System

Abstract

A system is provided.SOLUTION: A system, comprising: means for periodically obtaining trend keywords; means for collecting relevant news articles based on the obtained trend keywords; means for summarizing the collected news articles; and means for delivering the summarized news articles to users.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] Currently, trending keywords provided to users on social networking services to help them understand trending information are merely lists of keywords, and further effort is required, such as searching, to find specific content. This makes it difficult for users to quickly and easily access the latest topics. Therefore, a system is needed that reduces user effort and quickly provides specific content of topics in real time. [Means for solving the problem]

[0005] This invention solves the above problems by the following means. By constructing a system including a means for periodically acquiring trend keywords, a means for collecting related news articles based on the acquired trend keywords, a means for summarizing the collected news articles, and a means for delivering the summarized news articles to users, users can quickly and easily grasp the specific content of trend keywords. In particular, using a generative AI model as a means for summarizing news articles enables efficient and highly accurate summarization. Furthermore, by acquiring data from a specific news provider service when collecting news articles, highly reliable news information can be provided.

[0006] "Trending keywords" are words or phrases that attract the attention of many people during a specific period of time and are used with increasing frequency on social media, search engines, etc.

[0007] "Means for periodic acquisition" refers to functions or methods for automatically acquiring information at regular intervals.

[0008] A means for collecting "related news articles" is a function or method for automatically obtaining news articles related to a specific trending keyword from multiple news sources on the Internet.

[0009] "Means for summarizing" refers to functions and methods for shortening the content of collected news articles and extracting only the important information.

[0010] A "generative AI model" is an artificial intelligence algorithm that uses natural language processing technology to analyze text data and automatically generate summaries.

[0011] A "news service" is an organization or company that provides a website or API that distributes news information over the Internet.

[0012] "Means of distribution" refers to the communication functions and display methods used to deliver information to users.

[0013] "Users" are individuals or organizations that utilize the system to receive news summaries related to trending keywords. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

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

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

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

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

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

[0029] 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.

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

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] As an embodiment of the present invention, a system is constructed and operated in the following manner.

[0036] 1. Obtaining trending keywords

[0037] The server obtains trending keywords using the API of the SNS service at specific time intervals. At this time, the server accesses the API using authentication information to obtain a trending list. Keywords recognized as trending are extracted from this list.

[0038] 2. Collecting relevant news articles

[0039] The server uses the API of the news service to collect news articles related to the acquired trending keywords. The server sends a query to the news service and lists the contents of the retrieved news articles. This collection is done from multiple news sources, with the aim of collecting reliable articles.

[0040] 3. News article summaries

[0041] The server uses a generative AI model to summarize the collected news articles. Specifically, it uses natural language processing technology to extract the key points of each article and convert them into a shortened text. In this summarization method, the generative AI model analyzes the input long text and generates a short summary that contains only the information that is important to the user.

[0042] 4. Distribution of summary results

[0043] The server delivers the generated summaries to the user's device, where they are displayed, allowing the user to easily understand the latest topics. This information is delivered in real time, allowing users to quickly understand the specific content of trending keywords. Users can read summarized news about specific trends and quickly access related detailed information.

[0044] Specific examples

[0045] For example, let's consider the case where "new virus" becomes a trending topic on a particular social media service.

[0046] 1. The server obtains the trending keyword "new virus" from the API of a social networking service.

[0047] 2. The server collects related news articles from a news service based on the acquired keyword "new virus." It calls the news service API and retrieves multiple news articles.

[0048] 3. The server summarizes the collected news articles using a generative AI model. For example, if the article says, "The number of infected people due to a new virus is rapidly increasing," the generated summary will be, "The number of infected people is rapidly increasing."

[0049] 4. The server delivers the summarized news articles to the user's device, allowing the user to quickly check the summarized news about the "new virus" through the device.

[0050] This allows users to quickly and easily grasp detailed information about trends. The system of the present invention allows users to understand the content of topics in real time, eliminating the need to gather information.

[0051] The processing flow will be explained below.

[0052] Step 1:

[0053] The server periodically acquires trending keywords using the API of the SNS service. To do this, the server sets API authentication information of the SNS service in advance and accesses the API.

[0054] Step 2:

[0055] The server analyzes the acquired trend keyword information and categorizes the acquired keywords as needed, such as trends in a specific region or global trends. This categorization improves the accuracy of the information provided to users.

[0056] Step 3:

[0057] The server uses the API of the news service to collect related news articles based on the categorized trending keywords. The server sends a query to the API for each keyword to retrieve related news articles and store them in a list.

[0058] Step 4:

[0059] The server summarizes the content of collected news articles using a generative AI model (e.g., a natural language processing algorithm). For each news article, the generative AI model is applied to generate a short summary that extracts the key points.

[0060] Step 5:

[0061] The server then distributes the generated summaries to the users' devices. To do this, the server communicates with each user's device and sends the summarized news articles in an appropriate format, such as a notification or dashboard display.

[0062] Step 6:

[0063] The user's device displays the received summary. The device reads the summarized news article and displays it in a format that is easy for the user to view. The user can quickly check the summarized latest trend information through the device.

[0064] Step 7:

[0065] Users can review the summary and then access the original news article for more details, effortlessly capturing key information about a trend.

[0066] Through the above steps, the system can efficiently provide trend information to users.

[0067] Example 1

[0068] 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."

[0069] There is a lack of a way to quickly access current trending keywords and obtain summaries of related news articles in a centralized manner. While there is a need for a system that collects related news from multiple sources and automatically summarizes and provides it, the current information gathering and summarization process is decentralized, resulting in inefficiencies. Furthermore, obtaining reliable information is difficult, requiring effective management of users' time and resources.

[0070] 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.

[0071] In this invention, the server includes means for acquiring trend keywords at specific time intervals, means for collecting news articles from relevant information sources based on the acquired trend keywords, means for summarizing the collected news articles using natural language processing techniques, and means for delivering the generated summaries to a user's display device, thereby enabling the user to quickly and efficiently obtain summarized news articles related to the latest trend keywords.

[0072] A "specific time interval" is a fixed time period during which the system is set to perform an action periodically.

[0073] "Trending Keywords" are important keywords related to current trends and topics, typically obtained from social networking services and news sites.

[0074] "Source" means a website or service that provides news articles or other information.

[0075] "Natural language processing technology" refers to technology that enables computers to understand and process human language, including text analysis, summarization, and translation.

[0076] A "generative AI model" is a model that allows artificial intelligence to automatically generate sentences or create summaries from input data.

[0077] A "display device" is a device that allows a user to visually view information, such as a smartphone, tablet, or computer.

[0078] "Deliver" means that the server sends the generated data or summary to the user's terminal, and the user receives the data.

[0079] "Summarizing" means extracting the important parts from a large amount of information and summarizing the content in a concise manner.

[0080] This invention is a system consisting of a server, an information source API, a generative AI model, and a user display device. This system acquires trending keywords at specific time intervals, collects news articles based on the keywords, summarizes the collected articles, and finally delivers them to the user. A specific embodiment of this system is described in detail below.

[0081] Acquiring trending keywords

[0082] server

[0083] The server retrieves trending keywords at specific time intervals using a scheduling function. For example, trending keywords are retrieved using the API of a social networking service (e.g., SNS API). A request including authentication information is sent to the API to retrieve a list of current trending keywords. From this list, the latest trending keyword is selected.

[0084] Collecting relevant news articles

[0085] server

[0086] The server sends a query to the API of a news service (e.g., news API) based on the trending keywords it has acquired. The server sets the keywords as parameters to the API, collects related news articles from multiple sources, and creates a list of news articles by filtering out reliable information.

[0087] News article summaries

[0088] server

[0089] The server converts the collected news articles into JSON format and passes them to a generative AI model (e.g., Generative AI API). This model uses natural language processing techniques to extract key points and generate a concise summary. The generated summary is then stored in a database.

[0090] Summary results delivery

[0091] server

[0092] The server delivers the summary results to the user's display device. For example, it selects an appropriate delivery method (API, push notification, etc.) based on the information on the user's device. It then sends the summarized news article to the user's display device.

[0093] Terminal

[0094] The terminal receives the summary results sent from the server, analyzes the data, and displays it on a user interface, where the user can check the displayed summary results and use links to obtain more information.

[0095] Specific examples

[0096] For example, if "new virus" becomes a trend on a particular social networking site, the following process will occur:

[0097] 1. The server retrieves the trending keyword "new virus" from the SNS API.

[0098] 2. Based on the acquired keyword "new virus," the server calls the news API and collects related news articles.

[0099] 3. The server summarizes the collected news articles using a generative AI model. If the collected article is titled "The number of infected people due to a new virus is rapidly increasing," the generated summary will be "The number of infected people is rapidly increasing."

[0100] 4. The server delivers the generated summary to the user's device, allowing the user to quickly check the summarized news about the "new virus" through the device.

[0101] Prompt Sentence Examples

[0102] "Please summarize the latest news about the virus. Below is the full news article."

[0103] This system allows users to efficiently grasp the latest trend information.

[0104] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0105] Program processing steps

[0106] Step 1: Get trending keywords

[0107] server

[0108] 1. Input: The server has a scheduler that runs periodically and prepares authentication information for the SNS service API at that time interval.

[0109] 2. Data processing: Send a request to the API using your authentication information and receive a list of trending keywords as a response.

[0110] 3. Specific operation: Send a "GET" request to the SNS service API endpoint and include authentication information in the header.

[0111] 4. Output: The trending keyword list is obtained and new trending keywords are extracted from this list.

[0112] Step 2: Collect relevant news articles

[0113] server

[0114] 1. Input: Prepare authentication information for the news service API based on the trending keywords obtained.

[0115] 2. Data calculation: Trending keywords are set as parameters in the API request, and article data is collected from multiple sources from news providers.

[0116] 3. Specific operation: Send a "GET" request to the news service API and set authentication information including the API key in the header.

[0117] 4. Output: A list containing multiple news articles is obtained, and the most reliable articles are filtered and listed.

[0118] Step 3: Summarize the news article

[0119] server

[0120] 1. Input: Collected news articles are converted into JSON format and passed to the generative AI model.

[0121] 2. Data calculation: The generative AI model is fed news article data along with a prompt, and the model extracts key points and generates a summary.

[0122] 3. Specific behavior: The generative AI model is given the prompt, "Please summarize the latest news about the new virus. Below is the full news article." and then the full news article is sent.

[0123] 4. Output: Receive the generated summary sentences and store them in a database in an appropriate format.

[0124] Step 4: Delivering summary results

[0125] server

[0126] 1. Input: Obtain the summary results stored in the database and the user's device information.

[0127] 2. Data calculation: To send the summary results to the user's device, the optimal delivery method is selected based on the user's device information (e.g., via API, push notification, etc.).

[0128] 3. Specific operation: Send an HTTP POST request to the user's device and send the summary results in JSON format.

[0129] 4. Output: The summarized news article is delivered to the user's device.

[0130] Terminal

[0131] 1. Input: Receives the summary results sent from the server.

[0132] 2. Data processing: Parse the JSON data and display it in the user interface.

[0133] 3. Specific operation: Parse the JSON data and display the summary results appropriately on the screen.

[0134] 4. Output: The summary results are ready for the user to review.

[0135] Step 5: Review summary results

[0136] User

[0137] 1. Input: Check the summary results displayed on the terminal.

[0138] 2. Specific action: Access detailed information by tapping or clicking on the summary results displayed on the device.

[0139] 3. Output: Users can see a concise summary of the latest trending information and quickly access more detailed information.

[0140] (Application example 1)

[0141] 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."

[0142] In today's society, it is difficult for users to quickly grasp the latest trend information from the vast amount of information available on the Internet. Furthermore, because news articles cover a wide range of topics, users need to be able to grasp the key points in a short amount of time. Furthermore, users want to be able to receive summaries of news in real time, no matter where they are. New technologies are needed to solve these problems.

[0143] 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.

[0144] In this invention, the server includes means for periodically acquiring trend keywords, means for collecting news articles related to the acquired trend keywords, and means for summarizing the collected news articles, thereby enabling users to receive summarized news in real time using a smartphone or head-mounted display and quickly grasp the latest information.

[0145] "Trending keywords" refer to keywords obtained from SNS services at specific time intervals that are of interest to many users at that time.

[0146] A "news article" refers to a piece of text that contains information about a particular event or topic, collected from a news service.

[0147] A "generative AI model" refers to an artificial intelligence model that uses natural language processing technology to analyze text, extract key points, and generate a summary.

[0148] "Real-time" refers to a state in which processing is almost instantaneous and results are reflected without delay.

[0149] "User terminal" refers to a device operated by a user to receive and display information, and specifically refers to a smartphone or head-mounted display.

[0150] To implement this invention, a system is constructed using a server, a smartphone, a head-mounted display, and specific software.

[0151] Hardware and software used

[0152] Hardware: Smartphone (iOS / Android), Head-Mounted Display (HMD)

[0153] software:

[0154] Backend: Node.js, Express.js

[0155] Database: MongoDB

[0156] Frontend: React Native (for smartphones), Unity (for HMD)

[0157] API: SNS service API (acquiring trending keywords), news service API (acquiring news articles)

[0158] NLP: Generative AI model (OpenAI GPT-3)

[0159] System Operation

[0160] The server obtains trending keywords at regular intervals using the API of the SNS service, and extracts important keywords from the obtained trending list using the API authentication information.

[0161] The server then uses the API of the news service to collect relevant news articles based on the trending keywords it has acquired. This collection is done from multiple reliable news sources, and the acquired news articles are stored in the server's database.

[0162] The collected news articles are summarized using a generative AI model that analyzes the key points of the news article and generates a summary text.

[0163] The user's device (smartphone or head-mounted display) receives and displays summarized news articles from the server in real time. The interface for smartphones is built using React Native, and the interface for HMDs is built using Unity.

[0164] Specific examples

[0165] For example, if "new virus" becomes a trending topic on a particular social networking service, the server obtains the trending keyword "new virus" from the social networking service's API. Next, the server collects related news articles from news providers based on the obtained keyword "new virus." If the collected news article states that "the number of people infected with the new virus is rapidly increasing," the news article is summarized using a generative AI model, and a summary is generated stating, "The number of infected people is rapidly increasing." This summary is then distributed from the server to the user's device in real time.

[0166] Prompt Sentence Examples

[0167] Summarize the following news article:

[0168] The number of people infected with the new virus is rapidly increasing. New countermeasures are needed, and governments around the world are scrambling to implement them. Vaccine development is also progressing at a rapid pace.

[0169] summary:

[0170] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0171] Step 1:

[0172] The server obtains trending keywords at specific time intervals using the API of the SNS service. At this time, the server accesses the API using pre-configured API authentication information to obtain a trending list. The input is raw data from the API of the SNS service, and the output is a list of the obtained trending keywords.

[0173] Step 2:

[0174] The server collects related news articles using the news service's API based on the trending keywords obtained in step 1. The server sends a query to the news service using each trending keyword, lists the obtained news articles, and stores them in a database. The input is the list of trending keywords and the raw data from the news service's API, and the output is the list of collected news articles.

[0175] Step 3:

[0176] The server uses a generative AI model to summarize the collected news articles. First, each news article is input into the generative AI model, and natural language processing techniques are used to extract key points. The server then retrieves the generated summary text and stores it in a database. The input is a list of news articles, and the output is a list of summarized text.

[0177] Step 4:

[0178] The server delivers summarized news articles to users' devices (smartphones and head-mounted displays) in real time. The server uses WebSocket to send the summary results to connected devices. The input is a list of summarized text, and the output is the summarized news article displayed on the user's device.

[0179] Step 5:

[0180] The user's device displays the summarized news article received from the server. The user interface is built using React Native for smartphones and Unity for HMDs. The input is the summary text from the server, and the output is the summarized news that the user sees on the interface.

[0181] Step 6:

[0182] Users can check the summary news delivered through the device and access detailed information as needed. Links to detailed information are displayed on the smartphone or HMD interface for easy access. The input is the displayed summary news, and the output is the viewing of the detailed page based on the user's action.

[0183] This process flow allows users to quickly obtain the latest trend information summarized in real time and access the information they need.

[0184] 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.

[0185] As an embodiment of the present invention, a system is constructed and operated in the following manner.

[0186] 1. Obtaining trending keywords

[0187] The server periodically obtains trending keywords using the API of the SNS service at specific time intervals. To do this, the server sets API authentication information for the SNS service in advance and obtains a trending list by accessing the API. Keywords recognized as trending are extracted from this list.

[0188] 2. Collecting relevant news articles

[0189] The server uses the API of the news service to collect related news articles based on the acquired trending keywords. The server sends queries to the news service and stores the contents of related news articles in a list. This collection is done from multiple news sources, with the aim of collecting reliable articles.

[0190] 3. News article summaries

[0191] The server summarizes the content of collected news articles using a generative AI model (e.g., a natural language processing algorithm). For each news article, the generative AI model is applied to generate a short summary that extracts the key points.

[0192] 4. Recognition of user emotions using an emotion engine

[0193] The server uses an emotion engine to recognize the user's emotions. This emotion recognition is performed by analyzing input data (e.g., text, facial expression recognition, and voice tone) when the user operates the device. The analyzed user's emotions are used to deliver news articles.

[0194] 5. Delivery and customization of summary results

[0195] The server customizes the generated summary based on the user's emotions and delivers it to the user's device. For example, if the user is feeling stressed, positive news can be prioritized. This makes it possible to provide appropriate information according to the user's emotional state.

[0196] Specific examples

[0197] For example, let's say "pandemic" becomes a trending topic on a particular social media service.

[0198] 1. The server retrieves the trending keyword "pandemic" from the API of a social networking service.

[0199] 2. The server collects relevant news articles from a news service based on the acquired keyword "pandemic." It calls the news service API and retrieves multiple news articles.

[0200] 3. The server uses a generative AI model to summarize the collected news articles. For example, if the article says, "The pandemic is having widespread impacts," the generated summary will be, "The impact is widespread."

[0201] 4. The server uses the emotion engine to analyze the user's emotions. For example, if the user is feeling anxious, the server performs the next step based on this emotion information.

[0202] 5. When delivering summarized news articles to the user's device, the server customizes them based on the user's emotions. For example, it prioritizes articles containing positive news or countermeasures.

[0203] This allows users to quickly and easily grasp detailed information related to trending keywords while receiving news that matches their emotional state. The system of the present invention saves users the trouble of gathering information, enables them to understand the content of topics in real time, and provides information that takes into consideration the user's emotions.

[0204] The processing flow will be explained below.

[0205] Step 1:

[0206] The server periodically obtains trending keywords using the API of the social networking service. To do this, the server sets the API authentication information of the social networking service in advance and obtains a trending list by accessing the API. This list contains keywords that many people are currently interested in.

[0207] Step 2:

[0208] The server analyzes the acquired trend keyword information and categorizes it as necessary. Categorization can be divided into global trends, trends in specific regions, etc. This categorization makes it possible to provide information based on the user's interests.

[0209] Step 3:

[0210] The server uses the API of the news service to collect related news articles based on the classified trending keywords. The server sends a query to the API for each keyword to obtain the content of related news articles. This collection is done from multiple news sources, with the aim of collecting reliable articles.

[0211] Step 4:

[0212] The server uses a generative AI model to summarize the contents of collected news articles. Specifically, it uses natural language processing technology to extract key points from each article and convert them into a shortened text. For example, from an article titled "The pandemic has had widespread impacts," it generates a summary that reads "The impact is widespread."

[0213] Step 5:

[0214] The server uses an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's input data (e.g., keyboard input on a computer, touch operation on a smartphone, voice input, etc.) and facial expression data obtained through a facial recognition camera. This analysis identifies the user's current emotional state.

[0215] Step 6:

[0216] The server customizes the summarized news articles based on the analyzed user sentiment: for example, if the user is feeling anxious, it will prioritize articles that contain positive news or reassuring elements.

[0217] Step 7:

[0218] The server delivers the customized summary results to the user's device. The server communicates with each user's device and sends the summarized news article in an appropriate format (e.g., notification or display in a dashboard).

[0219] Step 8:

[0220] The user's device then displays the summaries it receives. The device reads the summarized news articles and displays them in a user-friendly format, allowing the user to quickly get up to speed on the latest and most important information about trending keywords.

[0221] Step 9:

[0222] Users can view the summary and access the original news article if they need more information, making it easy for users to get more information about a particular trend.

[0223] By implementing the above steps, the system can efficiently provide users with trend information. Furthermore, by recognizing the user's emotions and customizing the information provided, more appropriate and user-friendly information can be provided.

[0224] Example 2

[0225] 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."

[0226] In modern society, a vast amount of information exists on the Internet, making it difficult for users to quickly obtain the accurate and appropriate information they need. Furthermore, information provided is not adequately tailored to the user's emotional state and interests, which can lead to stress and confusion due to information overload. Therefore, there is a need for a system that collects appropriate information related to trending keywords, summarizes it using a generative AI model, and delivers it in a customized format according to the user's emotional state.

[0227] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0228] In this invention, the server includes means for periodically acquiring trend keywords, means for collecting related information based on the acquired trend keywords, means for summarizing the collected news information using a generative AI model, means for recognizing a user's emotion, and means for customizing and distributing the summarized news information based on the recognized user's emotion. This allows users to quickly and easily grasp detailed information related to trends and receive information that matches their own emotional state.

[0229] "Trending keywords" are keywords that are currently of great social interest or topicality and are acquired at specific time intervals.

[0230] An "information service" is a website or online platform accessible through an API that provides news or other information.

[0231] A "generative AI model" is an algorithm or system that uses artificial intelligence to generate text, summarize, or perform other natural language processing.

[0232] "User emotion" refers to the psychological state (e.g., excitement, fatigue, stress, anxiety, etc.) of the user when receiving information.

[0233] "Emotion recognition means" is a technology for analyzing the user's input data, facial expressions, tone of voice, etc. to identify the user's emotional state.

[0234] "News information" is a collective term that includes reports of a particular event or situation, including articles, video clips, and breaking news.

[0235] "Customization" is the process of tailoring information to a user's needs and emotional state, optimizing and delivering specific content.

[0236] "Summarization" is the process of extracting the key points from the original information and presenting them in a concise format.

[0237] In order to implement the present invention, a system is constructed and operated in the following manner.

[0238] First, the server periodically obtains trending keywords using the API of the SNS service. To do this, the server must be set up with the API authentication information of the SNS service in advance. For example, if Twitter is used as the SNS service, the server will access the API using the authentication information for the Twitter API and obtain trending keywords. This series of operations is performed automatically at specific time intervals.

[0239] Next, the server uses the API of the news provider to collect related news articles based on the acquired trending keywords. For example, when using the Google News API, the server generates a query based on a keyword such as "pandemic" and accesses the API to collect related news articles. The collected news articles are stored in a database.

[0240] The server summarizes the collected news articles using a generative AI model (e.g., OpenAI's GPT-3). Specifically, the server inputs the content of each news article into GPT-3, which generates a short summary that extracts the key points. An example prompt is as follows:

[0241] Summarize the news article.

[0242] Article: The impact of the pandemic is widespread. The economic impact is significant, calling for international cooperation and forcing governments to act quickly.

[0243] summary:

[0244] The summary generated is "Wide-reaching impact."

[0245] The server then uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's emotions. The server collects input data (e.g., text, facial expression recognition, and voice tone) provided by the user's device and inputs it into the emotion engine to analyze the user's emotional state. For example, it can determine that the user is feeling anxious.

[0246] Finally, the server customizes the summarized news articles based on the user's emotional state and delivers them to the user's device. For example, if the user is feeling anxious, it will prioritize articles containing positive news and information on how to cope with the situation. This allows the user to receive appropriate information tailored to their emotional state.

[0247] As described above, the present invention is a system that provides information suited to the user by collecting related information based on trend keywords, summarizing it, and further customizing it according to the user's emotional state.

[0248] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0249] System program processing flow

[0250] Step 1:

[0251] The server periodically obtains trending keywords using the API of the social networking service. First, the server accesses the social networking service using pre-configured API authentication information to obtain the latest list of trending keywords at specific time intervals. This is done by sending an API request and receiving trending keywords as a response. For example, consider the case where the server obtains the keyword "pandemic" using the Twitter API. This operation is repeated every few minutes, allowing the server to always maintain the latest trending information. The input is the API authentication information of the social networking service, and the output is the list of trending keywords.

[0252] Step 2:

[0253] The server uses the API of the news service to collect related news articles based on the acquired trending keywords. Specifically, the server uses the acquired trending keywords to send a search query to the API of the news service to collect related news articles. For example, it sends a query to the Google News API for the keyword "pandemic" to obtain related news articles. The collected news articles are stored in list format. The input is the trending keywords, and the output is a list of news articles.

[0254] Step 3:

[0255] The server summarizes the collected news articles using a generative AI model. First, the server inputs the content of each news article into a generative AI model (e.g., OpenAI's GPT-3) to generate a short summary that extracts the key points. A specific prompt is created and input into the model to obtain the summary. For example, for the news article "The impact of the pandemic is widespread. The economic impact is significant, calling for international cooperation. Governments around the world are being urged to act quickly," the prompt is set as follows:

[0256] Summarize the news article.

[0257] Article: The impact of the pandemic is widespread. The economic impact is significant, calling for international cooperation and forcing governments to act quickly.

[0258] summary:

[0259] The summary generated by this prompt is "Wide-reaching impact." The input is a news article and the output is a summary statement.

[0260] Step 4:

[0261] The server uses an emotion engine to recognize the user's emotions. The server collects input data (e.g., text, facial expression recognition, and voice tone) provided by the user's device and inputs this data into an emotion engine (e.g., IBM Watson Tone Analyzer) for analysis. For example, when a user enters a text message, the emotion engine analyzes the text and identifies the user's emotional state (e.g., anxiety, joy, anger). The input is the user's input data, and the output is the emotion analysis result.

[0262] Step 5:

[0263] The server customizes summarized news articles based on the user's emotional state and delivers them to the user's device. Based on the analyzed emotional information, the server selects the news summary that best suits each user's emotions and delivers it in a customized format. For example, if a user is feeling anxious, it will prioritize delivery of positive news and information about solutions. This allows users to receive information tailored to their emotional state. The input is a summarized news article and the results of the emotion analysis, and the output is customized news information delivered to the user.

[0264] This allows the server to provide information optimized for the user, thereby improving user satisfaction.

[0265] (Application example 2)

[0266] 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."

[0267] Currently, there are many systems that acquire and summarize trending information and related news articles and deliver them to users. However, these systems provide information uniformly without considering the user's emotional state. As a result, the information received by users may not necessarily match their current state of mind, which may increase stress and anxiety. Therefore, there is a need for information delivery that responds to the user's emotional state.

[0268] The identification process 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 periodically acquiring trend keywords, means for collecting related information based on the acquired trend keywords, means for summarizing the collected information, means for analyzing the user's emotions using an emotion analysis engine, and means for customizing the summarized information according to the user's emotions and delivering it. This makes it possible to provide information according to the user's emotional state.

[0269] "Trending keywords" are words or phrases that are trending across multiple sources over a specific time period.

[0270] "Related information" is data such as news articles and web pages collected based on trending keywords.

[0271] "Summarizing" refers to extracting the key points of the original information and converting it into a concise form.

[0272] An "emotion analysis engine" is an algorithm or software that analyzes a user's input data and determines their emotional state.

[0273] "Customization" refers to tailoring the content and presentation of information based on the user's particular requirements, particularly their emotional state.

[0274] An embodiment of the present invention is a system for enabling a user to obtain related information based on trend keywords and have it delivered in a form customized according to an emotional state. The system includes the following means.

[0275] First, the server periodically obtains trending keywords. To do this, the server uses SNS APIs to extract appropriate keywords from trending lists. The SNS APIs used include APIs of common social networking services.

[0276] Next, the server collects related information based on the acquired trending keywords from the APIs of various news providers, including a wide variety of news sources that are used as news provider APIs.

[0277] It then uses a generative AI model, which includes a natural language processing algorithm such as OpenAI GPT-4, to summarize the collected news articles. By utilizing this generative AI model, it extracts the main points of the news articles and summarizes them in a concise form that is easy for users to understand.

[0278] Furthermore, the server analyzes the user's emotions using an emotion analysis engine, such as Microsoft Azure Emotion API, which analyzes emotions from the user's input data (e.g., text, facial expressions, and voice tone).

[0279] Finally, the server customizes the summarized news articles according to the user's emotions and delivers them to the user's device. For example, if the user is feeling stressed, the server will prioritize positive news and information about relaxation based on this emotional information.

[0280] As a concrete example, let's consider the case where "pandemic" becomes a trending keyword on a social networking site. The server retrieves the keyword "pandemic" from the social networking site API and, based on this, collects related news articles from the news service API. The collected news articles are summarized using a generative AI model, and the content is summarized as "The impact of the pandemic is widespread." If the user is feeling anxious, this information is used to add positive countermeasure information and customize the message, delivering it as "The impact of the pandemic is widespread, but solutions are underway."

[0281] Examples of prompt sentences include:

[0282] import openai

[0283] import requests

[0284] from azure.ai.textanalytics import TextAnalyticsClient

[0285] from azure.core.credentials import AzureKeyCredential

[0286] Get trending keywords from SNS API

[0287] def fetch_trend_keywords(api_url, headers):

[0288] response = requests.get(api_url, headers=headers)

[0289] if response.status_code == 200:

[0290] trends = response.json()

[0291] return trends['data'][0]['trending_keywords']

[0292] else:

[0293] return []

[0294] Collecting related news articles from news service APIs

[0295] def fetch_news_articles(api_url, api_key, keyword):

[0296] params = {

[0297] 'q': keyword,

[0298] 'apiKey': api_key,

[0299] }

[0300] response = requests.get(api_url, params=params)

[0301] if response.status_code == 200:

[0302] articles = response.json()

[0303] return articles['articles']

[0304] else:

[0305] return []

[0306] Summarizing news articles with generative AI models

[0307] def summarize_article(article_text, model="text-davinci-003"):

[0308] response = openai.Completion.create(

[0309] engine=model,

[0310] prompt=f"Please summarize the following news article: {article_text}",

[0311] max_tokens=100

[0312] )

[0313] return response.choices[0].text.strip()

[0314] Recognize user emotions using an emotion engine

[0315] def analyze_user_emotion(text, endpoint, key):

[0316] client = TextAnalyticsClient(endpoint=endpoint, credential=AzureKeyCredential(key))

[0317] response = client.analyze_sentiment(documents=[text])[0]

[0318] return response.sentiment

[0319] Main Program

[0320] if __name__ == "__main__":

[0321] Get trending keywords

[0322] trend_keywords = fetch_trend_keywords("https: / / api.twitter.com / 2 / tweets / trending", headers={"Authorization": f"Bearer {twitter_bearer_token}"})

[0323] for keyword in trend_keywords:

[0324] Collect news articles

[0325] articles = fetch_news_articles("https: / / newsapi.org / v2 / everything", "your_newsapi_key", keyword)

[0326] for article in articles:

[0327] News article summaries

[0328] summary = summarize_article(article['content'])

[0329] Recognize user emotions

[0330] user_emotion = analyze_user_emotion(user_input_text, endpoint="your_endpoint", key="your_key")

[0331] News article delivery (customized based on user sentiment)

[0332] if user_emotion == 'positive':

[0333] customized_summary = f"Good News: {summary}"

[0334] elif user_emotion == 'negative':

[0335] customized_summary = f"Don't worry: we have a solution for {summary}."

[0336] else:

[0337] customized_summary = summary

[0338] View summary results

[0339] print(customized_summary)

[0340] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0341] Step 1:

[0342] The server periodically obtains trending keywords from the API of the social networking service. Specifically, it accesses the API of social networking services such as Twitter at specific time intervals to obtain a trending list. The latest trending keywords are extracted from this trending list and used as input for the next processing step. The input is the response data of the social networking service API, and the output is a list of trending keywords.

[0343] Step 2:

[0344] The server collects related information based on the acquired trend keywords. Specifically, it sends the trend keywords as queries to a news service API (e.g., NewsAPI) to retrieve related news articles. The input is the trend keywords and the response data of the news service API, and the output is a list of related news articles.

[0345] Step 3:

[0346] The server summarizes the collected news articles using a generative AI model. Specifically, the full text of each collected news article is input into OpenAI's GPT model, which generates a short summary that extracts the main points. The input is the content of the news article, and the output is the summary of the news article.

[0347] Step 4:

[0348] The server uses an emotion analysis engine to analyze the user's emotions. Specifically, it uses the Microsoft Azure Emotion API to analyze emotions based on text data, facial expressions, and voice tone entered by the user from their device. The input is the user's input data, and the output is the analyzed emotional state (e.g., positive, negative, neutral).

[0349] Step 5:

[0350] The server customizes the summarized news article according to the user's emotions. Specifically, it adjusts the content of the news article based on the analyzed emotional state. For example, if the user has negative emotions, it includes additional information that emphasizes positive aspects and solutions. This process takes the news summary and the results of the emotion analysis as input, and outputs a customized news article.

[0351] Step 6:

[0352] The server delivers customized news articles to the user's device. Specifically, the customized news articles are delivered to the user's smartphone or head-mounted display via push notifications, in-app displays, etc. The input is the customized news article, and the output is the delivery result to the user's device.

[0353] Through the above processing steps, it becomes possible to customize related information based on trend keywords according to the emotional state of the user and deliver it in an appropriate format.

[0354] 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.

[0355] 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.

[0356] 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.

[0357] [Second embodiment]

[0358] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0359] 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.

[0360] 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).

[0361] 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.

[0362] 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.

[0363] 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).

[0364] 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.

[0365] 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.

[0366] 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.

[0367] 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.

[0368] 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.

[0369] 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."

[0370] As an embodiment of the present invention, a system is constructed and operated in the following manner.

[0371] 1. Obtaining trending keywords

[0372] The server obtains trending keywords using the API of the SNS service at specific time intervals. At this time, the server accesses the API using authentication information to obtain a trending list. Keywords recognized as trending are extracted from this list.

[0373] 2. Collecting relevant news articles

[0374] The server uses the API of the news service to collect news articles related to the acquired trending keywords. The server sends a query to the news service and lists the contents of the retrieved news articles. This collection is done from multiple news sources, with the aim of collecting reliable articles.

[0375] 3. News article summaries

[0376] The server uses a generative AI model to summarize the collected news articles. Specifically, it uses natural language processing technology to extract the key points of each article and convert them into a shortened text. In this summarization method, the generative AI model analyzes the input long text and generates a short summary that contains only the information that is important to the user.

[0377] 4. Distribution of summary results

[0378] The server delivers the generated summaries to the user's device, where they are displayed, allowing the user to easily understand the latest topics. This information is delivered in real time, allowing users to quickly understand the specific content of trending keywords. Users can read summarized news about specific trends and quickly access related detailed information.

[0379] Specific examples

[0380] For example, let's consider the case where "new virus" becomes a trending topic on a particular social media service.

[0381] 1. The server obtains the trending keyword "new virus" from the API of a social networking service.

[0382] 2. The server collects related news articles from a news service based on the acquired keyword "new virus." It calls the news service API and retrieves multiple news articles.

[0383] 3. The server summarizes the collected news articles using a generative AI model. For example, if the article says, "The number of infected people due to a new virus is rapidly increasing," the generated summary will be, "The number of infected people is rapidly increasing."

[0384] 4. The server delivers the summarized news articles to the user's device, allowing the user to quickly check the summarized news about the "new virus" through the device.

[0385] This allows users to quickly and easily grasp detailed information about trends. The system of the present invention allows users to understand the content of topics in real time, eliminating the need to gather information.

[0386] The processing flow will be explained below.

[0387] Step 1:

[0388] The server periodically acquires trending keywords using the API of the SNS service. To do this, the server sets API authentication information of the SNS service in advance and accesses the API.

[0389] Step 2:

[0390] The server analyzes the acquired trend keyword information and categorizes the acquired keywords as needed, such as trends in a specific region or global trends. This categorization improves the accuracy of the information provided to users.

[0391] Step 3:

[0392] The server uses the API of the news service to collect related news articles based on the categorized trending keywords. The server sends a query to the API for each keyword to retrieve related news articles and store them in a list.

[0393] Step 4:

[0394] The server summarizes the content of collected news articles using a generative AI model (e.g., a natural language processing algorithm). For each news article, the generative AI model is applied to generate a short summary that extracts the key points.

[0395] Step 5:

[0396] The server then distributes the generated summaries to the users' devices. To do this, the server communicates with each user's device and sends the summarized news articles in an appropriate format, such as a notification or dashboard display.

[0397] Step 6:

[0398] The user's device displays the received summary. The device reads the summarized news article and displays it in a format that is easy for the user to view. The user can quickly check the summarized latest trend information through the device.

[0399] Step 7:

[0400] Users can review the summary and then access the original news article for more details, effortlessly capturing key information about a trend.

[0401] Through the above steps, the system can efficiently provide trend information to users.

[0402] Example 1

[0403] 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."

[0404] There is a lack of a way to quickly access current trending keywords and obtain summaries of related news articles in a centralized manner. While there is a need for a system that collects related news from multiple sources and automatically summarizes and provides it, the current information gathering and summarization process is decentralized, resulting in inefficiencies. Furthermore, obtaining reliable information is difficult, requiring effective management of users' time and resources.

[0405] 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.

[0406] In this invention, the server includes means for acquiring trend keywords at specific time intervals, means for collecting news articles from relevant information sources based on the acquired trend keywords, means for summarizing the collected news articles using natural language processing techniques, and means for delivering the generated summaries to a user's display device, thereby enabling the user to quickly and efficiently obtain summarized news articles related to the latest trend keywords.

[0407] A "specific time interval" is a fixed time period during which the system is set to perform an action periodically.

[0408] "Trending Keywords" are important keywords related to current trends and topics, typically obtained from social networking services and news sites.

[0409] "Source" means a website or service that provides news articles or other information.

[0410] "Natural language processing technology" refers to technology that enables computers to understand and process human language, including text analysis, summarization, and translation.

[0411] A "generative AI model" is a model that allows artificial intelligence to automatically generate sentences or create summaries from input data.

[0412] A "display device" is a device that allows a user to visually view information, such as a smartphone, tablet, or computer.

[0413] "Deliver" means that the server sends the generated data or summary to the user's terminal, and the user receives the data.

[0414] "Summarizing" means extracting the important parts from a large amount of information and summarizing the content in a concise manner.

[0415] This invention is a system consisting of a server, an information source API, a generative AI model, and a user display device. This system acquires trending keywords at specific time intervals, collects news articles based on the keywords, summarizes the collected articles, and finally delivers them to the user. A specific embodiment of this system is described in detail below.

[0416] Acquiring trending keywords

[0417] server

[0418] The server retrieves trending keywords at specific time intervals using a scheduling function. For example, trending keywords are retrieved using the API of a social networking service (e.g., SNS API). A request including authentication information is sent to the API to retrieve a list of current trending keywords. From this list, the latest trending keyword is selected.

[0419] Collecting relevant news articles

[0420] server

[0421] The server sends a query to the API of a news service (e.g., news API) based on the trending keywords it has acquired. The server sets the keywords as parameters to the API, collects related news articles from multiple sources, and creates a list of news articles by filtering out reliable information.

[0422] News article summaries

[0423] server

[0424] The server converts the collected news articles into JSON format and passes them to a generative AI model (e.g., Generative AI API). This model uses natural language processing techniques to extract key points and generate a concise summary. The generated summary is then stored in a database.

[0425] Summary results delivery

[0426] server

[0427] The server delivers the summary results to the user's display device. For example, it selects an appropriate delivery method (API, push notification, etc.) based on the information on the user's device. It then sends the summarized news article to the user's display device.

[0428] Terminal

[0429] The terminal receives the summary results sent from the server, analyzes the data, and displays it on a user interface, where the user can check the displayed summary results and use links to obtain more information.

[0430] Specific examples

[0431] For example, if "new virus" becomes a trend on a particular social networking site, the following process will occur:

[0432] 1. The server retrieves the trending keyword "new virus" from the SNS API.

[0433] 2. Based on the acquired keyword "new virus," the server calls the news API and collects related news articles.

[0434] 3. The server summarizes the collected news articles using a generative AI model. If the collected article is titled "The number of infected people due to a new virus is rapidly increasing," the generated summary will be "The number of infected people is rapidly increasing."

[0435] 4. The server delivers the generated summary to the user's device, allowing the user to quickly check the summarized news about the "new virus" through the device.

[0436] Prompt Sentence Examples

[0437] "Please summarize the latest news about the virus. Below is the full news article."

[0438] This system allows users to efficiently grasp the latest trend information.

[0439] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0440] Program processing steps

[0441] Step 1: Get trending keywords

[0442] server

[0443] 1. Input: The server has a scheduler that runs periodically and prepares authentication information for the SNS service API at that time interval.

[0444] 2. Data processing: Send a request to the API using your authentication information and receive a list of trending keywords as a response.

[0445] 3. Specific operation: Send a "GET" request to the SNS service API endpoint and include authentication information in the header.

[0446] 4. Output: The trending keyword list is obtained and new trending keywords are extracted from this list.

[0447] Step 2: Collect relevant news articles

[0448] server

[0449] 1. Input: Prepare authentication information for the news service API based on the trending keywords obtained.

[0450] 2. Data calculation: Trending keywords are set as parameters in the API request, and article data is collected from multiple sources from news providers.

[0451] 3. Specific operation: Send a "GET" request to the news service API and set authentication information including the API key in the header.

[0452] 4. Output: A list containing multiple news articles is obtained, and the most reliable articles are filtered and listed.

[0453] Step 3: Summarize the news article

[0454] server

[0455] 1. Input: Collected news articles are converted into JSON format and passed to the generative AI model.

[0456] 2. Data calculation: The generative AI model is fed news article data along with a prompt, and the model extracts key points and generates a summary.

[0457] 3. Specific behavior: The generative AI model is given the prompt, "Please summarize the latest news about the new virus. Below is the full news article." and then the full news article is sent.

[0458] 4. Output: Receive the generated summary sentences and store them in a database in an appropriate format.

[0459] Step 4: Delivering summary results

[0460] server

[0461] 1. Input: Obtain the summary results stored in the database and the user's device information.

[0462] 2. Data calculation: To send the summary results to the user's device, the optimal delivery method is selected based on the user's device information (e.g., via API, push notification, etc.).

[0463] 3. Specific operation: Send an HTTP POST request to the user's device and send the summary results in JSON format.

[0464] 4. Output: The summarized news article is delivered to the user's device.

[0465] Terminal

[0466] 1. Input: Receives the summary results sent from the server.

[0467] 2. Data processing: Parse the JSON data and display it in the user interface.

[0468] 3. Specific operation: Parse the JSON data and display the summary results appropriately on the screen.

[0469] 4. Output: The summary results are ready for the user to review.

[0470] Step 5: Review summary results

[0471] User

[0472] 1. Input: Check the summary results displayed on the terminal.

[0473] 2. Specific action: Access detailed information by tapping or clicking on the summary results displayed on the device.

[0474] 3. Output: Users can see a concise summary of the latest trending information and quickly access more detailed information.

[0475] (Application example 1)

[0476] 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."

[0477] In today's society, it is difficult for users to quickly grasp the latest trend information from the vast amount of information available on the Internet. Furthermore, because news articles cover a wide range of topics, users need to be able to grasp the key points in a short amount of time. Furthermore, users want to be able to receive summaries of news in real time, no matter where they are. New technologies are needed to solve these problems.

[0478] 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.

[0479] In this invention, the server includes means for periodically acquiring trend keywords, means for collecting news articles related to the acquired trend keywords, and means for summarizing the collected news articles, thereby enabling users to receive summarized news in real time using a smartphone or head-mounted display and quickly grasp the latest information.

[0480] "Trending keywords" refer to keywords obtained from SNS services at specific time intervals that are of interest to many users at that time.

[0481] A "news article" refers to a piece of text that contains information about a particular event or topic, collected from a news service.

[0482] A "generative AI model" refers to an artificial intelligence model that uses natural language processing technology to analyze text, extract key points, and generate a summary.

[0483] "Real-time" refers to a state in which processing is almost instantaneous and results are reflected without delay.

[0484] "User terminal" refers to a device operated by a user to receive and display information, and specifically refers to a smartphone or head-mounted display.

[0485] To implement this invention, a system is constructed using a server, a smartphone, a head-mounted display, and specific software.

[0486] Hardware and software used

[0487] Hardware: Smartphone (iOS / Android), Head-Mounted Display (HMD)

[0488] software:

[0489] Backend: Node.js, Express.js

[0490] Database: MongoDB

[0491] Frontend: React Native (for smartphones), Unity (for HMD)

[0492] API: SNS service API (acquiring trending keywords), news service API (acquiring news articles)

[0493] NLP: Generative AI model (OpenAI GPT-3)

[0494] System Operation

[0495] The server obtains trending keywords at regular intervals using the API of the SNS service, and extracts important keywords from the obtained trending list using the API authentication information.

[0496] The server then uses the API of the news service to collect relevant news articles based on the trending keywords it has acquired. This collection is done from multiple reliable news sources, and the acquired news articles are stored in the server's database.

[0497] The collected news articles are summarized using a generative AI model that analyzes the key points of the news article and generates a summary text.

[0498] The user's device (smartphone or head-mounted display) receives and displays summarized news articles from the server in real time. The interface for smartphones is built using React Native, and the interface for HMDs is built using Unity.

[0499] Specific examples

[0500] For example, if "new virus" becomes a trending topic on a particular social networking service, the server obtains the trending keyword "new virus" from the social networking service's API. Next, the server collects related news articles from news providers based on the obtained keyword "new virus." If the collected news article states that "the number of people infected with the new virus is rapidly increasing," the news article is summarized using a generative AI model, and a summary is generated stating, "The number of infected people is rapidly increasing." This summary is then distributed from the server to the user's device in real time.

[0501] Prompt Sentence Examples

[0502] Summarize the following news article:

[0503] The number of people infected with the new virus is rapidly increasing. New countermeasures are needed, and governments around the world are scrambling to implement them. Vaccine development is also progressing at a rapid pace.

[0504] summary:

[0505] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0506] Step 1:

[0507] The server obtains trending keywords at specific time intervals using the API of the SNS service. At this time, the server accesses the API using pre-configured API authentication information to obtain a trending list. The input is raw data from the API of the SNS service, and the output is a list of the obtained trending keywords.

[0508] Step 2:

[0509] The server collects related news articles using the news service's API based on the trending keywords obtained in step 1. The server sends a query to the news service using each trending keyword, lists the obtained news articles, and stores them in a database. The input is the list of trending keywords and the raw data from the news service's API, and the output is the list of collected news articles.

[0510] Step 3:

[0511] The server uses a generative AI model to summarize the collected news articles. First, each news article is input into the generative AI model, and natural language processing techniques are used to extract key points. The server then retrieves the generated summary text and stores it in a database. The input is a list of news articles, and the output is a list of summarized text.

[0512] Step 4:

[0513] The server delivers summarized news articles to users' devices (smartphones and head-mounted displays) in real time. The server uses WebSocket to send the summary results to connected devices. The input is a list of summarized text, and the output is the summarized news article displayed on the user's device.

[0514] Step 5:

[0515] The user's device displays the summarized news article received from the server. The user interface is built using React Native for smartphones and Unity for HMDs. The input is the summary text from the server, and the output is the summarized news that the user sees on the interface.

[0516] Step 6:

[0517] Users can check the summary news delivered through the device and access detailed information as needed. Links to detailed information are displayed on the smartphone or HMD interface for easy access. The input is the displayed summary news, and the output is the viewing of the detailed page based on the user's action.

[0518] This process flow allows users to quickly obtain the latest trend information summarized in real time and access the information they need.

[0519] 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.

[0520] As an embodiment of the present invention, a system is constructed and operated in the following manner.

[0521] 1. Obtaining trending keywords

[0522] The server periodically obtains trending keywords using the API of the SNS service at specific time intervals. To do this, the server sets API authentication information for the SNS service in advance and obtains a trending list by accessing the API. Keywords recognized as trending are extracted from this list.

[0523] 2. Collecting relevant news articles

[0524] The server uses the API of the news service to collect related news articles based on the acquired trending keywords. The server sends queries to the news service and stores the contents of related news articles in a list. This collection is done from multiple news sources, with the aim of collecting reliable articles.

[0525] 3. News article summaries

[0526] The server summarizes the content of collected news articles using a generative AI model (e.g., a natural language processing algorithm). For each news article, the generative AI model is applied to generate a short summary that extracts the key points.

[0527] 4. Recognition of user emotions using an emotion engine

[0528] The server uses an emotion engine to recognize the user's emotions. This emotion recognition is performed by analyzing input data (e.g., text, facial expression recognition, and voice tone) when the user operates the device. The analyzed user's emotions are used to deliver news articles.

[0529] 5. Delivery and customization of summary results

[0530] The server customizes the generated summary based on the user's emotions and delivers it to the user's device. For example, if the user is feeling stressed, positive news can be prioritized. This makes it possible to provide appropriate information according to the user's emotional state.

[0531] Specific examples

[0532] For example, let's say "pandemic" becomes a trending topic on a particular social media service.

[0533] 1. The server retrieves the trending keyword "pandemic" from the API of a social networking service.

[0534] 2. The server collects relevant news articles from a news service based on the acquired keyword "pandemic." It calls the news service API and retrieves multiple news articles.

[0535] 3. The server uses a generative AI model to summarize the collected news articles. For example, if the article says, "The pandemic is having widespread impacts," the generated summary will be, "The impact is widespread."

[0536] 4. The server uses the emotion engine to analyze the user's emotions. For example, if the user is feeling anxious, the server performs the next step based on this emotion information.

[0537] 5. When delivering summarized news articles to the user's device, the server customizes them based on the user's emotions. For example, it prioritizes articles containing positive news or countermeasures.

[0538] This allows users to quickly and easily grasp detailed information related to trending keywords while receiving news that matches their emotional state. The system of the present invention saves users the trouble of gathering information, enables them to understand the content of topics in real time, and provides information that takes into consideration the user's emotions.

[0539] The processing flow will be explained below.

[0540] Step 1:

[0541] The server periodically obtains trending keywords using the API of the social networking service. To do this, the server sets the API authentication information of the social networking service in advance and obtains a trending list by accessing the API. This list contains keywords that many people are currently interested in.

[0542] Step 2:

[0543] The server analyzes the acquired trend keyword information and categorizes it as necessary. Categorization can be divided into global trends, trends in specific regions, etc. This categorization makes it possible to provide information based on the user's interests.

[0544] Step 3:

[0545] The server uses the API of the news service to collect related news articles based on the classified trending keywords. The server sends a query to the API for each keyword to obtain the content of related news articles. This collection is done from multiple news sources, with the aim of collecting reliable articles.

[0546] Step 4:

[0547] The server uses a generative AI model to summarize the contents of collected news articles. Specifically, it uses natural language processing technology to extract key points from each article and convert them into a shortened text. For example, from an article titled "The pandemic has had widespread impacts," it generates a summary that reads "The impact is widespread."

[0548] Step 5:

[0549] The server uses an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's input data (e.g., keyboard input on a computer, touch operation on a smartphone, voice input, etc.) and facial expression data obtained through a facial recognition camera. This analysis identifies the user's current emotional state.

[0550] Step 6:

[0551] The server customizes the summarized news articles based on the analyzed user sentiment: for example, if the user is feeling anxious, it will prioritize articles that contain positive news or reassuring elements.

[0552] Step 7:

[0553] The server delivers the customized summary results to the user's device. The server communicates with each user's device and sends the summarized news article in an appropriate format (e.g., notification or display in a dashboard).

[0554] Step 8:

[0555] The user's device then displays the summaries it receives. The device reads the summarized news articles and displays them in a user-friendly format, allowing the user to quickly get up to speed on the latest and most important information about trending keywords.

[0556] Step 9:

[0557] Users can view the summary and access the original news article if they need more information, making it easy for users to get more information about a particular trend.

[0558] By implementing the above steps, the system can efficiently provide users with trend information. Furthermore, by recognizing the user's emotions and customizing the information provided, more appropriate and user-friendly information can be provided.

[0559] Example 2

[0560] 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."

[0561] In modern society, a vast amount of information exists on the Internet, making it difficult for users to quickly obtain the accurate and appropriate information they need. Furthermore, information provided is not adequately tailored to the user's emotional state and interests, which can lead to stress and confusion due to information overload. Therefore, there is a need for a system that collects appropriate information related to trending keywords, summarizes it using a generative AI model, and delivers it in a customized format according to the user's emotional state.

[0562] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0563] In this invention, the server includes means for periodically acquiring trend keywords, means for collecting related information based on the acquired trend keywords, means for summarizing the collected news information using a generative AI model, means for recognizing a user's emotion, and means for customizing and distributing the summarized news information based on the recognized user's emotion. This allows users to quickly and easily grasp detailed information related to trends and receive information that matches their own emotional state.

[0564] "Trending keywords" are keywords that are currently of great social interest or topicality and are acquired at specific time intervals.

[0565] An "information service" is a website or online platform accessible through an API that provides news or other information.

[0566] A "generative AI model" is an algorithm or system that uses artificial intelligence to generate text, summarize, or perform other natural language processing.

[0567] "User emotion" refers to the psychological state (e.g., excitement, fatigue, stress, anxiety, etc.) of the user when receiving information.

[0568] "Emotion recognition means" is a technology for analyzing the user's input data, facial expressions, tone of voice, etc. to identify the user's emotional state.

[0569] "News information" is a collective term that includes reports of a particular event or situation, including articles, video clips, and breaking news.

[0570] "Customization" is the process of tailoring information to a user's needs and emotional state, optimizing and delivering specific content.

[0571] "Summarization" is the process of extracting the key points from the original information and presenting them in a concise format.

[0572] In order to implement the present invention, a system is constructed and operated in the following manner.

[0573] First, the server periodically obtains trending keywords using the API of the SNS service. To do this, the server must be set up with the API authentication information of the SNS service in advance. For example, if Twitter is used as the SNS service, the server will access the API using the authentication information for the Twitter API and obtain trending keywords. This series of operations is performed automatically at specific time intervals.

[0574] Next, the server uses the API of the news provider to collect related news articles based on the acquired trending keywords. For example, when using the Google News API, the server generates a query based on a keyword such as "pandemic" and accesses the API to collect related news articles. The collected news articles are stored in a database.

[0575] The server summarizes the collected news articles using a generative AI model (e.g., OpenAI's GPT-3). Specifically, the server inputs the content of each news article into GPT-3, which generates a short summary that extracts the key points. An example prompt is as follows:

[0576] Summarize the news article.

[0577] Article: The impact of the pandemic is widespread. The economic impact is significant, calling for international cooperation and forcing governments to act quickly.

[0578] summary:

[0579] The summary generated is "Wide-reaching impact."

[0580] The server then uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's emotions. The server collects input data (e.g., text, facial expression recognition, and voice tone) provided by the user's device and inputs it into the emotion engine to analyze the user's emotional state. For example, it can determine that the user is feeling anxious.

[0581] Finally, the server customizes the summarized news articles based on the user's emotional state and delivers them to the user's device. For example, if the user is feeling anxious, it will prioritize articles containing positive news and information on how to cope with the situation. This allows the user to receive appropriate information tailored to their emotional state.

[0582] As described above, the present invention is a system that provides information suited to the user by collecting related information based on trend keywords, summarizing it, and further customizing it according to the user's emotional state.

[0583] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0584] System program processing flow

[0585] Step 1:

[0586] The server periodically obtains trending keywords using the API of the social networking service. First, the server accesses the social networking service using pre-configured API authentication information to obtain the latest list of trending keywords at specific time intervals. This is done by sending an API request and receiving trending keywords as a response. For example, consider the case where the server obtains the keyword "pandemic" using the Twitter API. This operation is repeated every few minutes, allowing the server to always maintain the latest trending information. The input is the API authentication information of the social networking service, and the output is the list of trending keywords.

[0587] Step 2:

[0588] The server uses the API of the news service to collect related news articles based on the acquired trending keywords. Specifically, the server uses the acquired trending keywords to send a search query to the API of the news service to collect related news articles. For example, it sends a query to the Google News API for the keyword "pandemic" to obtain related news articles. The collected news articles are stored in list format. The input is the trending keywords, and the output is a list of news articles.

[0589] Step 3:

[0590] The server summarizes the collected news articles using a generative AI model. First, the server inputs the content of each news article into a generative AI model (e.g., OpenAI's GPT-3) to generate a short summary that extracts the key points. A specific prompt is created and input into the model to obtain the summary. For example, for the news article "The impact of the pandemic is widespread. The economic impact is significant, calling for international cooperation. Governments around the world are being urged to act quickly," the prompt is set as follows:

[0591] Summarize the news article.

[0592] Article: The impact of the pandemic is widespread. The economic impact is significant, calling for international cooperation and forcing governments to act quickly.

[0593] summary:

[0594] The summary generated by this prompt is "Wide-reaching impact." The input is a news article and the output is a summary statement.

[0595] Step 4:

[0596] The server uses an emotion engine to recognize the user's emotions. The server collects input data (e.g., text, facial expression recognition, and voice tone) provided by the user's device and inputs this data into an emotion engine (e.g., IBM Watson Tone Analyzer) for analysis. For example, when a user enters a text message, the emotion engine analyzes the text and identifies the user's emotional state (e.g., anxiety, joy, anger). The input is the user's input data, and the output is the emotion analysis result.

[0597] Step 5:

[0598] The server customizes summarized news articles based on the user's emotional state and delivers them to the user's device. Based on the analyzed emotional information, the server selects the news summary that best suits each user's emotions and delivers it in a customized format. For example, if a user is feeling anxious, it will prioritize delivery of positive news and information about solutions. This allows users to receive information tailored to their emotional state. The input is a summarized news article and the results of the emotion analysis, and the output is customized news information delivered to the user.

[0599] This allows the server to provide information optimized for the user, thereby improving user satisfaction.

[0600] (Application example 2)

[0601] 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."

[0602] Currently, there are many systems that acquire and summarize trending information and related news articles and deliver them to users. However, these systems provide information uniformly without considering the user's emotional state. As a result, the information received by users may not necessarily match their current state of mind, which may increase stress and anxiety. Therefore, there is a need for information delivery that responds to the user's emotional state.

[0603] The identification process 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 periodically acquiring trend keywords, means for collecting related information based on the acquired trend keywords, means for summarizing the collected information, means for analyzing the user's emotions using an emotion analysis engine, and means for customizing the summarized information according to the user's emotions and delivering it. This makes it possible to provide information according to the user's emotional state.

[0604] "Trending keywords" are words or phrases that are trending across multiple sources over a specific time period.

[0605] "Related information" is data such as news articles and web pages collected based on trending keywords.

[0606] "Summarizing" refers to extracting the key points of the original information and converting it into a concise form.

[0607] An "emotion analysis engine" is an algorithm or software that analyzes a user's input data and determines their emotional state.

[0608] "Customization" refers to tailoring the content and presentation of information based on the user's particular requirements, particularly their emotional state.

[0609] An embodiment of the present invention is a system for enabling a user to obtain related information based on trend keywords and have it delivered in a form customized according to an emotional state. The system includes the following means.

[0610] First, the server periodically obtains trending keywords. To do this, the server uses SNS APIs to extract appropriate keywords from trending lists. The SNS APIs used include APIs of common social networking services.

[0611] Next, the server collects related information based on the acquired trending keywords from the APIs of various news providers, including a wide variety of news sources that are used as news provider APIs.

[0612] It then uses a generative AI model, which includes a natural language processing algorithm such as OpenAI GPT-4, to summarize the collected news articles. By utilizing this generative AI model, it extracts the main points of the news articles and summarizes them in a concise form that is easy for users to understand.

[0613] Furthermore, the server analyzes the user's emotions using an emotion analysis engine, such as Microsoft Azure Emotion API, which analyzes emotions from the user's input data (e.g., text, facial expressions, and voice tone).

[0614] Finally, the server customizes the summarized news articles according to the user's emotions and delivers them to the user's device. For example, if the user is feeling stressed, the server will prioritize positive news and information about relaxation based on this emotional information.

[0615] As a concrete example, let's consider the case where "pandemic" becomes a trending keyword on a social networking site. The server retrieves the keyword "pandemic" from the social networking site API and, based on this, collects related news articles from the news service API. The collected news articles are summarized using a generative AI model, and the content is summarized as "The impact of the pandemic is widespread." If the user is feeling anxious, this information is used to add positive countermeasure information and customize the message, delivering it as "The impact of the pandemic is widespread, but solutions are underway."

[0616] Examples of prompt sentences include:

[0617] import openai

[0618] import requests

[0619] from azure.ai.textanalytics import TextAnalyticsClient

[0620] from azure.core.credentials import AzureKeyCredential

[0621] Get trending keywords from SNS API

[0622] def fetch_trend_keywords(api_url, headers):

[0623] response = requests.get(api_url, headers=headers)

[0624] if response.status_code == 200:

[0625] trends = response.json()

[0626] return trends['data'][0]['trending_keywords']

[0627] else:

[0628] return []

[0629] Collecting related news articles from news service APIs

[0630] def fetch_news_articles(api_url, api_key, keyword):

[0631] params = {

[0632] 'q': keyword,

[0633] 'apiKey': api_key,

[0634] }

[0635] response = requests.get(api_url, params=params)

[0636] if response.status_code == 200:

[0637] articles = response.json()

[0638] return articles['articles']

[0639] else:

[0640] return []

[0641] Summarizing news articles with generative AI models

[0642] def summarize_article(article_text, model="text-davinci-003"):

[0643] response = openai.Completion.create(

[0644] engine=model,

[0645] prompt=f"Please summarize the following news article: {article_text}",

[0646] max_tokens=100

[0647] )

[0648] return response.choices[0].text.strip()

[0649] Recognize user emotions using an emotion engine

[0650] def analyze_user_emotion(text, endpoint, key):

[0651] client = TextAnalyticsClient(endpoint=endpoint, credential=AzureKeyCredential(key))

[0652] response = client.analyze_sentiment(documents=[text])[0]

[0653] return response.sentiment

[0654] Main Program

[0655] if __name__ == "__main__":

[0656] Get trending keywords

[0657] trend_keywords = fetch_trend_keywords("https: / / api.twitter.com / 2 / tweets / trending", headers={"Authorization": f"Bearer {twitter_bearer_token}"})

[0658] for keyword in trend_keywords:

[0659] Collect news articles

[0660] articles = fetch_news_articles("https: / / newsapi.org / v2 / everything", "your_newsapi_key", keyword)

[0661] for article in articles:

[0662] News article summaries

[0663] summary = summarize_article(article['content'])

[0664] Recognize user emotions

[0665] user_emotion = analyze_user_emotion(user_input_text, endpoint="your_endpoint", key="your_key")

[0666] News article delivery (customized based on user sentiment)

[0667] if user_emotion == 'positive':

[0668] customized_summary = f"Good News: {summary}"

[0669] elif user_emotion == 'negative':

[0670] customized_summary = f"Don't worry: we have a solution for {summary}."

[0671] else:

[0672] customized_summary = summary

[0673] View summary results

[0674] print(customized_summary)

[0675] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0676] Step 1:

[0677] The server periodically obtains trending keywords from the API of the social networking service. Specifically, it accesses the API of social networking services such as Twitter at specific time intervals to obtain a trending list. The latest trending keywords are extracted from this trending list and used as input for the next processing step. The input is the response data of the social networking service API, and the output is a list of trending keywords.

[0678] Step 2:

[0679] The server collects related information based on the acquired trend keywords. Specifically, it sends the trend keywords as queries to a news service API (e.g., NewsAPI) to retrieve related news articles. The input is the trend keywords and the response data of the news service API, and the output is a list of related news articles.

[0680] Step 3:

[0681] The server summarizes the collected news articles using a generative AI model. Specifically, the full text of each collected news article is input into OpenAI's GPT model, which generates a short summary that extracts the main points. The input is the content of the news article, and the output is the summary of the news article.

[0682] Step 4:

[0683] The server uses an emotion analysis engine to analyze the user's emotions. Specifically, it uses the Microsoft Azure Emotion API to analyze emotions based on text data, facial expressions, and voice tone entered by the user from their device. The input is the user's input data, and the output is the analyzed emotional state (e.g., positive, negative, neutral).

[0684] Step 5:

[0685] The server customizes the summarized news article according to the user's emotions. Specifically, it adjusts the content of the news article based on the analyzed emotional state. For example, if the user has negative emotions, it includes additional information that emphasizes positive aspects and solutions. This process takes the news summary and the results of the emotion analysis as input, and outputs a customized news article.

[0686] Step 6:

[0687] The server delivers customized news articles to the user's device. Specifically, the customized news articles are delivered to the user's smartphone or head-mounted display via push notifications, in-app displays, etc. The input is the customized news article, and the output is the delivery result to the user's device.

[0688] Through the above processing steps, it becomes possible to customize related information based on trend keywords according to the emotional state of the user and deliver it in an appropriate format.

[0689] 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.

[0690] 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.

[0691] 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.

[0692] [Third embodiment]

[0693] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0694] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0695] 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).

[0696] 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.

[0697] 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.

[0698] 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).

[0699] 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.

[0700] 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.

[0701] 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.

[0702] 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.

[0703] 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.

[0704] 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."

[0705] As an embodiment of the present invention, a system is constructed and operated in the following manner.

[0706] 1. Obtaining trending keywords

[0707] The server obtains trending keywords using the API of the SNS service at specific time intervals. At this time, the server accesses the API using authentication information to obtain a trending list. Keywords recognized as trending are extracted from this list.

[0708] 2. Collecting relevant news articles

[0709] The server uses the API of the news service to collect news articles related to the acquired trending keywords. The server sends a query to the news service and lists the contents of the retrieved news articles. This collection is done from multiple news sources, with the aim of collecting reliable articles.

[0710] 3. News article summaries

[0711] The server uses a generative AI model to summarize the collected news articles. Specifically, it uses natural language processing technology to extract the key points of each article and convert them into a shortened text. In this summarization method, the generative AI model analyzes the input long text and generates a short summary that contains only the information that is important to the user.

[0712] 4. Distribution of summary results

[0713] The server delivers the generated summaries to the user's device, where they are displayed, allowing the user to easily understand the latest topics. This information is delivered in real time, allowing users to quickly understand the specific content of trending keywords. Users can read summarized news about specific trends and quickly access related detailed information.

[0714] Specific examples

[0715] For example, let's consider the case where "new virus" becomes a trending topic on a particular social media service.

[0716] 1. The server obtains the trending keyword "new virus" from the API of a social networking service.

[0717] 2. The server collects related news articles from a news service based on the acquired keyword "new virus." It calls the news service API and retrieves multiple news articles.

[0718] 3. The server summarizes the collected news articles using a generative AI model. For example, if the article says, "The number of infected people due to a new virus is rapidly increasing," the generated summary will be, "The number of infected people is rapidly increasing."

[0719] 4. The server delivers the summarized news articles to the user's device, allowing the user to quickly check the summarized news about the "new virus" through the device.

[0720] This allows users to quickly and easily grasp detailed information about trends. The system of the present invention allows users to understand the content of topics in real time, eliminating the need to gather information.

[0721] The processing flow will be explained below.

[0722] Step 1:

[0723] The server periodically acquires trending keywords using the API of the SNS service. To do this, the server sets API authentication information of the SNS service in advance and accesses the API.

[0724] Step 2:

[0725] The server analyzes the acquired trend keyword information and categorizes the acquired keywords as needed, such as trends in a specific region or global trends. This categorization improves the accuracy of the information provided to users.

[0726] Step 3:

[0727] The server uses the API of the news service to collect related news articles based on the categorized trending keywords. The server sends a query to the API for each keyword to retrieve related news articles and store them in a list.

[0728] Step 4:

[0729] The server summarizes the content of collected news articles using a generative AI model (e.g., a natural language processing algorithm). For each news article, the generative AI model is applied to generate a short summary that extracts the key points.

[0730] Step 5:

[0731] The server then distributes the generated summaries to the users' devices. To do this, the server communicates with each user's device and sends the summarized news articles in an appropriate format, such as a notification or dashboard display.

[0732] Step 6:

[0733] The user's device displays the received summary. The device reads the summarized news article and displays it in a format that is easy for the user to view. The user can quickly check the summarized latest trend information through the device.

[0734] Step 7:

[0735] Users can review the summary and then access the original news article for more details, effortlessly capturing key information about a trend.

[0736] Through the above steps, the system can efficiently provide trend information to users.

[0737] Example 1

[0738] 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."

[0739] There is a lack of a way to quickly access current trending keywords and obtain summaries of related news articles in a centralized manner. While there is a need for a system that collects related news from multiple sources and automatically summarizes and provides it, the current information gathering and summarization process is decentralized, resulting in inefficiencies. Furthermore, obtaining reliable information is difficult, requiring effective management of users' time and resources.

[0740] 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.

[0741] In this invention, the server includes means for acquiring trend keywords at specific time intervals, means for collecting news articles from relevant information sources based on the acquired trend keywords, means for summarizing the collected news articles using natural language processing techniques, and means for delivering the generated summaries to a user's display device, thereby enabling the user to quickly and efficiently obtain summarized news articles related to the latest trend keywords.

[0742] A "specific time interval" is a fixed time period during which the system is set to perform an action periodically.

[0743] "Trending Keywords" are important keywords related to current trends and topics, typically obtained from social networking services and news sites.

[0744] "Source" means a website or service that provides news articles or other information.

[0745] "Natural language processing technology" refers to technology that enables computers to understand and process human language, including text analysis, summarization, and translation.

[0746] A "generative AI model" is a model that allows artificial intelligence to automatically generate sentences or create summaries from input data.

[0747] A "display device" is a device that allows a user to visually view information, such as a smartphone, tablet, or computer.

[0748] "Deliver" means that the server sends the generated data or summary to the user's terminal, and the user receives the data.

[0749] "Summarizing" means extracting the important parts from a large amount of information and summarizing the content in a concise manner.

[0750] This invention is a system consisting of a server, an information source API, a generative AI model, and a user display device. This system acquires trending keywords at specific time intervals, collects news articles based on the keywords, summarizes the collected articles, and finally delivers them to the user. A specific embodiment of this system is described in detail below.

[0751] Acquiring trending keywords

[0752] server

[0753] The server retrieves trending keywords at specific time intervals using a scheduling function. For example, trending keywords are retrieved using the API of a social networking service (e.g., SNS API). A request including authentication information is sent to the API to retrieve a list of current trending keywords. From this list, the latest trending keyword is selected.

[0754] Collecting relevant news articles

[0755] server

[0756] The server sends a query to the API of a news service (e.g., news API) based on the trending keywords it has acquired. The server sets the keywords as parameters to the API, collects related news articles from multiple sources, and creates a list of news articles by filtering out reliable information.

[0757] News article summaries

[0758] server

[0759] The server converts the collected news articles into JSON format and passes them to a generative AI model (e.g., Generative AI API). This model uses natural language processing techniques to extract key points and generate a concise summary. The generated summary is then stored in a database.

[0760] Summary results delivery

[0761] server

[0762] The server delivers the summary results to the user's display device. For example, it selects an appropriate delivery method (API, push notification, etc.) based on the information on the user's device. It then sends the summarized news article to the user's display device.

[0763] Terminal

[0764] The terminal receives the summary results sent from the server, analyzes the data, and displays it on a user interface, where the user can check the displayed summary results and use links to obtain more information.

[0765] Specific examples

[0766] For example, if "new virus" becomes a trend on a particular social networking site, the following process will occur:

[0767] 1. The server retrieves the trending keyword "new virus" from the SNS API.

[0768] 2. Based on the acquired keyword "new virus," the server calls the news API and collects related news articles.

[0769] 3. The server summarizes the collected news articles using a generative AI model. If the collected article is titled "The number of infected people due to a new virus is rapidly increasing," the generated summary will be "The number of infected people is rapidly increasing."

[0770] 4. The server delivers the generated summary to the user's device, allowing the user to quickly check the summarized news about the "new virus" through the device.

[0771] Prompt Sentence Examples

[0772] "Please summarize the latest news about the virus. Below is the full news article."

[0773] This system allows users to efficiently grasp the latest trend information.

[0774] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0775] Program processing steps

[0776] Step 1: Get trending keywords

[0777] server

[0778] 1. Input: The server has a scheduler that runs periodically and prepares authentication information for the SNS service API at that time interval.

[0779] 2. Data processing: Send a request to the API using your authentication information and receive a list of trending keywords as a response.

[0780] 3. Specific operation: Send a "GET" request to the SNS service API endpoint and include authentication information in the header.

[0781] 4. Output: The trending keyword list is obtained and new trending keywords are extracted from this list.

[0782] Step 2: Collect relevant news articles

[0783] server

[0784] 1. Input: Prepare authentication information for the news service API based on the trending keywords obtained.

[0785] 2. Data calculation: Trending keywords are set as parameters in the API request, and article data is collected from multiple sources from news providers.

[0786] 3. Specific operation: Send a "GET" request to the news service API and set authentication information including the API key in the header.

[0787] 4. Output: A list containing multiple news articles is obtained, and the most reliable articles are filtered and listed.

[0788] Step 3: Summarize the news article

[0789] server

[0790] 1. Input: Collected news articles are converted into JSON format and passed to the generative AI model.

[0791] 2. Data calculation: The generative AI model is fed news article data along with a prompt, and the model extracts key points and generates a summary.

[0792] 3. Specific behavior: The generative AI model is given the prompt, "Please summarize the latest news about the new virus. Below is the full news article." and then the full news article is sent.

[0793] 4. Output: Receive the generated summary sentences and store them in a database in an appropriate format.

[0794] Step 4: Delivering summary results

[0795] server

[0796] 1. Input: Obtain the summary results stored in the database and the user's device information.

[0797] 2. Data calculation: To send the summary results to the user's device, the optimal delivery method is selected based on the user's device information (e.g., via API, push notification, etc.).

[0798] 3. Specific operation: Send an HTTP POST request to the user's device and send the summary results in JSON format.

[0799] 4. Output: The summarized news article is delivered to the user's device.

[0800] Terminal

[0801] 1. Input: Receives the summary results sent from the server.

[0802] 2. Data processing: Parse the JSON data and display it in the user interface.

[0803] 3. Specific operation: Parse the JSON data and display the summary results appropriately on the screen.

[0804] 4. Output: The summary results are ready for the user to review.

[0805] Step 5: Review summary results

[0806] User

[0807] 1. Input: Check the summary results displayed on the terminal.

[0808] 2. Specific action: Access detailed information by tapping or clicking on the summary results displayed on the device.

[0809] 3. Output: Users can see a concise summary of the latest trending information and quickly access more detailed information.

[0810] (Application example 1)

[0811] 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."

[0812] In today's society, it is difficult for users to quickly grasp the latest trend information from the vast amount of information available on the Internet. Furthermore, because news articles cover a wide range of topics, users need to be able to grasp the key points in a short amount of time. Furthermore, users want to be able to receive summaries of news in real time, no matter where they are. New technologies are needed to solve these problems.

[0813] 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.

[0814] In this invention, the server includes means for periodically acquiring trend keywords, means for collecting news articles related to the acquired trend keywords, and means for summarizing the collected news articles, thereby enabling users to receive summarized news in real time using a smartphone or head-mounted display and quickly grasp the latest information.

[0815] "Trending keywords" refer to keywords obtained from SNS services at specific time intervals that are of interest to many users at that time.

[0816] A "news article" refers to a piece of text that contains information about a particular event or topic, collected from a news service.

[0817] A "generative AI model" refers to an artificial intelligence model that uses natural language processing technology to analyze text, extract key points, and generate a summary.

[0818] "Real-time" refers to a state in which processing is almost instantaneous and results are reflected without delay.

[0819] "User terminal" refers to a device operated by a user to receive and display information, and specifically refers to a smartphone or head-mounted display.

[0820] To implement this invention, a system is constructed using a server, a smartphone, a head-mounted display, and specific software.

[0821] Hardware and software used

[0822] Hardware: Smartphone (iOS / Android), Head-Mounted Display (HMD)

[0823] software:

[0824] Backend: Node.js, Express.js

[0825] Database: MongoDB

[0826] Frontend: React Native (for smartphones), Unity (for HMD)

[0827] API: SNS service API (acquiring trending keywords), news service API (acquiring news articles)

[0828] NLP: Generative AI model (OpenAI GPT-3)

[0829] System Operation

[0830] The server obtains trending keywords at regular intervals using the API of the SNS service, and extracts important keywords from the obtained trending list using the API authentication information.

[0831] The server then uses the API of the news service to collect relevant news articles based on the trending keywords it has acquired. This collection is done from multiple reliable news sources, and the acquired news articles are stored in the server's database.

[0832] The collected news articles are summarized using a generative AI model that analyzes the key points of the news article and generates a summary text.

[0833] The user's device (smartphone or head-mounted display) receives and displays summarized news articles from the server in real time. The interface for smartphones is built using React Native, and the interface for HMDs is built using Unity.

[0834] Specific examples

[0835] For example, if "new virus" becomes a trending topic on a particular social networking service, the server obtains the trending keyword "new virus" from the social networking service's API. Next, the server collects related news articles from news providers based on the obtained keyword "new virus." If the collected news article states that "the number of people infected with the new virus is rapidly increasing," the news article is summarized using a generative AI model, and a summary is generated stating, "The number of infected people is rapidly increasing." This summary is then distributed from the server to the user's device in real time.

[0836] Prompt Sentence Examples

[0837] Summarize the following news article:

[0838] The number of people infected with the new virus is rapidly increasing. New countermeasures are needed, and governments around the world are scrambling to implement them. Vaccine development is also progressing at a rapid pace.

[0839] summary:

[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 obtains trending keywords at specific time intervals using the API of the SNS service. At this time, the server accesses the API using pre-configured API authentication information to obtain a trending list. The input is raw data from the API of the SNS service, and the output is a list of the obtained trending keywords.

[0843] Step 2:

[0844] The server collects related news articles using the news service's API based on the trending keywords obtained in step 1. The server sends a query to the news service using each trending keyword, lists the obtained news articles, and stores them in a database. The input is the list of trending keywords and the raw data from the news service's API, and the output is the list of collected news articles.

[0845] Step 3:

[0846] The server uses a generative AI model to summarize the collected news articles. First, each news article is input into the generative AI model, and natural language processing techniques are used to extract key points. The server then retrieves the generated summary text and stores it in a database. The input is a list of news articles, and the output is a list of summarized text.

[0847] Step 4:

[0848] The server delivers summarized news articles to users' devices (smartphones and head-mounted displays) in real time. The server uses WebSocket to send the summary results to connected devices. The input is a list of summarized text, and the output is the summarized news article displayed on the user's device.

[0849] Step 5:

[0850] The user's device displays the summarized news article received from the server. The user interface is built using React Native for smartphones and Unity for HMDs. The input is the summary text from the server, and the output is the summarized news that the user sees on the interface.

[0851] Step 6:

[0852] Users can check the summary news delivered through the device and access detailed information as needed. Links to detailed information are displayed on the smartphone or HMD interface for easy access. The input is the displayed summary news, and the output is the viewing of the detailed page based on the user's action.

[0853] This process flow allows users to quickly obtain the latest trend information summarized in real time and access the information they need.

[0854] 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.

[0855] As an embodiment of the present invention, a system is constructed and operated in the following manner.

[0856] 1. Obtaining trending keywords

[0857] The server periodically obtains trending keywords using the API of the SNS service at specific time intervals. To do this, the server sets API authentication information for the SNS service in advance and obtains a trending list by accessing the API. Keywords recognized as trending are extracted from this list.

[0858] 2. Collecting relevant news articles

[0859] The server uses the API of the news service to collect related news articles based on the acquired trending keywords. The server sends queries to the news service and stores the contents of related news articles in a list. This collection is done from multiple news sources, with the aim of collecting reliable articles.

[0860] 3. News article summaries

[0861] The server summarizes the content of collected news articles using a generative AI model (e.g., a natural language processing algorithm). For each news article, the generative AI model is applied to generate a short summary that extracts the key points.

[0862] 4. Recognition of user emotions using an emotion engine

[0863] The server uses an emotion engine to recognize the user's emotions. This emotion recognition is performed by analyzing input data (e.g., text, facial expression recognition, and voice tone) when the user operates the device. The analyzed user's emotions are used to deliver news articles.

[0864] 5. Delivery and customization of summary results

[0865] The server customizes the generated summary based on the user's emotions and delivers it to the user's device. For example, if the user is feeling stressed, positive news can be prioritized. This makes it possible to provide appropriate information according to the user's emotional state.

[0866] Specific examples

[0867] For example, let's say "pandemic" becomes a trending topic on a particular social media service.

[0868] 1. The server retrieves the trending keyword "pandemic" from the API of a social networking service.

[0869] 2. The server collects relevant news articles from a news service based on the acquired keyword "pandemic." It calls the news service API and retrieves multiple news articles.

[0870] 3. The server uses a generative AI model to summarize the collected news articles. For example, if the article says, "The pandemic is having widespread impacts," the generated summary will be, "The impact is widespread."

[0871] 4. The server uses the emotion engine to analyze the user's emotions. For example, if the user is feeling anxious, the server performs the next step based on this emotion information.

[0872] 5. When delivering summarized news articles to the user's device, the server customizes them based on the user's emotions. For example, it prioritizes articles containing positive news or countermeasures.

[0873] This allows users to quickly and easily grasp detailed information related to trending keywords while receiving news that matches their emotional state. The system of the present invention saves users the trouble of gathering information, enables them to understand the content of topics in real time, and provides information that takes into consideration the user's emotions.

[0874] The processing flow will be explained below.

[0875] Step 1:

[0876] The server periodically obtains trending keywords using the API of the social networking service. To do this, the server sets the API authentication information of the social networking service in advance and obtains a trending list by accessing the API. This list contains keywords that many people are currently interested in.

[0877] Step 2:

[0878] The server analyzes the acquired trend keyword information and categorizes it as necessary. Categorization can be divided into global trends, trends in specific regions, etc. This categorization makes it possible to provide information based on the user's interests.

[0879] Step 3:

[0880] The server uses the API of the news service to collect related news articles based on the classified trending keywords. The server sends a query to the API for each keyword to obtain the content of related news articles. This collection is done from multiple news sources, with the aim of collecting reliable articles.

[0881] Step 4:

[0882] The server uses a generative AI model to summarize the contents of collected news articles. Specifically, it uses natural language processing technology to extract key points from each article and convert them into a shortened text. For example, from an article titled "The pandemic has had widespread impacts," it generates a summary that reads "The impact is widespread."

[0883] Step 5:

[0884] The server uses an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's input data (e.g., keyboard input on a computer, touch operation on a smartphone, voice input, etc.) and facial expression data obtained through a facial recognition camera. This analysis identifies the user's current emotional state.

[0885] Step 6:

[0886] The server customizes the summarized news articles based on the analyzed user sentiment: for example, if the user is feeling anxious, it will prioritize articles that contain positive news or reassuring elements.

[0887] Step 7:

[0888] The server delivers the customized summary results to the user's device. The server communicates with each user's device and sends the summarized news article in an appropriate format (e.g., notification or display in a dashboard).

[0889] Step 8:

[0890] The user's device then displays the summaries it receives. The device reads the summarized news articles and displays them in a user-friendly format, allowing the user to quickly get up to speed on the latest and most important information about trending keywords.

[0891] Step 9:

[0892] Users can view the summary and access the original news article if they need more information, making it easy for users to get more information about a particular trend.

[0893] By implementing the above steps, the system can efficiently provide users with trend information. Furthermore, by recognizing the user's emotions and customizing the information provided, more appropriate and user-friendly information can be provided.

[0894] Example 2

[0895] 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."

[0896] In modern society, a vast amount of information exists on the Internet, making it difficult for users to quickly obtain the accurate and appropriate information they need. Furthermore, information provided is not adequately tailored to the user's emotional state and interests, which can lead to stress and confusion due to information overload. Therefore, there is a need for a system that collects appropriate information related to trending keywords, summarizes it using a generative AI model, and delivers it in a customized format according to the user's emotional state.

[0897] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0898] In this invention, the server includes means for periodically acquiring trend keywords, means for collecting related information based on the acquired trend keywords, means for summarizing the collected news information using a generative AI model, means for recognizing a user's emotion, and means for customizing and distributing the summarized news information based on the recognized user's emotion. This allows users to quickly and easily grasp detailed information related to trends and receive information that matches their own emotional state.

[0899] "Trending keywords" are keywords that are currently of great social interest or topicality and are acquired at specific time intervals.

[0900] An "information service" is a website or online platform accessible through an API that provides news or other information.

[0901] A "generative AI model" is an algorithm or system that uses artificial intelligence to generate text, summarize, or perform other natural language processing.

[0902] "User emotion" refers to the psychological state (e.g., excitement, fatigue, stress, anxiety, etc.) of the user when receiving information.

[0903] "Emotion recognition means" is a technology for analyzing the user's input data, facial expressions, tone of voice, etc. to identify the user's emotional state.

[0904] "News information" is a collective term that includes reports of a particular event or situation, including articles, video clips, and breaking news.

[0905] "Customization" is the process of tailoring information to a user's needs and emotional state, optimizing and delivering specific content.

[0906] "Summarization" is the process of extracting the key points from the original information and presenting them in a concise format.

[0907] In order to implement the present invention, a system is constructed and operated in the following manner.

[0908] First, the server periodically obtains trending keywords using the API of the SNS service. To do this, the server must be set up with the API authentication information of the SNS service in advance. For example, if Twitter is used as the SNS service, the server will access the API using the authentication information for the Twitter API and obtain trending keywords. This series of operations is performed automatically at specific time intervals.

[0909] Next, the server uses the API of the news provider to collect related news articles based on the acquired trending keywords. For example, when using the Google News API, the server generates a query based on a keyword such as "pandemic" and accesses the API to collect related news articles. The collected news articles are stored in a database.

[0910] The server summarizes the collected news articles using a generative AI model (e.g., OpenAI's GPT-3). Specifically, the server inputs the content of each news article into GPT-3, which generates a short summary that extracts the key points. An example prompt is as follows:

[0911] Summarize the news article.

[0912] Article: The impact of the pandemic is widespread. The economic impact is significant, calling for international cooperation and forcing governments to act quickly.

[0913] summary:

[0914] The summary generated is "Wide-reaching impact."

[0915] The server then uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's emotions. The server collects input data (e.g., text, facial expression recognition, and voice tone) provided by the user's device and inputs it into the emotion engine to analyze the user's emotional state. For example, it can determine that the user is feeling anxious.

[0916] Finally, the server customizes the summarized news articles based on the user's emotional state and delivers them to the user's device. For example, if the user is feeling anxious, it will prioritize articles containing positive news and information on how to cope with the situation. This allows the user to receive appropriate information tailored to their emotional state.

[0917] As described above, the present invention is a system that provides information suited to the user by collecting related information based on trend keywords, summarizing it, and further customizing it according to the user's emotional state.

[0918] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0919] System program processing flow

[0920] Step 1:

[0921] The server periodically obtains trending keywords using the API of the social networking service. First, the server accesses the social networking service using pre-configured API authentication information to obtain the latest list of trending keywords at specific time intervals. This is done by sending an API request and receiving trending keywords as a response. For example, consider the case where the server obtains the keyword "pandemic" using the Twitter API. This operation is repeated every few minutes, allowing the server to always maintain the latest trending information. The input is the API authentication information of the social networking service, and the output is the list of trending keywords.

[0922] Step 2:

[0923] The server uses the API of the news service to collect related news articles based on the acquired trending keywords. Specifically, the server uses the acquired trending keywords to send a search query to the API of the news service to collect related news articles. For example, it sends a query to the Google News API for the keyword "pandemic" to obtain related news articles. The collected news articles are stored in list format. The input is the trending keywords, and the output is a list of news articles.

[0924] Step 3:

[0925] The server summarizes the collected news articles using a generative AI model. First, the server inputs the content of each news article into a generative AI model (e.g., OpenAI's GPT-3) to generate a short summary that extracts the key points. A specific prompt is created and input into the model to obtain the summary. For example, for the news article "The impact of the pandemic is widespread. The economic impact is significant, calling for international cooperation. Governments around the world are being urged to act quickly," the prompt is set as follows:

[0926] Summarize the news article.

[0927] Article: The impact of the pandemic is widespread. The economic impact is significant, calling for international cooperation and forcing governments to act quickly.

[0928] summary:

[0929] The summary generated by this prompt is "Wide-reaching impact." The input is a news article and the output is a summary statement.

[0930] Step 4:

[0931] The server uses an emotion engine to recognize the user's emotions. The server collects input data (e.g., text, facial expression recognition, and voice tone) provided by the user's device and inputs this data into an emotion engine (e.g., IBM Watson Tone Analyzer) for analysis. For example, when a user enters a text message, the emotion engine analyzes the text and identifies the user's emotional state (e.g., anxiety, joy, anger). The input is the user's input data, and the output is the emotion analysis result.

[0932] Step 5:

[0933] The server customizes summarized news articles based on the user's emotional state and delivers them to the user's device. Based on the analyzed emotional information, the server selects the news summary that best suits each user's emotions and delivers it in a customized format. For example, if a user is feeling anxious, it will prioritize delivery of positive news and information about solutions. This allows users to receive information tailored to their emotional state. The input is a summarized news article and the results of the emotion analysis, and the output is customized news information delivered to the user.

[0934] This allows the server to provide information optimized for the user, thereby improving user satisfaction.

[0935] (Application example 2)

[0936] 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."

[0937] Currently, there are many systems that acquire and summarize trending information and related news articles and deliver them to users. However, these systems provide information uniformly without considering the user's emotional state. As a result, the information received by users may not necessarily match their current state of mind, which may increase stress and anxiety. Therefore, there is a need for information delivery that responds to the user's emotional state.

[0938] The identification process 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 periodically acquiring trend keywords, means for collecting related information based on the acquired trend keywords, means for summarizing the collected information, means for analyzing the user's emotions using an emotion analysis engine, and means for customizing the summarized information according to the user's emotions and delivering it. This makes it possible to provide information according to the user's emotional state.

[0939] "Trending keywords" are words or phrases that are trending across multiple sources over a specific time period.

[0940] "Related information" is data such as news articles and web pages collected based on trending keywords.

[0941] "Summarizing" refers to extracting the key points of the original information and converting it into a concise form.

[0942] An "emotion analysis engine" is an algorithm or software that analyzes a user's input data and determines their emotional state.

[0943] "Customization" refers to tailoring the content and presentation of information based on the user's particular requirements, particularly their emotional state.

[0944] An embodiment of the present invention is a system for enabling a user to obtain related information based on trend keywords and have it delivered in a form customized according to an emotional state. The system includes the following means.

[0945] First, the server periodically obtains trending keywords. To do this, the server uses SNS APIs to extract appropriate keywords from trending lists. The SNS APIs used include APIs of common social networking services.

[0946] Next, the server collects related information based on the acquired trending keywords from the APIs of various news providers, including a wide variety of news sources that are used as news provider APIs.

[0947] It then uses a generative AI model, which includes a natural language processing algorithm such as OpenAI GPT-4, to summarize the collected news articles. By utilizing this generative AI model, it extracts the main points of the news articles and summarizes them in a concise form that is easy for users to understand.

[0948] Furthermore, the server analyzes the user's emotions using an emotion analysis engine, such as Microsoft Azure Emotion API, which analyzes emotions from the user's input data (e.g., text, facial expressions, and voice tone).

[0949] Finally, the server customizes the summarized news articles according to the user's emotions and delivers them to the user's device. For example, if the user is feeling stressed, the server will prioritize positive news and information about relaxation based on this emotional information.

[0950] As a concrete example, let's consider the case where "pandemic" becomes a trending keyword on a social networking site. The server retrieves the keyword "pandemic" from the social networking site API and, based on this, collects related news articles from the news service API. The collected news articles are summarized using a generative AI model, and the content is summarized as "The impact of the pandemic is widespread." If the user is feeling anxious, this information is used to add positive countermeasure information and customize the message, delivering it as "The impact of the pandemic is widespread, but solutions are underway."

[0951] Examples of prompt sentences include:

[0952] import openai

[0953] import requests

[0954] from azure.ai.textanalytics import TextAnalyticsClient

[0955] from azure.core.credentials import AzureKeyCredential

[0956] Get trending keywords from SNS API

[0957] def fetch_trend_keywords(api_url, headers):

[0958] response = requests.get(api_url, headers=headers)

[0959] if response.status_code == 200:

[0960] trends = response.json()

[0961] return trends['data'][0]['trending_keywords']

[0962] else:

[0963] return []

[0964] Collecting related news articles from news service APIs

[0965] def fetch_news_articles(api_url, api_key, keyword):

[0966] params = {

[0967] 'q': keyword,

[0968] 'apiKey': api_key,

[0969] }

[0970] response = requests.get(api_url, params=params)

[0971] if response.status_code == 200:

[0972] articles = response.json()

[0973] return articles['articles']

[0974] else:

[0975] return []

[0976] Summarizing news articles with generative AI models

[0977] def summarize_article(article_text, model="text-davinci-003"):

[0978] response = openai.Completion.create(

[0979] engine=model,

[0980] prompt=f"Please summarize the following news article: {article_text}",

[0981] max_tokens=100

[0982] )

[0983] return response.choices[0].text.strip()

[0984] Recognize user emotions using an emotion engine

[0985] def analyze_user_emotion(text, endpoint, key):

[0986] client = TextAnalyticsClient(endpoint=endpoint, credential=AzureKeyCredential(key))

[0987] response = client.analyze_sentiment(documents=[text])[0]

[0988] return response.sentiment

[0989] Main Program

[0990] if __name__ == "__main__":

[0991] Get trending keywords

[0992] trend_keywords = fetch_trend_keywords("https: / / api.twitter.com / 2 / tweets / trending", headers={"Authorization": f"Bearer {twitter_bearer_token}"})

[0993] for keyword in trend_keywords:

[0994] Collect news articles

[0995] articles = fetch_news_articles("https: / / newsapi.org / v2 / everything", "your_newsapi_key", keyword)

[0996] for article in articles:

[0997] News article summaries

[0998] summary = summarize_article(article['content'])

[0999] Recognize user emotions

[1000] user_emotion = analyze_user_emotion(user_input_text, endpoint="your_endpoint", key="your_key")

[1001] News article delivery (customized based on user sentiment)

[1002] if user_emotion == 'positive':

[1003] customized_summary = f"Good News: {summary}"

[1004] elif user_emotion == 'negative':

[1005] customized_summary = f"Don't worry: we have a solution for {summary}."

[1006] else:

[1007] customized_summary = summary

[1008] View summary results

[1009] print(customized_summary)

[1010] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1011] Step 1:

[1012] The server periodically obtains trending keywords from the API of the social networking service. Specifically, it accesses the API of social networking services such as Twitter at specific time intervals to obtain a trending list. The latest trending keywords are extracted from this trending list and used as input for the next processing step. The input is the response data of the social networking service API, and the output is a list of trending keywords.

[1013] Step 2:

[1014] The server collects related information based on the acquired trend keywords. Specifically, it sends the trend keywords as queries to a news service API (e.g., NewsAPI) to retrieve related news articles. The input is the trend keywords and the response data of the news service API, and the output is a list of related news articles.

[1015] Step 3:

[1016] The server summarizes the collected news articles using a generative AI model. Specifically, the full text of each collected news article is input into OpenAI's GPT model, which generates a short summary that extracts the main points. The input is the content of the news article, and the output is the summary of the news article.

[1017] Step 4:

[1018] The server uses an emotion analysis engine to analyze the user's emotions. Specifically, it uses the Microsoft Azure Emotion API to analyze emotions based on text data, facial expressions, and voice tone entered by the user from their device. The input is the user's input data, and the output is the analyzed emotional state (e.g., positive, negative, neutral).

[1019] Step 5:

[1020] The server customizes the summarized news article according to the user's emotions. Specifically, it adjusts the content of the news article based on the analyzed emotional state. For example, if the user has negative emotions, it includes additional information that emphasizes positive aspects and solutions. This process takes the news summary and the results of the emotion analysis as input, and outputs a customized news article.

[1021] Step 6:

[1022] The server delivers customized news articles to the user's device. Specifically, the customized news articles are delivered to the user's smartphone or head-mounted display via push notifications, in-app displays, etc. The input is the customized news article, and the output is the delivery result to the user's device.

[1023] Through the above processing steps, it becomes possible to customize related information based on trend keywords according to the emotional state of the user and deliver it in an appropriate format.

[1024] 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.

[1025] 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.

[1026] 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.

[1027] [Fourth embodiment]

[1028] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1029] 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.

[1030] 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).

[1031] 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.

[1032] 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.

[1033] 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).

[1034] 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.

[1035] 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.

[1036] 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.

[1037] 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.

[1038] 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.

[1039] 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.

[1040] 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."

[1041] As an embodiment of the present invention, a system is constructed and operated in the following manner.

[1042] 1. Obtaining trending keywords

[1043] The server obtains trending keywords using the API of the SNS service at specific time intervals. At this time, the server accesses the API using authentication information to obtain a trending list. Keywords recognized as trending are extracted from this list.

[1044] 2. Collecting relevant news articles

[1045] The server uses the API of the news service to collect news articles related to the acquired trending keywords. The server sends a query to the news service and lists the contents of the retrieved news articles. This collection is done from multiple news sources, with the aim of collecting reliable articles.

[1046] 3. News article summaries

[1047] The server uses a generative AI model to summarize the collected news articles. Specifically, it uses natural language processing technology to extract the key points of each article and convert them into a shortened text. In this summarization method, the generative AI model analyzes the input long text and generates a short summary that contains only the information that is important to the user.

[1048] 4. Distribution of summary results

[1049] The server delivers the generated summaries to the user's device, where they are displayed, allowing the user to easily understand the latest topics. This information is delivered in real time, allowing users to quickly understand the specific content of trending keywords. Users can read summarized news about specific trends and quickly access related detailed information.

[1050] Specific examples

[1051] For example, let's consider the case where "new virus" becomes a trending topic on a particular social media service.

[1052] 1. The server obtains the trending keyword "new virus" from the API of a social networking service.

[1053] 2. The server collects related news articles from a news service based on the acquired keyword "new virus." It calls the news service API and retrieves multiple news articles.

[1054] 3. The server summarizes the collected news articles using a generative AI model. For example, if the article says, "The number of infected people due to a new virus is rapidly increasing," the generated summary will be, "The number of infected people is rapidly increasing."

[1055] 4. The server delivers the summarized news articles to the user's device, allowing the user to quickly check the summarized news about the "new virus" through the device.

[1056] This allows users to quickly and easily grasp detailed information about trends. The system of the present invention allows users to understand the content of topics in real time, eliminating the need to gather information.

[1057] The processing flow will be explained below.

[1058] Step 1:

[1059] The server periodically acquires trending keywords using the API of the SNS service. To do this, the server sets API authentication information of the SNS service in advance and accesses the API.

[1060] Step 2:

[1061] The server analyzes the acquired trend keyword information and categorizes the acquired keywords as needed, such as trends in a specific region or global trends. This categorization improves the accuracy of the information provided to users.

[1062] Step 3:

[1063] The server uses the API of the news service to collect related news articles based on the categorized trending keywords. The server sends a query to the API for each keyword to retrieve related news articles and store them in a list.

[1064] Step 4:

[1065] The server summarizes the content of collected news articles using a generative AI model (e.g., a natural language processing algorithm). For each news article, the generative AI model is applied to generate a short summary that extracts the key points.

[1066] Step 5:

[1067] The server then distributes the generated summaries to the users' devices. To do this, the server communicates with each user's device and sends the summarized news articles in an appropriate format, such as a notification or dashboard display.

[1068] Step 6:

[1069] The user's device displays the received summary. The device reads the summarized news article and displays it in a format that is easy for the user to view. The user can quickly check the summarized latest trend information through the device.

[1070] Step 7:

[1071] Users can review the summary and then access the original news article for more details, effortlessly capturing key information about a trend.

[1072] Through the above steps, the system can efficiently provide trend information to users.

[1073] Example 1

[1074] 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."

[1075] There is a lack of a way to quickly access current trending keywords and obtain summaries of related news articles in a centralized manner. While there is a need for a system that collects related news from multiple sources and automatically summarizes and provides it, the current information gathering and summarization process is decentralized, resulting in inefficiencies. Furthermore, obtaining reliable information is difficult, requiring effective management of users' time and resources.

[1076] 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.

[1077] In this invention, the server includes means for acquiring trend keywords at specific time intervals, means for collecting news articles from relevant information sources based on the acquired trend keywords, means for summarizing the collected news articles using natural language processing techniques, and means for delivering the generated summaries to a user's display device, thereby enabling the user to quickly and efficiently obtain summarized news articles related to the latest trend keywords.

[1078] A "specific time interval" is a fixed time period during which the system is set to perform an action periodically.

[1079] "Trending Keywords" are important keywords related to current trends and topics, typically obtained from social networking services and news sites.

[1080] "Source" means a website or service that provides news articles or other information.

[1081] "Natural language processing technology" refers to technology that enables computers to understand and process human language, including text analysis, summarization, and translation.

[1082] A "generative AI model" is a model that allows artificial intelligence to automatically generate sentences or create summaries from input data.

[1083] A "display device" is a device that allows a user to visually view information, such as a smartphone, tablet, or computer.

[1084] "Deliver" means that the server sends the generated data or summary to the user's terminal, and the user receives the data.

[1085] "Summarizing" means extracting the important parts from a large amount of information and summarizing the content in a concise manner.

[1086] This invention is a system consisting of a server, an information source API, a generative AI model, and a user display device. This system acquires trending keywords at specific time intervals, collects news articles based on the keywords, summarizes the collected articles, and finally delivers them to the user. A specific embodiment of this system is described in detail below.

[1087] Acquiring trending keywords

[1088] server

[1089] The server retrieves trending keywords at specific time intervals using a scheduling function. For example, trending keywords are retrieved using the API of a social networking service (e.g., SNS API). A request including authentication information is sent to the API to retrieve a list of current trending keywords. From this list, the latest trending keyword is selected.

[1090] Collecting relevant news articles

[1091] server

[1092] The server sends a query to the API of a news service (e.g., news API) based on the trending keywords it has acquired. The server sets the keywords as parameters to the API, collects related news articles from multiple sources, and creates a list of news articles by filtering out reliable information.

[1093] News article summaries

[1094] server

[1095] The server converts the collected news articles into JSON format and passes them to a generative AI model (e.g., Generative AI API). This model uses natural language processing techniques to extract key points and generate a concise summary. The generated summary is then stored in a database.

[1096] Summary results delivery

[1097] server

[1098] The server delivers the summary results to the user's display device. For example, it selects an appropriate delivery method (API, push notification, etc.) based on the information on the user's device. It then sends the summarized news article to the user's display device.

[1099] Terminal

[1100] The terminal receives the summary results sent from the server, analyzes the data, and displays it on a user interface, where the user can check the displayed summary results and use links to obtain more information.

[1101] Specific examples

[1102] For example, if "new virus" becomes a trend on a particular social networking site, the following process will occur:

[1103] 1. The server retrieves the trending keyword "new virus" from the SNS API.

[1104] 2. Based on the acquired keyword "new virus," the server calls the news API and collects related news articles.

[1105] 3. The server summarizes the collected news articles using a generative AI model. If the collected article is titled "The number of infected people due to a new virus is rapidly increasing," the generated summary will be "The number of infected people is rapidly increasing."

[1106] 4. The server delivers the generated summary to the user's device, allowing the user to quickly check the summarized news about the "new virus" through the device.

[1107] Prompt Sentence Examples

[1108] "Please summarize the latest news about the virus. Below is the full news article."

[1109] This system allows users to efficiently grasp the latest trend information.

[1110] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1111] Program processing steps

[1112] Step 1: Get trending keywords

[1113] server

[1114] 1. Input: The server has a scheduler that runs periodically and prepares authentication information for the SNS service API at that time interval.

[1115] 2. Data processing: Send a request to the API using your authentication information and receive a list of trending keywords as a response.

[1116] 3. Specific operation: Send a "GET" request to the SNS service API endpoint and include authentication information in the header.

[1117] 4. Output: The trending keyword list is obtained and new trending keywords are extracted from this list.

[1118] Step 2: Collect relevant news articles

[1119] server

[1120] 1. Input: Prepare authentication information for the news service API based on the trending keywords obtained.

[1121] 2. Data calculation: Trending keywords are set as parameters in the API request, and article data is collected from multiple sources from news providers.

[1122] 3. Specific operation: Send a "GET" request to the news service API and set authentication information including the API key in the header.

[1123] 4. Output: A list containing multiple news articles is obtained, and the most reliable articles are filtered and listed.

[1124] Step 3: Summarize the news article

[1125] server

[1126] 1. Input: Collected news articles are converted into JSON format and passed to the generative AI model.

[1127] 2. Data calculation: The generative AI model is fed news article data along with a prompt, and the model extracts key points and generates a summary.

[1128] 3. Specific behavior: The generative AI model is given the prompt, "Please summarize the latest news about the new virus. Below is the full news article." and then the full news article is sent.

[1129] 4. Output: Receive the generated summary sentences and store them in a database in an appropriate format.

[1130] Step 4: Delivering summary results

[1131] server

[1132] 1. Input: Obtain the summary results stored in the database and the user's device information.

[1133] 2. Data calculation: To send the summary results to the user's device, the optimal delivery method is selected based on the user's device information (e.g., via API, push notification, etc.).

[1134] 3. Specific operation: Send an HTTP POST request to the user's device and send the summary results in JSON format.

[1135] 4. Output: The summarized news article is delivered to the user's device.

[1136] Terminal

[1137] 1. Input: Receives the summary results sent from the server.

[1138] 2. Data processing: Parse the JSON data and display it in the user interface.

[1139] 3. Specific operation: Parse the JSON data and display the summary results appropriately on the screen.

[1140] 4. Output: The summary results are ready for the user to review.

[1141] Step 5: Review summary results

[1142] User

[1143] 1. Input: Check the summary results displayed on the terminal.

[1144] 2. Specific action: Access detailed information by tapping or clicking on the summary results displayed on the device.

[1145] 3. Output: Users can see a concise summary of the latest trending information and quickly access more detailed information.

[1146] (Application example 1)

[1147] 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."

[1148] In today's society, it is difficult for users to quickly grasp the latest trend information from the vast amount of information available on the Internet. Furthermore, because news articles cover a wide range of topics, users need to be able to grasp the key points in a short amount of time. Furthermore, users want to be able to receive summaries of news in real time, no matter where they are. New technologies are needed to solve these problems.

[1149] 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.

[1150] In this invention, the server includes means for periodically acquiring trend keywords, means for collecting news articles related to the acquired trend keywords, and means for summarizing the collected news articles, thereby enabling users to receive summarized news in real time using a smartphone or head-mounted display and quickly grasp the latest information.

[1151] "Trending keywords" refer to keywords obtained from SNS services at specific time intervals that are of interest to many users at that time.

[1152] A "news article" refers to a piece of text that contains information about a particular event or topic, collected from a news service.

[1153] A "generative AI model" refers to an artificial intelligence model that uses natural language processing technology to analyze text, extract key points, and generate a summary.

[1154] "Real-time" refers to a state in which processing is almost instantaneous and results are reflected without delay.

[1155] "User terminal" refers to a device operated by a user to receive and display information, and specifically refers to a smartphone or head-mounted display.

[1156] To implement this invention, a system is constructed using a server, a smartphone, a head-mounted display, and specific software.

[1157] Hardware and software used

[1158] Hardware: Smartphone (iOS / Android), Head-Mounted Display (HMD)

[1159] software:

[1160] Backend: Node.js, Express.js

[1161] Database: MongoDB

[1162] Frontend: React Native (for smartphones), Unity (for HMD)

[1163] API: SNS service API (acquiring trending keywords), news service API (acquiring news articles)

[1164] NLP: Generative AI model (OpenAI GPT-3)

[1165] System Operation

[1166] The server obtains trending keywords at regular intervals using the API of the SNS service, and extracts important keywords from the obtained trending list using the API authentication information.

[1167] The server then uses the API of the news service to collect relevant news articles based on the trending keywords it has acquired. This collection is done from multiple reliable news sources, and the acquired news articles are stored in the server's database.

[1168] The collected news articles are summarized using a generative AI model that analyzes the key points of the news article and generates a summary text.

[1169] The user's device (smartphone or head-mounted display) receives and displays summarized news articles from the server in real time. The interface for smartphones is built using React Native, and the interface for HMDs is built using Unity.

[1170] Specific examples

[1171] For example, if "new virus" becomes a trending topic on a particular social networking service, the server obtains the trending keyword "new virus" from the social networking service's API. Next, the server collects related news articles from news providers based on the obtained keyword "new virus." If the collected news article states that "the number of people infected with the new virus is rapidly increasing," the news article is summarized using a generative AI model, and a summary is generated stating, "The number of infected people is rapidly increasing." This summary is then distributed from the server to the user's device in real time.

[1172] Prompt Sentence Examples

[1173] Summarize the following news article:

[1174] The number of people infected with the new virus is rapidly increasing. New countermeasures are needed, and governments around the world are scrambling to implement them. Vaccine development is also progressing at a rapid pace.

[1175] summary:

[1176] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1177] Step 1:

[1178] The server obtains trending keywords at specific time intervals using the API of the SNS service. At this time, the server accesses the API using pre-configured API authentication information to obtain a trending list. The input is raw data from the API of the SNS service, and the output is a list of the obtained trending keywords.

[1179] Step 2:

[1180] The server collects related news articles using the news service's API based on the trending keywords obtained in step 1. The server sends a query to the news service using each trending keyword, lists the obtained news articles, and stores them in a database. The input is the list of trending keywords and the raw data from the news service's API, and the output is the list of collected news articles.

[1181] Step 3:

[1182] The server uses a generative AI model to summarize the collected news articles. First, each news article is input into the generative AI model, and natural language processing techniques are used to extract key points. The server then retrieves the generated summary text and stores it in a database. The input is a list of news articles, and the output is a list of summarized text.

[1183] Step 4:

[1184] The server delivers summarized news articles to users' devices (smartphones and head-mounted displays) in real time. The server uses WebSocket to send the summary results to connected devices. The input is a list of summarized text, and the output is the summarized news article displayed on the user's device.

[1185] Step 5:

[1186] The user's device displays the summarized news article received from the server. The user interface is built using React Native for smartphones and Unity for HMDs. The input is the summary text from the server, and the output is the summarized news that the user sees on the interface.

[1187] Step 6:

[1188] Users can check the summary news delivered through the device and access detailed information as needed. Links to detailed information are displayed on the smartphone or HMD interface for easy access. The input is the displayed summary news, and the output is the viewing of the detailed page based on the user's action.

[1189] This process flow allows users to quickly obtain the latest trend information summarized in real time and access the information they need.

[1190] 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.

[1191] As an embodiment of the present invention, a system is constructed and operated in the following manner.

[1192] 1. Obtaining trending keywords

[1193] The server periodically obtains trending keywords using the API of the SNS service at specific time intervals. To do this, the server sets API authentication information for the SNS service in advance and obtains a trending list by accessing the API. Keywords recognized as trending are extracted from this list.

[1194] 2. Collecting relevant news articles

[1195] The server uses the API of the news service to collect related news articles based on the acquired trending keywords. The server sends queries to the news service and stores the contents of related news articles in a list. This collection is done from multiple news sources, with the aim of collecting reliable articles.

[1196] 3. News article summaries

[1197] The server summarizes the content of collected news articles using a generative AI model (e.g., a natural language processing algorithm). For each news article, the generative AI model is applied to generate a short summary that extracts the key points.

[1198] 4. Recognition of user emotions using an emotion engine

[1199] The server uses an emotion engine to recognize the user's emotions. This emotion recognition is performed by analyzing input data (e.g., text, facial expression recognition, and voice tone) when the user operates the device. The analyzed user's emotions are used to deliver news articles.

[1200] 5. Delivery and customization of summary results

[1201] The server customizes the generated summary based on the user's emotions and delivers it to the user's device. For example, if the user is feeling stressed, positive news can be prioritized. This makes it possible to provide appropriate information according to the user's emotional state.

[1202] Specific examples

[1203] For example, let's say "pandemic" becomes a trending topic on a particular social media service.

[1204] 1. The server retrieves the trending keyword "pandemic" from the API of a social networking service.

[1205] 2. The server collects relevant news articles from a news service based on the acquired keyword "pandemic." It calls the news service API and retrieves multiple news articles.

[1206] 3. The server uses a generative AI model to summarize the collected news articles. For example, if the article says, "The pandemic is having widespread impacts," the generated summary will be, "The impact is widespread."

[1207] 4. The server uses the emotion engine to analyze the user's emotions. For example, if the user is feeling anxious, the server performs the next step based on this emotion information.

[1208] 5. When delivering summarized news articles to the user's device, the server customizes them based on the user's emotions. For example, it prioritizes articles containing positive news or countermeasures.

[1209] This allows users to quickly and easily grasp detailed information related to trending keywords while receiving news that matches their emotional state. The system of the present invention saves users the trouble of gathering information, enables them to understand the content of topics in real time, and provides information that takes into consideration the user's emotions.

[1210] The processing flow will be explained below.

[1211] Step 1:

[1212] The server periodically obtains trending keywords using the API of the social networking service. To do this, the server sets the API authentication information of the social networking service in advance and obtains a trending list by accessing the API. This list contains keywords that many people are currently interested in.

[1213] Step 2:

[1214] The server analyzes the acquired trend keyword information and categorizes it as necessary. Categorization can be divided into global trends, trends in specific regions, etc. This categorization makes it possible to provide information based on the user's interests.

[1215] Step 3:

[1216] The server uses the API of the news service to collect related news articles based on the classified trending keywords. The server sends a query to the API for each keyword to obtain the content of related news articles. This collection is done from multiple news sources, with the aim of collecting reliable articles.

[1217] Step 4:

[1218] The server uses a generative AI model to summarize the contents of collected news articles. Specifically, it uses natural language processing technology to extract key points from each article and convert them into a shortened text. For example, from an article titled "The pandemic has had widespread impacts," it generates a summary that reads "The impact is widespread."

[1219] Step 5:

[1220] The server uses an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's input data (e.g., keyboard input on a computer, touch operation on a smartphone, voice input, etc.) and facial expression data obtained through a facial recognition camera. This analysis identifies the user's current emotional state.

[1221] Step 6:

[1222] The server customizes the summarized news articles based on the analyzed user sentiment: for example, if the user is feeling anxious, it will prioritize articles that contain positive news or reassuring elements.

[1223] Step 7:

[1224] The server delivers the customized summary results to the user's device. The server communicates with each user's device and sends the summarized news article in an appropriate format (e.g., notification or display in a dashboard).

[1225] Step 8:

[1226] The user's device then displays the summaries it receives. The device reads the summarized news articles and displays them in a user-friendly format, allowing the user to quickly get up to speed on the latest and most important information about trending keywords.

[1227] Step 9:

[1228] Users can view the summary and access the original news article if they need more information, making it easy for users to get more information about a particular trend.

[1229] By implementing the above steps, the system can efficiently provide users with trend information. Furthermore, by recognizing the user's emotions and customizing the information provided, more appropriate and user-friendly information can be provided.

[1230] Example 2

[1231] 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."

[1232] In modern society, a vast amount of information exists on the Internet, making it difficult for users to quickly obtain the accurate and appropriate information they need. Furthermore, information provided is not adequately tailored to the user's emotional state and interests, which can lead to stress and confusion due to information overload. Therefore, there is a need for a system that collects appropriate information related to trending keywords, summarizes it using a generative AI model, and delivers it in a customized format according to the user's emotional state.

[1233] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1234] In this invention, the server includes means for periodically acquiring trend keywords, means for collecting related information based on the acquired trend keywords, means for summarizing the collected news information using a generative AI model, means for recognizing a user's emotion, and means for customizing and distributing the summarized news information based on the recognized user's emotion. This allows users to quickly and easily grasp detailed information related to trends and receive information that matches their own emotional state.

[1235] "Trending keywords" are keywords that are currently of great social interest or topicality and are acquired at specific time intervals.

[1236] An "information service" is a website or online platform accessible through an API that provides news or other information.

[1237] A "generative AI model" is an algorithm or system that uses artificial intelligence to generate text, summarize, or perform other natural language processing.

[1238] "User emotion" refers to the psychological state (e.g., excitement, fatigue, stress, anxiety, etc.) of the user when receiving information.

[1239] "Emotion recognition means" is a technology for analyzing the user's input data, facial expressions, tone of voice, etc. to identify the user's emotional state.

[1240] "News information" is a collective term that includes reports of a particular event or situation, including articles, video clips, and breaking news.

[1241] "Customization" is the process of tailoring information to a user's needs and emotional state, optimizing and delivering specific content.

[1242] "Summarization" is the process of extracting the key points from the original information and presenting them in a concise format.

[1243] In order to implement the present invention, a system is constructed and operated in the following manner.

[1244] First, the server periodically obtains trending keywords using the API of the SNS service. To do this, the server must be set up with the API authentication information of the SNS service in advance. For example, if Twitter is used as the SNS service, the server will access the API using the authentication information for the Twitter API and obtain trending keywords. This series of operations is performed automatically at specific time intervals.

[1245] Next, the server uses the API of the news provider to collect related news articles based on the acquired trending keywords. For example, when using the Google News API, the server generates a query based on a keyword such as "pandemic" and accesses the API to collect related news articles. The collected news articles are stored in a database.

[1246] The server summarizes the collected news articles using a generative AI model (e.g., OpenAI's GPT-3). Specifically, the server inputs the content of each news article into GPT-3, which generates a short summary that extracts the key points. An example prompt is as follows:

[1247] Summarize the news article.

[1248] Article: The impact of the pandemic is widespread. The economic impact is significant, calling for international cooperation and forcing governments to act quickly.

[1249] summary:

[1250] The summary generated is "Wide-reaching impact."

[1251] The server then uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's emotions. The server collects input data (e.g., text, facial expression recognition, and voice tone) provided by the user's device and inputs it into the emotion engine to analyze the user's emotional state. For example, it can determine that the user is feeling anxious.

[1252] Finally, the server customizes the summarized news articles based on the user's emotional state and delivers them to the user's device. For example, if the user is feeling anxious, it will prioritize articles containing positive news and information on how to cope with the situation. This allows the user to receive appropriate information tailored to their emotional state.

[1253] As described above, the present invention is a system that provides information suited to the user by collecting related information based on trend keywords, summarizing it, and further customizing it according to the user's emotional state.

[1254] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1255] System program processing flow

[1256] Step 1:

[1257] The server periodically obtains trending keywords using the API of the social networking service. First, the server accesses the social networking service using pre-configured API authentication information to obtain the latest list of trending keywords at specific time intervals. This is done by sending an API request and receiving trending keywords as a response. For example, consider the case where the server obtains the keyword "pandemic" using the Twitter API. This operation is repeated every few minutes, allowing the server to always maintain the latest trending information. The input is the API authentication information of the social networking service, and the output is the list of trending keywords.

[1258] Step 2:

[1259] The server uses the API of the news service to collect related news articles based on the acquired trending keywords. Specifically, the server uses the acquired trending keywords to send a search query to the API of the news service to collect related news articles. For example, it sends a query to the Google News API for the keyword "pandemic" to obtain related news articles. The collected news articles are stored in list format. The input is the trending keywords, and the output is a list of news articles.

[1260] Step 3:

[1261] The server summarizes the collected news articles using a generative AI model. First, the server inputs the content of each news article into a generative AI model (e.g., OpenAI's GPT-3) to generate a short summary that extracts the key points. A specific prompt is created and input into the model to obtain the summary. For example, for the news article "The impact of the pandemic is widespread. The economic impact is significant, calling for international cooperation. Governments around the world are being urged to act quickly," the prompt is set as follows:

[1262] Summarize the news article.

[1263] Article: The impact of the pandemic is widespread. The economic impact is significant, calling for international cooperation and forcing governments to act quickly.

[1264] summary:

[1265] The summary generated by this prompt is "Wide-reaching impact." The input is a news article and the output is a summary statement.

[1266] Step 4:

[1267] The server uses an emotion engine to recognize the user's emotions. The server collects input data (e.g., text, facial expression recognition, and voice tone) provided by the user's device and inputs this data into an emotion engine (e.g., IBM Watson Tone Analyzer) for analysis. For example, when a user enters a text message, the emotion engine analyzes the text and identifies the user's emotional state (e.g., anxiety, joy, anger). The input is the user's input data, and the output is the emotion analysis result.

[1268] Step 5:

[1269] The server customizes summarized news articles based on the user's emotional state and delivers them to the user's device. Based on the analyzed emotional information, the server selects the news summary that best suits each user's emotions and delivers it in a customized format. For example, if a user is feeling anxious, it will prioritize delivery of positive news and information about solutions. This allows users to receive information tailored to their emotional state. The input is a summarized news article and the results of the emotion analysis, and the output is customized news information delivered to the user.

[1270] This allows the server to provide information optimized for the user, thereby improving user satisfaction.

[1271] (Application example 2)

[1272] 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."

[1273] Currently, there are many systems that acquire and summarize trending information and related news articles and deliver them to users. However, these systems provide information uniformly without considering the user's emotional state. As a result, the information received by users may not necessarily match their current state of mind, which may increase stress and anxiety. Therefore, there is a need for information delivery that responds to the user's emotional state.

[1274] The identification process 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 periodically acquiring trend keywords, means for collecting related information based on the acquired trend keywords, means for summarizing the collected information, means for analyzing the user's emotions using an emotion analysis engine, and means for customizing the summarized information according to the user's emotions and delivering it. This makes it possible to provide information according to the user's emotional state.

[1275] "Trending keywords" are words or phrases that are trending across multiple sources over a specific time period.

[1276] "Related information" is data such as news articles and web pages collected based on trending keywords.

[1277] "Summarizing" refers to extracting the key points of the original information and converting it into a concise form.

[1278] An "emotion analysis engine" is an algorithm or software that analyzes a user's input data and determines their emotional state.

[1279] "Customization" refers to tailoring the content and presentation of information based on the user's particular requirements, particularly their emotional state.

[1280] An embodiment of the present invention is a system for enabling a user to obtain related information based on trend keywords and have it delivered in a form customized according to an emotional state. The system includes the following means.

[1281] First, the server periodically obtains trending keywords. To do this, the server uses SNS APIs to extract appropriate keywords from trending lists. The SNS APIs used include APIs of common social networking services.

[1282] Next, the server collects related information based on the acquired trending keywords from the APIs of various news providers, including a wide variety of news sources that are used as news provider APIs.

[1283] It then uses a generative AI model, which includes a natural language processing algorithm such as OpenAI GPT-4, to summarize the collected news articles. By utilizing this generative AI model, it extracts the main points of the news articles and summarizes them in a concise form that is easy for users to understand.

[1284] Furthermore, the server analyzes the user's emotions using an emotion analysis engine, such as Microsoft Azure Emotion API, which analyzes emotions from the user's input data (e.g., text, facial expressions, and voice tone).

[1285] Finally, the server customizes the summarized news articles according to the user's emotions and delivers them to the user's device. For example, if the user is feeling stressed, the server will prioritize positive news and information about relaxation based on this emotional information.

[1286] As a concrete example, let's consider the case where "pandemic" becomes a trending keyword on a social networking site. The server retrieves the keyword "pandemic" from the social networking site API and, based on this, collects related news articles from the news service API. The collected news articles are summarized using a generative AI model, and the content is summarized as "The impact of the pandemic is widespread." If the user is feeling anxious, this information is used to add positive countermeasure information and customize the message, delivering it as "The impact of the pandemic is widespread, but solutions are underway."

[1287] Examples of prompt sentences include:

[1288] import openai

[1289] import requests

[1290] from azure.ai.textanalytics import TextAnalyticsClient

[1291] from azure.core.credentials import AzureKeyCredential

[1292] Get trending keywords from SNS API

[1293] def fetch_trend_keywords(api_url, headers):

[1294] response = requests.get(api_url, headers=headers)

[1295] if response.status_code == 200:

[1296] trends = response.json()

[1297] return trends['data'][0]['trending_keywords']

[1298] else:

[1299] return []

[1300] Collecting related news articles from news service APIs

[1301] def fetch_news_articles(api_url, api_key, keyword):

[1302] params = {

[1303] 'q': keyword,

[1304] 'apiKey': api_key,

[1305] }

[1306] response = requests.get(api_url, params=params)

[1307] if response.status_code == 200:

[1308] articles = response.json()

[1309] return articles['articles']

[1310] else:

[1311] return []

[1312] Summarizing news articles with generative AI models

[1313] def summarize_article(article_text, model="text-davinci-003"):

[1314] response = openai.Completion.create(

[1315] engine=model,

[1316] prompt=f"Please summarize the following news article: {article_text}",

[1317] max_tokens=100

[1318] )

[1319] return response.choices[0].text.strip()

[1320] Recognize user emotions using an emotion engine

[1321] def analyze_user_emotion(text, endpoint, key):

[1322] client = TextAnalyticsClient(endpoint=endpoint, credential=AzureKeyCredential(key))

[1323] response = client.analyze_sentiment(documents=[text])[0]

[1324] return response.sentiment

[1325] Main Program

[1326] if __name__ == "__main__":

[1327] Get trending keywords

[1328] trend_keywords = fetch_trend_keywords("https: / / api.twitter.com / 2 / tweets / trending", headers={"Authorization": f"Bearer {twitter_bearer_token}"})

[1329] for keyword in trend_keywords:

[1330] Collect news articles

[1331] articles = fetch_news_articles("https: / / newsapi.org / v2 / everything", "your_newsapi_key", keyword)

[1332] for article in articles:

[1333] News article summaries

[1334] summary = summarize_article(article['content'])

[1335] Recognize user emotions

[1336] user_emotion = analyze_user_emotion(user_input_text, endpoint="your_endpoint", key="your_key")

[1337] News article delivery (customized based on user sentiment)

[1338] if user_emotion == 'positive':

[1339] customized_summary = f"Good News: {summary}"

[1340] elif user_emotion == 'negative':

[1341] customized_summary = f"Don't worry: we have a solution for {summary}."

[1342] else:

[1343] customized_summary = summary

[1344] View summary results

[1345] print(customized_summary)

[1346] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1347] Step 1:

[1348] The server periodically obtains trending keywords from the API of the social networking service. Specifically, it accesses the API of social networking services such as Twitter at specific time intervals to obtain a trending list. The latest trending keywords are extracted from this trending list and used as input for the next processing step. The input is the response data of the social networking service API, and the output is a list of trending keywords.

[1349] Step 2:

[1350] The server collects related information based on the acquired trend keywords. Specifically, it sends the trend keywords as queries to a news service API (e.g., NewsAPI) to retrieve related news articles. The input is the trend keywords and the response data of the news service API, and the output is a list of related news articles.

[1351] Step 3:

[1352] The server summarizes the collected news articles using a generative AI model. Specifically, the full text of each collected news article is input into OpenAI's GPT model, which generates a short summary that extracts the main points. The input is the content of the news article, and the output is the summary of the news article.

[1353] Step 4:

[1354] The server uses an emotion analysis engine to analyze the user's emotions. Specifically, it uses the Microsoft Azure Emotion API to analyze emotions based on text data, facial expressions, and voice tone entered by the user from their device. The input is the user's input data, and the output is the analyzed emotional state (e.g., positive, negative, neutral).

[1355] Step 5:

[1356] The server customizes the summarized news article according to the user's emotions. Specifically, it adjusts the content of the news article based on the analyzed emotional state. For example, if the user has negative emotions, it includes additional information that emphasizes positive aspects and solutions. This process takes the news summary and the results of the emotion analysis as input, and outputs a customized news article.

[1357] Step 6:

[1358] The server delivers customized news articles to the user's device. Specifically, the customized news articles are delivered to the user's smartphone or head-mounted display via push notifications, in-app displays, etc. The input is the customized news article, and the output is the delivery result to the user's device.

[1359] Through the above processing steps, it becomes possible to customize related information based on trend keywords according to the emotional state of the user and deliver it in an appropriate format.

[1360] 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.

[1361] 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.

[1362] 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.

[1363] 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.

[1364] 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.

[1365] 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.

[1366] 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).

[1367] 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.

[1368] 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."

[1369] 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.

[1370] 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).

[1371] 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.

[1372] 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.

[1373] 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.

[1374] 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.

[1375] 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.

[1376] 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.

[1377] 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.

[1378] 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.

[1379] 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.

[1380] 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.

[1381] The following is further disclosed regarding the above embodiment.

[1382] (Claim 1)

[1383] A means of regularly obtaining trending keywords,

[1384] A means for collecting related news articles based on the acquired trending keywords;

[1385] a means of summarizing the collected news articles;

[1386] means for delivering summarized news articles to a user;

[1387] A system including:

[1388] (Claim 2)

[1389] 2. The system according to claim 1, further comprising means for acquiring data from a specific news service when collecting news articles based on the acquired trending keywords.

[1390] (Claim 3)

[1391] 10. The system of claim 1, wherein the means for summarizing the news article uses a generative AI model.

[1392] "Example 1"

[1393] (Claim 1)

[1394] A means of obtaining trending keywords for a specific time interval;

[1395] a means for collecting news articles from relevant sources based on the acquired trending keywords;

[1396] A means for summarizing collected news articles using natural language processing techniques;

[1397] means for delivering the generated summary to a user's display device;

[1398] A system including:

[1399] (Claim 2)

[1400] 2. The system according to claim 1, further comprising means for acquiring data from a specific information providing service when collecting news articles based on the acquired trend keywords.

[1401] (Claim 3)

[1402] 10. The system of claim 1, wherein the means for summarizing the news article uses a generative AI model.

[1403] "Application Example 1"

[1404] (Claim 1)

[1405] A means of regularly obtaining trending keywords,

[1406] A means for collecting related news articles based on the acquired trending keywords;

[1407] a means of summarizing the collected news articles;

[1408] means for delivering summarized news articles to a user's device in real time;

[1409] A means for supporting a smartphone and a head-mounted display as a user terminal;

[1410] A system including:

[1411] (Claim 2)

[1412] 2. The system according to claim 1, further comprising means for acquiring data from a specific news service when collecting news articles based on the acquired trending keywords.

[1413] (Claim 3)

[1414] 10. The system of claim 1, wherein the means for summarizing the news article uses a generative AI model.

[1415] "Example 2: Combining Emotion Engines"

[1416] (Claim 1)

[1417] A means of regularly obtaining trending keywords,

[1418] A means for collecting related information based on the acquired trending keywords;

[1419] A means for summarizing collected news information using a generative AI model; and

[1420] means for recognizing a user's emotion;

[1421] means for customizing and delivering summarized news information based on the recognized user sentiment;

[1422] A system including:

[1423] (Claim 2)

[1424] 2. The system according to claim 1, further comprising means for acquiring data from a specific information providing service when collecting news information based on the acquired trend keywords.

[1425] (Claim 3)

[1426] 2. The system according to claim 1, wherein the means for recognizing the user's emotion is means for analyzing input data from the user.

[1427] "Application example 2 when combining emotion engines"

[1428] (Claim 1)

[1429] A means of regularly obtaining trending keywords,

[1430] A means for collecting related information based on the acquired trending keywords;

[1431] a means of summarizing the collected information;

[1432] means for analyzing user emotions using a sentiment analysis engine;

[1433] A means for customizing and delivering summarized information according to the user's emotions;

[1434] A system including:

[1435] (Claim 2)

[1436] 10. The system of claim 1, further comprising means for acquiring data from multiple sources when collecting information based on the acquired trend keywords.

[1437] (Claim 3)

[1438] 10. The system of claim 1, wherein the means for summarizing information uses a generative AI model. [Explanation of symbols]

[1439] 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 regularly obtaining trending keywords, A means for collecting related news articles based on the acquired trending keywords; a means of summarizing the collected news articles; means for delivering summarized news articles to a user; A system including:

2. 2. The system according to claim 1, further comprising means for acquiring data from a specific news service when collecting news articles based on the acquired trend keywords.

3. 10. The system of claim 1, wherein the means for summarizing the news article uses a generative AI model.

Images