. The generative AI model is pre-trained with a large amount of data and provides appropriately summarized text. The generated summaries are stored in a database for later retrieval and display.

[0868] 4. Trend Analysis

[0869] The server analyzes the generated summary data and identifies trends by extracting frequently occurring keywords and topics. The results of this trend analysis provide the basis for users to quickly grasp the latest trends.

[0870] 5. Emotion Recognition by Emotion Engine

[0871] When a user accesses the system, the terminal activates an emotion engine to recognize the user's emotional state, for example, through analysis of the user's facial expressions or emotion analysis during text input.

[0872] 6. Utilizing Emotional Data

[0873] The server stores and analyzes the emotional data acquired by the emotion engine. Based on this data, the server adjusts the article summary and recommended articles according to the user's emotional state. For example, if the user is feeling stressed, articles about relaxation will be displayed preferentially.

[0874] 7. User Interaction

[0875] Users access the system from their smartphones or PCs and view news summaries. They can enter search criteria and filtering options to narrow down news from specific countries or categories. For example, they can select "Global Economic Trends" or "Japanese Political News."

[0876] Based on user input, the terminal sends a request to the server to search for the relevant news summary. The server receives the request, searches for the relevant summary from its database, and sends it to the terminal. The terminal displays a list of the received summaries to the user. When the user clicks on a specific news summary, the terminal requests more information from the server, displaying the original article and additional analysis results. In this way, users can quickly and easily grasp the latest trend information.

[0877] Specific examples

[0878] 1. Emotion Recognition and News Recommendation Example

[0879] During the morning commute, a user launches the app on their smartphone and checks the latest news summary. The emotion engine recognizes the user's emotions and detects that they are feeling stressed. The system prioritizes displaying articles related to relaxation, which can help reduce stress. The user can then click on an article of interest to continue reading.

[0880] 2. Example of adjusting news summaries according to sentiment

[0881] When the user returns home and wants to read more news on their PC, the emotion engine measures the user's emotions again and detects a relaxed state. While the system displays the usual trending news, it also provides summaries tailored to the user's emotions, ensuring the user receives the information most suited to their mood at the time.

[0882] Thus, the present invention is a system that allows users to efficiently and effectively grasp the latest news and trends while taking into account their emotions.

[0883] The processing flow will be explained below.

[0884] Step 1:

[0885] The server collects the latest article data from multiple reliable sources. Specifically, it periodically retrieves news articles using RSS feeds and APIs. The retrieved article data is stored in a database along with metadata such as the article title, text, and publication date.

[0886] Step 2:

[0887] The server performs natural language processing (NLP) on the stored article data, tokenizing the article text, tagging it by part of speech, and segmenting it into sentences. It also analyzes the article content to extract important keywords and phrases.

[0888] Step 3:

[0889] The server uses a generative AI model to generate a summary of the article based on the information extracted by the NLP process. The generative AI model is pre-trained with a large amount of data and creates a short summary of the main points of the article. The generated summary is then stored in a database.

[0890] Step 4:

[0891] The server performs trend analysis on the generated summary data, extracting frequently occurring keywords and topics from the summary data to identify themes and trends that are currently attracting attention. The results of this trend analysis are also stored in a database.

[0892] Step 5:

[0893] When a user accesses the system, the terminal activates an emotion engine to recognize the user's emotional state, for example, through analysis of the user's facial expressions or emotion analysis during text input.

[0894] Step 6:

[0895] The server stores and analyzes the emotion data acquired by the emotion engine, and adjusts article summaries and recommendations based on the emotion data according to the user's emotional state.

[0896] Step 7:

[0897] Users access the system from their smartphones or PCs to view news summaries, and can enter search criteria and filtering options to narrow down news from specific countries or categories.

[0898] Step 8:

[0899] The terminal sends a request to the server based on the search criteria entered by the user, including any filtering options set by the user.

[0900] Step 9:

[0901] The server searches the database for relevant news summaries based on the received search criteria, finds the appropriate summary data, and sends it to the terminal.

[0902] Step 10:

[0903] The terminal displays the news summaries received from the server to the user, who can scroll through the displayed list of summaries to check them.

[0904] Step 11:

[0905] If a user wants to select a particular news summary and view more detailed information, he or she clicks on the summary.

[0906] Step 12:

[0907] The terminal sends a detailed information request to the server based on the user's selection.

[0908] Step 13:

[0909] The server receives a request for detailed information, searches the database for the relevant original article and additional analysis results, and sends them to the terminal.

[0910] Step 14:

[0911] The device displays the detailed information received from the server to the user, who can then view the full text of the original article and additional analysis results.

[0912] Example 2

[0913] 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."

[0914] Currently, to stay up to date on new news and trending information, users must individually check numerous information sources, which takes time and effort. Furthermore, there is no system that provides appropriate information based on the user's emotional state, making it difficult to provide content that matches the user's mood and interests. This leads to a problem of reduced user satisfaction.

[0915] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting article data from multiple reliable information sources, means for saving the collected article data, means for performing natural language processing on the saved article data and extracting important information, means for generating article summaries based on the information extracted using a generative AI model, means for saving the generated summaries, means for performing trend analysis on the summary data to identify trends, means for searching and displaying summaries based on conditions specified by the user, means for recognizing the user's emotional state, and means for adjusting article summaries and recommended articles based on the recognized emotional state. This allows users to efficiently grasp the latest news and trend information and further obtain appropriate information according to their emotions at that time.

[0916] A "source" is a reliable source of news articles or data.

[0917] "Article data" is a collection of text and metadata containing news or specific information.

[0918] A "gathering means" is a method or device for automatically acquiring article data from multiple sources.

[0919] "Storage means" refers to a method or device for storing collected article data in a database or the like so that it can be used for later processing.

[0920] "Natural language processing" is a process that involves tokenizing text data, tagging parts of speech, dividing sentences, and extracting important keywords and phrases.

[0921] A "generative AI model" is an artificial intelligence model that is trained in advance on large amounts of data and generates summaries and inferences from new data.

[0922] A "summary" is a concise summary of important information extracted from the original article data.

[0923] "Trend analysis" is the process of analyzing summary data to identify frequently occurring keywords and topics.

[0924] "Emotional state" indicates the user's emotions and is recognized through facial expression analysis and emotion analysis during text entry.

[0925] A "means for recognizing" is a method or device for detecting the emotional state of a user.

[0926] The "adjusting means" refers to a method or device that appropriately changes the article summary or recommended articles based on the user's emotional state.

[0927] The "search and display means" refers to a method or device that searches for summary data based on conditions specified by the user and displays the results to the user.

[0928] This invention is a system that uses a generative AI model to automatically generate article summaries based on article data collected from multiple reliable sources, allowing users to easily grasp the latest trend information. It also includes an emotion engine that recognizes the user's emotions, and has the ability to adjust article summaries and recommendations according to the user's emotional state. This system uses the following combination of major hardware and software:

[0929] First, the server collects news articles from multiple reliable sources. Specifically, it uses a web server (e.g., Apache or Nginx) to periodically obtain the latest article data through an RSS feed reader or the API of a news site. For example, articles are periodically obtained from the RSS feed URL "example-rss.com / rss / latest-news" and stored in a database (e.g., MySQL or PostgreSQL).

[0930] The server then performs natural language processing on the stored news articles, using NLP libraries (e.g., SpaCy, NLTK) to tokenize the article text, tag parts of speech, split sentences, and extract important keywords and phrases, thereby clarifying key information within the article.

[0931] Next, the server generates a summary of the article using a generative AI model (e.g., GPT-4) based on the information extracted by the NLP process. The generative AI model is pre-trained with a large amount of data and provides an appropriately summarized text using the prompt, "Please create a summary of this article." The generated summary is stored in a database for later retrieval and display.

[0932] The server also analyzes the generated summary data and identifies trends by extracting frequently occurring keywords and topics. This analysis is performed using data analysis tools (e.g., Pandas, NumPy). For example, if there are many articles containing keywords such as "AI," "economy," or "new virus," the server recognizes that the topic is currently trending.

[0933] When a user accesses the system, the device activates an emotion engine to recognize the user's emotional state. This emotion recognition uses a facial expression analysis library (e.g., OpenCV, DeepFace) and an emotion analysis tool for text input (e.g., VADER, TextBlob). Specifically, the device captures the user's facial expression with a camera and analyzes features such as "smiling" or "frowning."

[0934] The server stores and analyzes the emotional data acquired by the emotion engine. Based on this data, the server adjusts the article summary and recommended articles according to the user's emotional state. For example, if the server recognizes that the user is "feeling stressed," it will prioritize displaying articles related to relaxation.

[0935] Finally, users access the system from their smartphones or PCs to view news summaries. They input search criteria and filtering options to narrow down news for specific countries or categories. The device sends a request to the server based on the user's input, searches for relevant news summaries, and sends them to the device. The device displays a list of received summaries to the user, and when the user clicks on a specific news summary, detailed information is displayed.

[0936] In this way, users can quickly and efficiently grasp the latest trend information, and are provided with information that best suits their emotions at the time, thereby improving the user experience.

[0937] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0938] Step 1:

[0939] The server collects article data from multiple reliable sources. The input is an RSS feed URL or API endpoint. Specifically, it uses an RSS feed reader library (e.g., feedparser) to periodically retrieve the latest article data from the URL "example-rss.com / rss / latest-news". The output is the retrieved raw news article data.

[0940] Step 2:

[0941] The server stores the collected article data in a database. The input is the news article data obtained in step 1. Specifically, using a database management system (e.g., MySQL, PostgreSQL), the data is stored in a table with fields such as article title, body text, author, and publication date and time. The output is a record of the article stored in the database.

[0942] Step 3:

[0943] The server performs natural language processing (NLP) on the stored news articles. The input is the article data stored in the database. To do this, an NLP library (e.g., SpaCy, NLTK) is used to tokenize the text, tag parts of speech, segment sentences, and extract important keywords and phrases. The output is processed NLP feature data.

[0944] Step 4:

[0945] The server generates a summary of the article using a generative AI model (e.g., GPT-4) based on the information extracted by the NLP process. The input is the NLP feature data. The prompt sentence "Please create a summary of this article" is input to the generative AI model, and summary text is generated. The output is the generated summary text.

[0946] Step 5:

[0947] The server saves the generated summary data in a database. The input is the summary text. The specific operation is to save the summary text in a separate table in the database. The output is a summary record saved in the database.

[0948] Step 6:

[0949] The server analyzes the generated summary data and identifies trends by extracting frequently occurring keywords and topics. The input is the summary data. Data analysis tools (e.g., Pandas, NumPy) are used to aggregate frequently occurring keywords and topics and create graphs and lists to identify trends. The output is the identified trend data.

[0950] Step 7:

[0951] When a user accesses the system, the device activates the emotion engine to recognize the user's emotional state. The input is the user's facial expression and text input. Specifically, the device uses a facial expression analysis library (e.g., OpenCV, DeepFace) to analyze the user's facial expression. The output is the recognized emotion data.

[0952] Step 8:

[0953] The server stores and analyzes the emotion data acquired by the emotion engine. The input is the recognized emotion data. Specifically, the server stores the emotion data in a database and generates statistical data based on the user's emotion history. The output is the stored emotion data and the analysis results.

[0954] Step 9:

[0955] The server adjusts the summary content of articles and recommended articles based on the analyzed emotional data according to the user's emotional state. The inputs are emotional data and summary data. Specifically, the algorithm is adjusted to prioritize articles related to relaxation for users who are feeling stressed. The output is the adjusted summary and recommended articles.

[0956] Step 10:

[0957] Users access the system from their smartphones or PCs and view news summaries. Inputs include search criteria and filtering options. For example, the user might select "Japanese economic news." The terminal sends a request to the server based on this input, and the server searches the database for the corresponding news summary and sends it to the terminal. The output is the news summary that is displayed to the user.

[0958] Step 11:

[0959] The terminal sends a request to the server based on the user's input and receives news summaries. The input is the user's filtering conditions. The server receives the request, searches the database for the relevant summary, and sends it to the terminal. The output is the received summary information.

[0960] Step 12:

[0961] The terminal displays a list of received news summaries to the user, and when the user clicks on a particular news summary, it requests detailed information from the server. The input is the received summary information. The output is the displayed news summary and a request for detailed information.

[0962] In this way, the user can quickly and efficiently grasp the latest trend information and can obtain information that best suits his or her feelings at the time.

[0963] (Application example 2)

[0964] 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."

[0965] In today's world, news and trend information from reliable sources is extremely important. However, especially in self-driving vehicles, passengers have limited access to the information they need in real time. Furthermore, information provided does not take into account the emotional state of passengers, preventing passenger satisfaction. There is a need to develop a system that can solve these issues and provide more appropriate and comfortable information.

[0966] 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 article data from multiple reliable information sources, means for saving the collected article data, means for performing natural language processing on the saved article data and extracting important information, means for generating article summaries based on the extracted information using a generative AI model, means for saving the generated summaries, means for performing trend analysis on the summary data to identify trends, means for searching for and displaying summaries based on conditions specified by the user, means for recognizing the user's emotional state in an on-board system of an autonomous vehicle, and means for adjusting article summaries and recommendations based on the recognized emotional state. This allows users to access appropriate news summaries and trend information in real time while in an autonomous vehicle, and further allows them to receive information provided according to their emotional state.

[0967] "Reliable sources" refer to news sites and databases whose content is guaranteed to be accurate and fair and that are widely recognized.

[0968] "Article data" refers to information content such as text and images provided by news and media organizations.

[0969] "Collection means" refers to the methods and techniques used to continuously obtain the required data from a particular source.

[0970] "Storage means" refers to the mechanism by which collected data is persistently stored for later use.

[0971] "Natural language processing" refers to a set of techniques that enable computers to understand and analyze human language.

[0972] "Important information" refers to valuable content that is particularly needed among the collected data.

[0973] A "generative AI model" refers to an artificial intelligence model that learns using large amounts of data and generates appropriate outputs for specific inputs.

[0974] A "summary" is a concise summary of long data or information.

[0975] "Trend analysis" refers to an analytical technique for discovering specific patterns or trends in data.

[0976] A "trend" refers to movement in data that shows a particular direction or pattern.

[0977] "User-specified criteria" refers to the particular criteria or filtering options that a user is interested in or concerned with.

[0978] "In-vehicle system" refers to an electronic device installed in an autonomous vehicle that provides information and entertainment functions.

[0979] "Emotional state" refers to the psychological state recognized from the user's facial expressions and voice.

[0980] "Means for adjusting recommendations" refers to a mechanism that dynamically changes the selection and ranking of content provided based on the user's emotional state.

[0981] This invention is a system that utilizes the infotainment system of an autonomous vehicle to provide users with optimal news summaries and trend information in real time. The system is composed of the following main elements:

[0982] 1. News gathering

[0983] The server collects news articles from multiple reliable sources, using RSS feeds and APIs to periodically retrieve the latest article data, which is then stored in a database for easy access later.

[0984] 2. Natural Language Processing (NLP)

[0985] The server performs natural language processing on the stored news articles, tokenizing the text, tagging parts of speech, segmenting sentences, and extracting important keywords and phrases, which helps clarify key information within the article.

[0986] 3. Summary Generation

[0987] The server generates article summaries using a generative AI model based on the information extracted through NLP processing. The generative AI model is pre-trained with a large amount of data and provides appropriately summarized text. The generated summaries are stored in a database for later retrieval and display.

[0988] 4. Trend Analysis

[0989] The server analyzes the generated summary data and identifies trends by extracting frequently occurring keywords and topics. The results of this trend analysis provide the basis for users to quickly grasp the latest trends.

[0990] 5. Emotion Recognition by Emotion Engine

[0991] The in-car system activates an emotion engine when the user is in the car to recognize the user's emotional state through facial expression analysis using an in-car camera and voice analysis via a microphone.

[0992] 6. Utilizing Emotional Data

[0993] The server stores and analyzes the emotional data acquired by the emotion engine. Based on this data, the server adjusts the article summary and recommended articles according to the user's emotional state. For example, if the user is feeling stressed, articles about relaxation will be displayed preferentially.

[0994] 7. User Interaction

[0995] The user browses news summaries through the in-car infotainment system. The user can use voice commands or the touchscreen to select a specific news category or topic, for example, "Latest Technology Trends" or "Today's Top News." Based on the user's input, the in-car system sends a request to the server to search for relevant news summaries. The server receives the request, searches for relevant summaries in its database, and sends them to the in-car system. The in-car system displays the received summaries to the user. When the user clicks on a particular news summary, it requests more information from the server, displaying the original article and additional analysis results.

[0996] Specific hardware and software

[0997] Hardware: In-car cameras, microphones, in-car infotainment systems

[0998] Software: OpenCV (image analysis), speech recognition library, NLP library, generative AI models (e.g., GPT-3.5), database management system

[0999] Specific examples

[1000] Usage example:

[1001] As passengers enter the vehicle, the in-vehicle system begins facial expression analysis to recognize the user's emotional state.

[1002] The emotion engine determines that the user is relaxed and displays a news summary that matches their current mood.

[1003] When a user issues the voice command "Tell me today's top news stories," the in-car system will display a list of the most important news summaries for the user to view in more detail.

[1004] Example prompt sentence:

[1005] "Please summarize this article: {article_text}"

[1006] In this way, the present invention makes it possible to provide comfortable and personalized news in an autonomous vehicle, thereby improving user satisfaction.

[1007] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1008] Step 1:

[1009] News gathering:

[1010] The server retrieves article data from multiple reliable sources, using RSS feeds and API keys as input, to aggregate the latest news articles. The aggregated article data is then stored in a database for easy access in future processing.

[1011] Step 2:

[1012] Natural Language Processing:

[1013] The server applies natural language processing (NLP) to the stored news articles. Using the stored article data as input, it tokenizes the text, tags parts of speech, splits sentences, and extracts important keywords and phrases. This uncovers important information within the article and passes the extracted data on for further processing.

[1014] Step 3:

[1015] Summary generation:

[1016] The server generates a summary of the article using a generative AI model based on the information extracted by the NLP process. It uses key information from the extracted text as input to generate a prompt (e.g., "Please summarize this article: {article_text}"). As output, the generated summary text is stored in a database.

[1017] Step 4:

[1018] Trend analysis:

[1019] The server analyzes the generated summary data and identifies trends by extracting frequently occurring keywords and topics. Using the summary data as input, it applies data analysis algorithms, which generate trend information that is stored in a database for later retrieval and display.

[1020] Step 5:

[1021] Emotion recognition:

[1022] The in-vehicle system activates the emotion engine when the user is in the car to recognize the user's emotional state. As input, it uses facial expression data captured by an in-vehicle camera and voice data collected by an in-vehicle microphone. As output, analyzed emotion data is generated and sent to the server.

[1023] Step 6:

[1024] Leveraging sentiment data:

[1025] The server stores and analyzes the emotion data obtained from the emotion recognition engine. Using the emotion data as input, it applies an algorithm that adjusts article summary content and recommendations based on the user's emotional state. This results in appropriate news summaries and articles being selected and prepared for display to the user.

[1026] Step 7:

[1027] User interaction:

[1028] Users browse news summaries through their in-car infotainment system. They can use voice commands or the touchscreen as input to select a specific news category or topic, such as "Latest Technology Trends" or "Today's Top News." The server then searches for relevant news summaries based on the user's request and sends them to the in-car system. The in-car system displays the received summaries, and users can click on a specific news summary to view more information about it.

[1029] The above is the overall processing flow from news gathering to emotion recognition and article display.

[1030] 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.

[1031] 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.

[1032] 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.

[1033] [Fourth embodiment]

[1034] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1035] 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.

[1036] 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).

[1037] 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.

[1038] 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.

[1039] 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).

[1040] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1041] 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.

[1042] 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.

[1043] 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.

[1044] 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.

[1045] 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.

[1046] 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."

[1047] This invention is a system that uses a generative AI model to automatically generate summaries based on article data collected from multiple reliable sources, allowing users to easily grasp the latest trend information. This system includes the following main elements:

[1048] 1. News gathering

[1049] The server collects news articles from multiple reliable sources, using RSS feeds and APIs to periodically retrieve the latest article data, which is then stored in a database for easy access later.

[1050] 2. Natural Language Processing (NLP)

[1051] The server performs natural language processing on the collected news articles, tokenizing the text, tagging parts of speech, segmenting sentences, and extracting important keywords and phrases, which helps clarify key information within the articles.

[1052] 3. Summary Generation

[1053] The server uses the extracted information to generate a summary of the article using a generative AI model, which is pre-trained on a large amount of data to provide an appropriately summarized text. The generated summary is stored in a database for later retrieval and display.

[1054] 4. Trend Analysis

[1055] The server analyzes the generated summary data and identifies trends by extracting frequently occurring keywords and topics. The results of this trend analysis provide the basis for users to quickly grasp the latest trends.

[1056] 5. User Interaction

[1057] Users can access the system from their smartphones or PCs and view news summaries. They can enter search criteria and filtering options to narrow down news for specific countries or categories. For example, they can select "Global Economic Trends" or "Japanese Political News."

[1058] Based on user input, the terminal sends a request to the server to search for the relevant news summary. The server receives the request, searches for the relevant summary from its database, and sends it to the terminal. The terminal displays a list of the received summaries to the user. When the user clicks on a specific news summary, the terminal requests more information from the server, displaying the original article and additional analysis results. In this way, users can quickly and easily grasp the latest trend information.

[1059] Specific examples

[1060] During the morning commute, a user launches the app on their smartphone and checks the latest news summaries. If the user is interested in economic news, they set the category to "Economy" and retrieve the latest summaries. The server searches the summary database based on the set criteria and sends the relevant summaries to the device. The user scrolls through the displayed summaries and clicks on interesting news to obtain more information.

[1061] Furthermore, when users return home and want to read more about the news on their PC, they can select the important news summary of the day and view more detailed analysis results and the original article, allowing users to quickly gather a wide range of information and gain a deeper understanding.

[1062] Thus, the present invention is a system that allows users to efficiently and effectively stay up to date with the latest news and trends.

[1063] The processing flow will be explained below.

[1064] Step 1:

[1065] The server collects the latest article data from multiple reliable sources. Specifically, it periodically retrieves news articles using RSS feeds and APIs. The retrieved article data is stored in a database along with metadata such as the article title, text, and publication date.

[1066] Step 2:

[1067] The server performs natural language processing (NLP) on the stored article data, tokenizing the article text, tagging it by part of speech, and segmenting it into sentences. It also analyzes the article content to extract important keywords and phrases.

[1068] Step 3:

[1069] The server uses a generative AI model to generate a summary of the article based on the information extracted by the NLP process. The generative AI model has been trained on a large amount of summary data in advance, and it creates a short summary of the main points of the article. This generated summary is stored in a database.

[1070] Step 4:

[1071] The server performs trend analysis on the generated summary data, extracting frequently occurring keywords and topics from the summary data to identify themes and trends that are currently attracting attention. The results of this trend analysis are also stored in a database.

[1072] Step 5:

[1073] Users access the system from their smartphones or PCs to view news summaries, set filtering options (e.g., country, category, time period), and enter search criteria.

[1074] Step 6:

[1075] The terminal sends a request to the server based on the search criteria entered by the user, including any filtering options set by the user.

[1076] Step 7:

[1077] The server searches the database for relevant news summaries based on the received search criteria, finds the appropriate summary data, and sends it to the terminal.

[1078] Step 8:

[1079] The terminal displays the news summaries received from the server to the user, who can scroll through the displayed list of summaries to check them.

[1080] Step 9:

[1081] If a user wants to select a particular news summary and view more detailed information, he or she clicks on the summary.

[1082] Step 10:

[1083] The terminal sends a detailed information request to the server based on the user's selection.

[1084] Step 11:

[1085] The server receives a request for detailed information, searches the database for the relevant original article and additional analysis results, and sends them to the terminal.

[1086] Step 12:

[1087] The device displays the detailed information received from the server to the user, who can then view the full text of the original article and additional analysis results.

[1088] Example 1

[1089] 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."

[1090] In recent years, the diversification of information and the vast amount of news articles available on the Internet have made it difficult for users to efficiently grasp important information and the latest trend information. Furthermore, manually collecting news articles, summarizing them, and analyzing trends requires a great deal of time and effort. Therefore, there is a need for a system that automates the process from article collection to summarization and trend analysis, allowing users to quickly obtain the information they need.

[1091] 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.

[1092] In this invention, the server includes means for collecting article data from multiple reliable information sources, means for saving the collected article data in a database, means for performing natural language processing on the saved article data and extracting important information, means for generating article summaries based on prompt sentences using a generative AI model, means for saving the generated summaries in a database, means for performing trend analysis on the summary data to identify trends, and means for searching for and displaying summaries based on user-specified conditions. This automates the collection, summarization, and trend analysis of news articles, enabling users to efficiently and quickly grasp important information and the latest trends.

[1093] "Reliable sources" refers to multiple sources and services that provide accurate and trustworthy news and articles.

[1094] "Article data" refers to content data including news, blogs, release information, etc.

[1095] A "database" refers to an information system that systematically stores collected data and generated information and enables it to be searched and managed.

[1096] "Natural language processing" refers to the technologies and methods that allow computers to understand, analyze, and process human language.

[1097] A "generative AI model" is an artificial intelligence model that learns from existing data and has the ability to generate new information.

[1098] A "prompt sentence" refers to an input sentence provided to an AI model to perform a specific task.

[1099] "Summary" refers to summary information that briefly summarizes the content of the original article.

[1100] "Trend analysis" refers to the process of analyzing frequently occurring keywords and topics within data to identify current trends and themes that are attracting attention.

[1101] "User-specified criteria" refers to the parameters and options that a user specifically sets for searching or filtering.

[1102] "Request" refers to a request sent by a user to a system to obtain specific data or information.

[1103] "Searching" refers to the process of locating information in a database based on specific criteria.

[1104] "Display" refers to presenting search results and related information on the screen in a format that is easy for the user to see.

[1105] This invention is a system that uses a generative AI model to automatically generate summaries based on article data collected from multiple reliable sources, allowing users to easily grasp the latest trend information. This system includes several main processes, each of which is implemented using specific hardware and software.

[1106] Hardware and Software Configuration

[1107] The server plays a central role in collecting news articles from multiple reliable sources and storing, analyzing, and generating them. The server stores the data using a database (e.g., MySQL or PostgreSQL) and analyzes the article data using a natural language processing (NLP) library (e.g., SpaCy or NLTK). The generative AI model can be, for example, OpenAI's GPT-3.

[1108] The terminal provides an interface for users to access the system. Terminals include smartphones and PCs, and send user input to the server and display information obtained from the server.

[1109] Process example

[1110] News gathering

[1111] The server configures RSS feeds or APIs to aggregate news articles from multiple reliable sources and periodically retrieves the latest article data, for example, using the RSS feed URL or API endpoint.

[1112] Natural Language Processing

[1113] The server performs natural language processing on the collected news articles, tokenizing the text, tagging parts of speech, splitting sentences, and extracting important keywords and phrases. For example, it uses the SpaCy library to tokenize and tag articles.

[1114] Summary Generation

[1115] The server uses the extracted information to generate a summary of the article using a generative AI model (e.g., OpenAI GPT-3), inputting a prompt to the model. For example, the following prompt can be used:

[1116] "Please summarize the following news article:"

[1117] Trend Analysis

[1118] The server analyzes the generated summary data, extracts frequently occurring keywords and topics, and identifies trends, for example by using the TF-IDF algorithm to select important keywords.

[1119] User Interaction

[1120] Users can access the system from their smartphones or PCs, search for summaries based on specified criteria, and view the displayed summaries. For example, if a user searches for "economic news," the server retrieves the relevant summaries from the database and sends them to the device.

[1121] Specific example explanation

[1122] Consider a scenario in which a user launches a smartphone app during their morning commute to check the latest news summaries. If the user is interested in "economic news," they set the category to "economics" and retrieve the latest summaries. The server searches the summary database based on the set criteria and sends the relevant summaries to the device. The user scrolls through the displayed summaries and clicks on interesting news to obtain more information. In this way, users can quickly and easily grasp the latest trending information.

[1123] As a result, the present invention is a system that allows users to efficiently and effectively stay up to date with the latest news and trends.

[1124] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1125] Step 1: Gather news articles

[1126] The server collects news articles from multiple reliable sources. Specifically, it periodically obtains the latest article data using RSS feeds or APIs. For example, the RSS feed URL or API endpoint is set on the server and an HTTP request is sent to obtain the latest article data. The input is the RSS feed or API endpoint, and the output is the collected news article data. This data is temporarily stored and used in the next step.

[1127] Step 2: Saving to the database

[1128] The server stores the collected news article data in a database. Specifically, it stores metadata such as article title, body text, and publication date in a database (e.g., MySQL or PostgreSQL). The input is the collected news article data, and the output is formatted data stored in the database. This stored data can be easily accessed in later processes.

[1129] Step 3: Natural Language Processing (NLP)

[1130] The server performs natural language processing on the stored news article data. Specifically, it tokenizes the article text, tags it with parts of speech, splits sentences, and extracts important keywords and phrases. This is done using a natural language processing library (e.g., SpaCy or NLTK). The input is the news article data stored in the database, and the output is tokens, part-of-speech tags, sentence split information, and a list of keywords. This processing clarifies important information within the article.

[1131] Step 4: Summary generation

[1132] The server uses the extracted information to generate a summary of the article using a generative AI model. Specifically, it generates a prompt, "Please summarize the following news article:," and inputs the prompt and article data into an AI model (e.g., OpenAI GPT-3). The AI ​​model generates a summary and returns the result to the server. The input is the prompt and article data, and the output is the generated summary text. This summary text is stored in a database.

[1133] Step 5: Save the summary to the database

[1134] The server stores the generated summary in a database. Specifically, it associates the generated summary with the article's metadata and stores it in the database. The input is the generated summary text, and the output is the summary data stored in the database. This stored summary is used for later trend analysis and user searches.

[1135] Step 6: Trend analysis

[1136] The server analyzes the generated summary data and identifies trends by extracting frequently occurring keywords and topics. Specifically, it extracts important keywords based on the summary text using TF-IDF (Term Frequency-Inverse Document Frequency) and other statistical methods. The input is the saved summary data, and the output is the extracted trend keywords and topics. This trend information is stored in a separate database.

[1137] Step 7: User interaction

[1138] Users access the system from their smartphones or PCs and browse news summaries. Specifically, users enter search criteria and filtering options to narrow down news from specific countries or categories. The device sends a request to the server based on the user's input. The input is the user's search criteria, and the output is a request to the server.

[1139] Step 8: Search and view the summary

[1140] The server receives a user request, searches for the relevant summary from the database, and sends it to the terminal. The terminal displays a list of the received summaries to the user. When the user clicks on a specific news summary, the terminal requests more information from the server and displays the original article and additional analysis results. The input is a request for more information from the user, and the output is the display of the detailed information. This allows the user to quickly and easily grasp the latest trend information.

[1141] (Application example 1)

[1142] 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."

[1143] In modern society, it is difficult for users to efficiently obtain reliable information from the news and articles provided by many sources. Furthermore, checking multiple sources individually is time-consuming, making it difficult to quickly grasp the latest trend information. Furthermore, there are few systems that can easily obtain the latest news summaries for a target category or topic, and that have the functionality to analyze trends and display frequently occurring keywords.

[1144] 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.

[1145] In this invention, the server includes means for collecting article data from multiple reliable information sources, means for saving the collected article data, means for performing natural language processing on the saved article data and extracting important information, means for generating article summaries based on the information extracted using a generative AI model, means for saving the generated summaries, means for performing trend analysis on the summary data to identify trends, means for searching and displaying summaries based on user-specified conditions, means for generating and distributing the latest news summaries for specified categories or topics, and means for automatically analyzing frequently occurring keywords from the news summaries and displaying trend information. This allows users to easily obtain the latest news summaries for specified categories or topics and quickly grasp trend information.

[1146] A "reliable source" refers to a trusted source that provides news and articles with high legitimacy and accuracy.

[1147] "Article data" refers to data that includes sentences or text information related to news or topics.

[1148] "Natural language processing" refers to the technology that enables computers to understand, interpret, and manipulate human language.

[1149] "Important information" refers to information contained within an article or text that is useful and meaningful to the user.

[1150] A "generative AI model" refers to a model in which artificial intelligence uses machine learning algorithms to generate new information from given data.

[1151] An "article summary" is a text that summarizes the content of the original article and briefly summarizes the main points.

[1152] "Summary data" refers to data containing text information of the generated summary.

[1153] "Trend analysis" refers to the process of analyzing frequently occurring keywords and topics within data to identify current trends and fads.

[1154] "User-specified conditions" refers to the filtering or search criteria set by the user for information extraction.

[1155] A "category" refers to a broad theme or field for classifying information.

[1156] A "topic" refers to a specific theme or subject of information.

[1157] "Latest News Summary" refers to text generated from collected news articles that summarizes the most current situations and events.

[1158] "Frequent keywords" refer to important words or phrases that appear frequently within the data being analyzed.

[1159] "Trend Information" refers to information about current trends and fads obtained as a result of trend analysis.

[1160] This invention is a system that uses a generative AI model to automatically generate summaries based on article data collected from multiple reliable sources, allowing users to easily grasp the latest trend information. The system includes the following main components:

[1161] 1. News gathering

[1162] The server collects news articles from multiple reliable sources, using RSS feeds and APIs to periodically retrieve the latest article data, which is then stored in a database for easy access later.

[1163] 2. Natural Language Processing (NLP)

[1164] The server performs natural language processing on the collected news articles, tokenizing the text, tagging parts of speech, segmenting sentences, and extracting important keywords and phrases, which helps clarify key information within the articles.

[1165] 3. Summary Generation

[1166] The server uses the extracted information to generate a summary of the article using a generative AI model, which is pre-trained on a large amount of data to provide an appropriately summarized text. The generated summary is stored in a database for later retrieval and display.

[1167] 4. Trend Analysis

[1168] The server analyzes the generated summary data and identifies trends by extracting frequently occurring keywords and topics. The trend analysis results serve as the basis for users to quickly grasp the latest trends. Trend information automatically analyzed from the summary data is also displayed.

[1169] 5. User Interaction

[1170] Users can access the system from their smartphones or PCs and view news summaries. They can enter search criteria and filtering options to narrow down news to specific categories or topics. For example, they can select "economic news" or "latest technology trends." The device sends a request to the server based on the user's input to search for relevant news summaries. The server receives the request, searches the database for relevant summaries, and sends them to the device. The device displays a list of received summaries to the user. When the user clicks on a specific news summary, the device requests more information from the server, displaying the original article and additional analysis results. In this way, users can quickly and easily grasp the latest trend information.

[1171] Specific examples

[1172] During the morning commute, a user launches the app on their smartphone and checks the latest news summaries. If the user is interested in economic news, they set the category to "Economy" and retrieve the latest summaries. The server searches the summary database based on the set criteria and sends the relevant summaries to the device. The user scrolls through the displayed summaries and clicks on interesting news to obtain more information. After returning home, if the user wants to read more about the news on their PC, they can select the important news summaries of the day and view more detailed analysis results and original articles. This allows users to quickly gather a wide range of information and gain a deeper understanding.

[1173] Prompt Sentence Examples

[1174] Example prompts to be input to the generative AI model:

[1175] "Summarize an article from a current, reliable news source. The text of the article is below: {article text}"

[1176] Thus, the present invention is a system that allows users to efficiently and effectively stay up to date with the latest news and trends.

[1177] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1178] Step 1:

[1179] The server collects news article data from multiple reliable sources, and periodically retrieves the latest article links using RSS feeds and APIs. As input, it uses the RSS feed URL or API endpoint, and as output, it gets a list of article URLs.

[1180] Step 2:

[1181] The server retrieves the text of each article based on the URL of the collected article. Specifically, it downloads the HTML data of the article using an HTTP request and extracts the article text using an HTML parsing library (e.g., BeautifulSoup). The article URL is used as input, and the article text is obtained as output.

[1182] Step 3:

[1183] The server performs natural language processing on the retrieved article text. Specifically, it tokenizes the text, tags parts of speech, splits sentences, and extracts important keywords and phrases. The article text is used as input, and the extracted important keywords and phrases are obtained as output. This processing uses an NLP library (e.g., NLTK or spaCy).

[1184] Step 4:

[1185] The server generates a summary of the article based on the extracted information using a generative AI model. Specifically, the article text is input into a generative AI model (e.g., BERT or GPT) to generate a summary text. The article text and extracted important keywords are used as input, and the summarized text is obtained as output.

[1186] Step 5:

[1187] The server stores the generated summaries in a database, specifically, it saves the summary data and metadata about the original article. It uses the summary text and article metadata as input and obtains the summary data stored in the database as output.

[1188] Step 6:

[1189] The server performs trend analysis on the stored summary data to identify trends. Specifically, it aggregates frequently occurring keywords and topics and extracts trend information. It uses the contents of the summary database as input and obtains the trend analysis results as output.

[1190] Step 7:

[1191] It searches and displays summaries based on user-specified criteria from the terminal. Specifically, the user enters a search filter (e.g., "economic news" or "technology") and sends a request to the server. The search criteria specified by the user are used as input, and a list of corresponding summaries is obtained as output.

[1192] Step 8:

[1193] The device requests and displays detailed information about the specific news summary selected by the user from the server. Specifically, it retrieves the original article and additional analysis results from the server and displays them to the user. The news summary clicked by the user is used as input, and the detailed information is obtained as output.

[1194] Step 9:

[1195] The server periodically updates the trend analysis results and makes them available for users to access. Specifically, it performs trend analysis again based on newly collected article data and makes the results available for users to view via a web interface or other means. The latest summary data is used as input, and updated trend analysis results are obtained as output.

[1196] As described above, this system is able to efficiently collect, summarize, analyze, and provide reliable, up-to-date information to users through each step.

[1197] 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.

[1198] This system uses a generative AI model to automatically generate summaries based on article data collected from multiple reliable sources, allowing users to easily grasp the latest trend information. Furthermore, it is equipped with an emotion engine that recognizes user emotions, and adds a function to adjust article summaries and recommendations according to the user's emotions. This system includes the following main components:

[1199] 1. News gathering

[1200] The server collects news articles from multiple reliable sources, using RSS feeds and APIs to periodically retrieve the latest article data, which is then stored in a database for easy access later.

[1201] 2. Natural Language Processing (NLP)

[1202] The server performs natural language processing on the stored news articles, tokenizing the text, tagging parts of speech, segmenting sentences, and extracting important keywords and phrases, which helps clarify key information within the article.

[1203] 3. Summary Generation

[1204] The server generates article summaries using a generative AI model based on the information extracted through NLP processing. The generative AI model is pre-trained with a large amount of data and provides appropriately summarized text. The generated summaries are stored in a database for later retrieval and display.

[1205] 4. Trend Analysis

[1206] The server analyzes the generated summary data and identifies trends by extracting frequently occurring keywords and topics. The results of this trend analysis provide the basis for users to quickly grasp the latest trends.

[1207] 5. Emotion Recognition by Emotion Engine

[1208] When a user accesses the system, the terminal activates an emotion engine to recognize the user's emotional state, for example, through analysis of the user's facial expressions or emotion analysis during text input.

[1209] 6. Utilizing Emotional Data

[1210] The server stores and analyzes the emotional data acquired by the emotion engine. Based on this data, the server adjusts the article summary and recommended articles according to the user's emotional state. For example, if the user is feeling stressed, articles about relaxation will be displayed preferentially.

[1211] 7. User Interaction

[1212] Users access the system from their smartphones or PCs and view news summaries. They can enter search criteria and filtering options to narrow down news from specific countries or categories. For example, they can select "Global Economic Trends" or "Japanese Political News."

[1213] Based on user input, the terminal sends a request to the server to search for the relevant news summary. The server receives the request, searches for the relevant summary from its database, and sends it to the terminal. The terminal displays a list of the received summaries to the user. When the user clicks on a specific news summary, the terminal requests more information from the server, displaying the original article and additional analysis results. In this way, users can quickly and easily grasp the latest trend information.

[1214] Specific examples

[1215] 1. Emotion Recognition and News Recommendation Example

[1216] During the morning commute, a user launches the app on their smartphone and checks the latest news summary. The emotion engine recognizes the user's emotions and detects that they are feeling stressed. The system prioritizes displaying articles related to relaxation, which can help reduce stress. The user can then click on an article of interest to continue reading.

[1217] 2. Example of adjusting news summaries according to sentiment

[1218] When the user returns home and wants to read more news on their PC, the emotion engine measures the user's emotions again and detects a relaxed state. While the system displays the usual trending news, it also provides summaries tailored to the user's emotions, ensuring the user receives the information most suited to their mood at the time.

[1219] Thus, the present invention is a system that allows users to efficiently and effectively grasp the latest news and trends while taking into account their emotions.

[1220] The processing flow will be explained below.

[1221] Step 1:

[1222] The server collects the latest article data from multiple reliable sources. Specifically, it periodically retrieves news articles using RSS feeds and APIs. The retrieved article data is stored in a database along with metadata such as the article title, text, and publication date.

[1223] Step 2:

[1224] The server performs natural language processing (NLP) on the stored article data, tokenizing the article text, tagging it by part of speech, and segmenting it into sentences. It also analyzes the article content to extract important keywords and phrases.

[1225] Step 3:

[1226] The server uses a generative AI model to generate a summary of the article based on the information extracted by the NLP process. The generative AI model is pre-trained with a large amount of data and creates a short summary of the main points of the article. The generated summary is then stored in a database.

[1227] Step 4:

[1228] The server performs trend analysis on the generated summary data, extracting frequently occurring keywords and topics from the summary data to identify themes and trends that are currently attracting attention. The results of this trend analysis are also stored in a database.

[1229] Step 5:

[1230] When a user accesses the system, the terminal activates an emotion engine to recognize the user's emotional state, for example, through analysis of the user's facial expressions or emotion analysis during text input.

[1231] Step 6:

[1232] The server stores and analyzes the emotion data acquired by the emotion engine, and adjusts article summaries and recommendations based on the emotion data according to the user's emotional state.

[1233] Step 7:

[1234] Users access the system from their smartphones or PCs to view news summaries, and can enter search criteria and filtering options to narrow down news from specific countries or categories.

[1235] Step 8:

[1236] The terminal sends a request to the server based on the search criteria entered by the user, including any filtering options set by the user.

[1237] Step 9:

[1238] The server searches the database for relevant news summaries based on the received search criteria, finds the appropriate summary data, and sends it to the terminal.

[1239] Step 10:

[1240] The terminal displays the news summaries received from the server to the user, who can scroll through the displayed list of summaries to check them.

[1241] Step 11:

[1242] If a user wants to select a particular news summary and view more detailed information, he or she clicks on the summary.

[1243] Step 12:

[1244] The terminal sends a detailed information request to the server based on the user's selection.

[1245] Step 13:

[1246] The server receives a request for detailed information, searches the database for the relevant original article and additional analysis results, and sends them to the terminal.

[1247] Step 14:

[1248] The device displays the detailed information received from the server to the user, who can then view the full text of the original article and additional analysis results.

[1249] Example 2

[1250] 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."

[1251] Currently, to stay up to date on new news and trending information, users must individually check numerous information sources, which takes time and effort. Furthermore, there is no system that provides appropriate information based on the user's emotional state, making it difficult to provide content that matches the user's mood and interests. This leads to a problem of reduced user satisfaction.

[1252] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting article data from multiple reliable information sources, means for saving the collected article data, means for performing natural language processing on the saved article data and extracting important information, means for generating article summaries based on the information extracted using a generative AI model, means for saving the generated summaries, means for performing trend analysis on the summary data to identify trends, means for searching and displaying summaries based on conditions specified by the user, means for recognizing the user's emotional state, and means for adjusting article summaries and recommended articles based on the recognized emotional state. This allows users to efficiently grasp the latest news and trend information and further obtain appropriate information according to their emotions at that time.

[1253] A "source" is a reliable source of news articles or data.

[1254] "Article data" is a collection of text and metadata containing news or specific information.

[1255] A "gathering means" is a method or device for automatically acquiring article data from multiple sources.

[1256] "Storage means" refers to a method or device for storing collected article data in a database or the like so that it can be used for later processing.

[1257] "Natural language processing" is a process that involves tokenizing text data, tagging parts of speech, dividing sentences, and extracting important keywords and phrases.

[1258] A "generative AI model" is an artificial intelligence model that is trained in advance on large amounts of data and generates summaries and inferences from new data.

[1259] A "summary" is a concise summary of important information extracted from the original article data.

[1260] "Trend analysis" is the process of analyzing summary data to identify frequently occurring keywords and topics.

[1261] "Emotional state" indicates the user's emotions and is recognized through facial expression analysis and emotion analysis during text entry.

[1262] A "means for recognizing" is a method or device for detecting the emotional state of a user.

[1263] The "adjusting means" refers to a method or device that appropriately changes the article summary or recommended articles based on the user's emotional state.

[1264] The "search and display means" refers to a method or device that searches for summary data based on conditions specified by the user and displays the results to the user.

[1265] This invention is a system that uses a generative AI model to automatically generate article summaries based on article data collected from multiple reliable sources, allowing users to easily grasp the latest trend information. It also includes an emotion engine that recognizes the user's emotions, and has the ability to adjust article summaries and recommendations according to the user's emotional state. This system uses the following combination of major hardware and software:

[1266] First, the server collects news articles from multiple reliable sources. Specifically, it uses a web server (e.g., Apache or Nginx) to periodically obtain the latest article data through an RSS feed reader or the API of a news site. For example, articles are periodically obtained from the RSS feed URL "example-rss.com / rss / latest-news" and stored in a database (e.g., MySQL or PostgreSQL).

[1267] The server then performs natural language processing on the stored news articles, using NLP libraries (e.g., SpaCy, NLTK) to tokenize the article text, tag parts of speech, split sentences, and extract important keywords and phrases, thereby clarifying key information within the article.

[1268] Next, the server generates a summary of the article using a generative AI model (e.g., GPT-4) based on the information extracted by the NLP process. The generative AI model is pre-trained with a large amount of data and provides an appropriately summarized text using the prompt, "Please create a summary of this article." The generated summary is stored in a database for later retrieval and display.

[1269] The server also analyzes the generated summary data and identifies trends by extracting frequently occurring keywords and topics. This analysis is performed using data analysis tools (e.g., Pandas, NumPy). For example, if there are many articles containing keywords such as "AI," "economy," or "new virus," the server recognizes that the topic is currently trending.

[1270] When a user accesses the system, the device activates an emotion engine to recognize the user's emotional state. This emotion recognition uses a facial expression analysis library (e.g., OpenCV, DeepFace) and an emotion analysis tool for text input (e.g., VADER, TextBlob). Specifically, the device captures the user's facial expression with a camera and analyzes features such as "smiling" or "frowning."

[1271] The server stores and analyzes the emotional data acquired by the emotion engine. Based on this data, the server adjusts the article summary and recommended articles according to the user's emotional state. For example, if the server recognizes that the user is "feeling stressed," it will prioritize displaying articles related to relaxation.

[1272] Finally, users access the system from their smartphones or PCs to view news summaries. They input search criteria and filtering options to narrow down news for specific countries or categories. The device sends a request to the server based on the user's input, searches for relevant news summaries, and sends them to the device. The device displays a list of received summaries to the user, and when the user clicks on a specific news summary, detailed information is displayed.

[1273] In this way, users can quickly and efficiently grasp the latest trend information, and are provided with information that best suits their emotions at the time, thereby improving the user experience.

[1274] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1275] Step 1:

[1276] The server collects article data from multiple reliable sources. The input is an RSS feed URL or API endpoint. Specifically, it uses an RSS feed reader library (e.g., feedparser) to periodically retrieve the latest article data from the URL "example-rss.com / rss / latest-news". The output is the retrieved raw news article data.

[1277] Step 2:

[1278] The server stores the collected article data in a database. The input is the news article data obtained in step 1. Specifically, using a database management system (e.g., MySQL, PostgreSQL), the data is stored in a table with fields such as article title, body text, author, and publication date and time. The output is a record of the article stored in the database.

[1279] Step 3:

[1280] The server performs natural language processing (NLP) on the stored news articles. The input is the article data stored in the database. To do this, an NLP library (e.g., SpaCy, NLTK) is used to tokenize the text, tag parts of speech, segment sentences, and extract important keywords and phrases. The output is processed NLP feature data.

[1281] Step 4:

[1282] The server generates a summary of the article using a generative AI model (e.g., GPT-4) based on the information extracted by the NLP process. The input is the NLP feature data. The prompt sentence "Please create a summary of this article" is input to the generative AI model, and summary text is generated. The output is the generated summary text.

[1283] Step 5:

[1284] The server saves the generated summary data in a database. The input is the summary text. The specific operation is to save the summary text in a separate table in the database. The output is a summary record saved in the database.

[1285] Step 6:

[1286] The server analyzes the generated summary data and identifies trends by extracting frequently occurring keywords and topics. The input is the summary data. Data analysis tools (e.g., Pandas, NumPy) are used to aggregate frequently occurring keywords and topics and create graphs and lists to identify trends. The output is the identified trend data.

[1287] Step 7:

[1288] When a user accesses the system, the device activates the emotion engine to recognize the user's emotional state. The input is the user's facial expression and text input. Specifically, the device uses a facial expression analysis library (e.g., OpenCV, DeepFace) to analyze the user's facial expression. The output is the recognized emotion data.

[1289] Step 8:

[1290] The server stores and analyzes the emotion data acquired by the emotion engine. The input is the recognized emotion data. Specifically, the server stores the emotion data in a database and generates statistical data based on the user's emotion history. The output is the stored emotion data and the analysis results.

[1291] Step 9:

[1292] The server adjusts the summary content of articles and recommended articles based on the analyzed emotional data according to the user's emotional state. The inputs are emotional data and summary data. Specifically, the algorithm is adjusted to prioritize articles related to relaxation for users who are feeling stressed. The output is the adjusted summary and recommended articles.

[1293] Step 10:

[1294] Users access the system from their smartphones or PCs and view news summaries. Inputs include search criteria and filtering options. For example, the user might select "Japanese economic news." The terminal sends a request to the server based on this input, and the server searches the database for the corresponding news summary and sends it to the terminal. The output is the news summary that is displayed to the user.

[1295] Step 11:

[1296] The terminal sends a request to the server based on the user's input and receives news summaries. The input is the user's filtering conditions. The server receives the request, searches the database for the relevant summary, and sends it to the terminal. The output is the received summary information.

[1297] Step 12:

[1298] The terminal displays a list of received news summaries to the user, and when the user clicks on a particular news summary, it requests detailed information from the server. The input is the received summary information. The output is the displayed news summary and a request for detailed information.

[1299] In this way, the user can quickly and efficiently grasp the latest trend information and can obtain information that best suits his or her feelings at the time.

[1300] (Application example 2)

[1301] 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."

[1302] In today's world, news and trend information from reliable sources is extremely important. However, especially in self-driving vehicles, passengers have limited access to the information they need in real time. Furthermore, information provided does not take into account the emotional state of passengers, preventing passenger satisfaction. There is a need to develop a system that can solve these issues and provide more appropriate and comfortable information.

[1303] 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 article data from multiple reliable information sources, means for saving the collected article data, means for performing natural language processing on the saved article data and extracting important information, means for generating article summaries based on the extracted information using a generative AI model, means for saving the generated summaries, means for performing trend analysis on the summary data to identify trends, means for searching for and displaying summaries based on conditions specified by the user, means for recognizing the user's emotional state in an on-board system of an autonomous vehicle, and means for adjusting article summaries and recommendations based on the recognized emotional state. This allows users to access appropriate news summaries and trend information in real time while in an autonomous vehicle, and further allows them to receive information provided according to their emotional state.

[1304] "Reliable sources" refer to news sites and databases whose content is guaranteed to be accurate and fair and that are widely recognized.

[1305] "Article data" refers to information content such as text and images provided by news and media organizations.

[1306] "Collection means" refers to the methods and techniques used to continuously obtain the required data from a particular source.

[1307] "Storage means" refers to the mechanism by which collected data is persistently stored for later use.

[1308] "Natural language processing" refers to a set of techniques that enable computers to understand and analyze human language.

[1309] "Important information" refers to valuable content that is particularly needed among the collected data.

[1310] A "generative AI model" refers to an artificial intelligence model that learns using large amounts of data and generates appropriate outputs for specific inputs.

[1311] A "summary" is a concise summary of long data or information.

[1312] "Trend analysis" refers to an analytical technique for discovering specific patterns or trends in data.

[1313] A "trend" refers to movement in data that shows a particular direction or pattern.

[1314] "User-specified criteria" refers to the particular criteria or filtering options that a user is interested in or concerned with.

[1315] "In-vehicle system" refers to an electronic device installed in an autonomous vehicle that provides information and entertainment functions.

[1316] "Emotional state" refers to the psychological state recognized from the user's facial expressions and voice.

[1317] "Means for adjusting recommendations" refers to a mechanism that dynamically changes the selection and ranking of content provided based on the user's emotional state.

[1318] This invention is a system that utilizes the infotainment system of an autonomous vehicle to provide users with optimal news summaries and trend information in real time. The system is composed of the following main elements:

[1319] 1. News gathering

[1320] The server collects news articles from multiple reliable sources, using RSS feeds and APIs to periodically retrieve the latest article data, which is then stored in a database for easy access later.

[1321] 2. Natural Language Processing (NLP)

[1322] The server performs natural language processing on the stored news articles, tokenizing the text, tagging parts of speech, segmenting sentences, and extracting important keywords and phrases, which helps clarify key information within the article.

[1323] 3. Summary Generation

[1324] The server generates article summaries using a generative AI model based on the information extracted through NLP processing. The generative AI model is pre-trained with a large amount of data and provides appropriately summarized text. The generated summaries are stored in a database for later retrieval and display.

[1325] 4. Trend Analysis

[1326] The server analyzes the generated summary data and identifies trends by extracting frequently occurring keywords and topics. The results of this trend analysis provide the basis for users to quickly grasp the latest trends.

[1327] 5. Emotion Recognition by Emotion Engine

[1328] The in-car system activates an emotion engine when the user is in the car to recognize the user's emotional state through facial expression analysis using an in-car camera and voice analysis via a microphone.

[1329] 6. Utilizing Emotional Data

[1330] The server stores and analyzes the emotional data acquired by the emotion engine. Based on this data, the server adjusts the article summary and recommended articles according to the user's emotional state. For example, if the user is feeling stressed, articles about relaxation will be displayed preferentially.

[1331] 7. User Interaction

[1332] The user browses news summaries through the in-car infotainment system. The user can use voice commands or the touchscreen to select a specific news category or topic, for example, "Latest Technology Trends" or "Today's Top News." Based on the user's input, the in-car system sends a request to the server to search for relevant news summaries. The server receives the request, searches for relevant summaries in its database, and sends them to the in-car system. The in-car system displays the received summaries to the user. When the user clicks on a particular news summary, it requests more information from the server, displaying the original article and additional analysis results.

[1333] Specific hardware and software

[1334] Hardware: In-car cameras, microphones, in-car infotainment systems

[1335] Software: OpenCV (image analysis), speech recognition library, NLP library, generative AI models (e.g., GPT-3.5), database management system

[1336] Specific examples

[1337] Usage example:

[1338] As passengers enter the vehicle, the in-vehicle system begins facial expression analysis to recognize the user's emotional state.

[1339] The emotion engine determines that the user is relaxed and displays a news summary that matches their current mood.

[1340] When a user issues the voice command "Tell me today's top news stories," the in-car system will display a list of the most important news summaries for the user to view in more detail.

[1341] Example prompt sentence:

[1342] "Please summarize this article: {article_text}"

[1343] In this way, the present invention makes it possible to provide comfortable and personalized news in an autonomous vehicle, thereby improving user satisfaction.

[1344] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1345] Step 1:

[1346] News gathering:

[1347] The server retrieves article data from multiple reliable sources, using RSS feeds and API keys as input, to aggregate the latest news articles. The aggregated article data is then stored in a database for easy access in future processing.

[1348] Step 2:

[1349] Natural Language Processing:

[1350] The server applies natural language processing (NLP) to the stored news articles. Using the stored article data as input, it tokenizes the text, tags parts of speech, splits sentences, and extracts important keywords and phrases. This uncovers important information within the article and passes the extracted data on for further processing.

[1351] Step 3:

[1352] Summary generation:

[1353] The server generates a summary of the article using a generative AI model based on the information extracted by the NLP process. It uses key information from the extracted text as input to generate a prompt (e.g., "Please summarize this article: {article_text}"). As output, the generated summary text is stored in a database.

[1354] Step 4:

[1355] Trend analysis:

[1356] The server analyzes the generated summary data and identifies trends by extracting frequently occurring keywords and topics. Using the summary data as input, it applies data analysis algorithms, which generate trend information that is stored in a database for later retrieval and display.

[1357] Step 5:

[1358] Emotion recognition:

[1359] The in-vehicle system activates the emotion engine when the user is in the car to recognize the user's emotional state. As input, it uses facial expression data captured by an in-vehicle camera and voice data collected by an in-vehicle microphone. As output, analyzed emotion data is generated and sent to the server.

[1360] Step 6:

[1361] Leveraging sentiment data:

[1362] The server stores and analyzes the emotion data obtained from the emotion recognition engine. Using the emotion data as input, it applies an algorithm that adjusts article summary content and recommendations based on the user's emotional state. This results in appropriate news summaries and articles being selected and prepared for display to the user.

[1363] Step 7:

[1364] User interaction:

[1365] Users browse news summaries through their in-car infotainment system. They can use voice commands or the touchscreen as input to select a specific news category or topic, such as "Latest Technology Trends" or "Today's Top News." The server then searches for relevant news summaries based on the user's request and sends them to the in-car system. The in-car system displays the received summaries, and users can click on a specific news summary to view more information about it.

[1366] The above is the overall processing flow from news gathering to emotion recognition and article display.

[1367] 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.

[1368] 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.

[1369] 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.

[1370] 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.

[1371] 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.

[1372] 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.

[1373] 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).

[1374] 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.

[1375] 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."

[1376] 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.

[1377] 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).

[1378] 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.

[1379] 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.

[1380] 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.

[1381] 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.

[1382] 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.

[1383] 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.

[1384] 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.

[1385] 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.

[1386] 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.

[1387] 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.

[1388] The following is further disclosed regarding the above embodiment.

[1389] (Claim 1)

[1390] A means of collecting article data from multiple reliable sources;

[1391] a means for storing the collected article data;

[1392] A means of performing natural language processing on the stored article data to extract important information;

[1393] a means for generating a summary of the article based on the extracted information using a generative AI model;

[1394] a means for saving the generated summary;

[1395] A means of trending summary data to identify trends;

[1396] means for searching and displaying summaries based on user-specified criteria;

[1397] A system including:

[1398] (Claim 2)

[1399] 10. The system of claim 1, further comprising means for storing and providing trend analysis results for user access.

[1400] (Claim 3)

[1401] 10. The system of claim 1, further comprising means for allowing a user to view detailed information based on the summary data.

[1402] "Example 1"

[1403] (Claim 1)

[1404] A means of collecting article data from multiple reliable sources;

[1405] a means for storing the collected article data in a database;

[1406] A means of performing natural language processing on the stored article data to extract important information;

[1407] a means for generating a summary of the article based on the prompt using a generative AI model;

[1408] a means for storing the generated summaries in a database;

[1409] A means of trending summary data to identify trends;

[1410] means for searching and displaying summaries based on user-specified criteria;

[1411] A system including:

[1412] (Claim 2)

[1413] 10. The system of claim 1, further comprising means for storing the trend analysis results in a database and providing them for user access.

[1414] (Claim 3)

[1415] 10. The system of claim 1, further comprising means for allowing a user to view detailed information based on the summary data and trend analysis results.

[1416] "Application Example 1"

[1417] (Claim 1)

[1418] A means of collecting article data from multiple reliable sources;

[1419] a means for storing the collected article data;

[1420] A means of performing natural language processing on the stored article data to extract important information;

[1421] a means for generating a summary of the article based on the extracted information using a generative AI model;

[1422] a means for saving the generated summary;

[1423] A means of trending summary data to identify trends;

[1424] means for searching and displaying summaries based on user-specified criteria;

[1425] a means for generating and distributing recent news summaries for specified categories or topics;

[1426] A method to automatically analyze frequently occurring keywords from news summaries and display trend information,

[1427] A system including:

[1428] (Claim 2)

[1429] 10. The system of claim 1, further comprising means for storing and providing trend analysis results for user access.

[1430] (Claim 3)

[1431] 10. The system of claim 1, further comprising means for allowing a user to view detailed information based on the summary data.

[1432] "Example 2: Combining Emotion Engines"

[1433] (Claim 1)

[1434] A means of collecting article data from multiple reliable sources;

[1435] a means for storing the collected article data;

[1436] A means of performing natural language processing on the stored article data to extract important information;

[1437] a means for generating a summary of the article based on the extracted information using a generative AI model;

[1438] a means for saving the generated summary;

[1439] A means of trending summary data to identify trends;

[1440] means for searching and displaying summaries based on user-specified criteria;

[1441] means for recognizing the emotional state of a user;

[1442] means for tailoring article summaries and article recommendations based on the perceived emotional state;

[1443] A system including:

[1444] (Claim 2)

[1445] 10. The system of claim 1, further comprising means for storing and providing trend analysis results for user access.

[1446] (Claim 3)

[1447] 10. The system of claim 1, further comprising means for allowing a user to view detailed information based on the summary data.

[1448] "Application example 2 when combining emotion engines"

[1449] (Claim 1)

[1450] A means of collecting article data from multiple reliable sources;

[1451] a means for storing the collected article data;

[1452] A means of performing natural language processing on the stored article data to extract important information;

[1453] a means for generating a summary of the article based on the extracted information using a generative AI model;

[1454] a means for saving the generated summary;

[1455] A means of trending summary data to identify trends;

[1456] means for searching and displaying summaries based on user-specified criteria;

[1457] a means for recognizing an emotional state of a user in an in-vehicle system of an autonomous vehicle;

[1458] a means for tailoring article summaries and recommendations based on the perceived emotional state;

[1459] A system including:

[1460] (Claim 2)

[1461] 10. The system of claim 1, further comprising means for storing and providing trend analysis results for user access.

[1462] (Claim 3)

[1463] 10. The system of claim 1, further comprising means for allowing a user to view detailed information based on the summary data. [Explanation of symbols]

[1464] 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 article data from multiple reliable sources; a means for storing the collected article data; A means of performing natural language processing on the stored article data to extract important information; a means for generating a summary of the article based on the extracted information using a generative AI model; a means for saving the generated summary; A means of trending summary data to identify trends; means for searching and displaying summaries based on user-specified criteria; A system including:

2. 10. The system of claim 1, further comprising means for storing and providing trend analysis results for user access.

3. 10. The system of claim 1, further comprising means for allowing a user to view detailed information based on the summary data.

Images