system

Abstract

A system is provided.SOLUTION: The system includes a means for collecting various information from the SNS, a means for analyzing the collected information and generating a news article, a means for evaluating the credibility of the generated news article, a means for predicting the future and simulating the good future and the bad future of the news, and a means for distributing the news article and a future prediction scenario to a user terminal.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] Current news media have limited speed at which they provide information, making it difficult to obtain the latest information in real time. Furthermore, the information available on social media is fragmented and its reliability is often questionable. Furthermore, current news applications lack the ability to predict future developments, making it difficult for users to prepare for future events. There is a need for a system that can solve these issues and provide fast, reliable news delivery and future predictions. [Means for solving the problem]

[0005] The present invention provides a system that collects diverse information from social media, analyzes it, and generates news articles in real time. It also provides only highly reliable information by utilizing a generative AI model and providing a means for evaluating the credibility of the collected information. Furthermore, it implements a future prediction function and simulates good and bad news scenarios, allowing users to prepare for the worst-case scenario. Specifically, the system includes a means for collecting information from social media, a means for generating articles using a generative AI model, a means for evaluating credibility, a means for simulating future scenarios, and a means for delivering this information to a user's device.

[0006] "SNS" is an abbreviation for social networking service, an online platform where users can share information and communicate in real time.

[0007] "Information collection means" refers to a system equipped with functions for collecting related posts and data from social media.

[0008] A "generative AI model" is an artificial intelligence model trained on a large dataset, and is a technology that automatically generates news articles based on collected data.

[0009] "Credibility assessment tools" are functions that include algorithms and processes that assess the reliability of collected information and generated news articles.

[0010] "Future prediction tools" refers to functions and technologies that simulate future scenarios based on existing data and news articles.

[0011] "News distribution means" refers to the function for sending and displaying generated news articles and future prediction scenarios to users' devices.

[0012] A "user terminal" is a device such as a computer, smartphone, or tablet that receives news articles and future prediction scenarios and allows users to view them. [Brief explanation of the drawings]

[0013] [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

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] This invention is a system that collects various information from social media, analyzes it, and generates news articles in real time. The system utilizes a generative AI model, has a means to evaluate the credibility of the collected information, and provides only highly reliable information. Furthermore, it predicts the future and simulates good and bad news, allowing users to prepare for the worst-case scenario.

[0035] Program processing overview

[0036] 1. Information gathering methods

[0037] The server uses social media APIs to collect various posts based on specific keywords or hashtags, including those from multiple social media platforms such as Twitter and Facebook.

[0038] 2. Creating news articles using generative AI models

[0039] The server preprocesses the collected data (denoising, normalising) and then inputs it into a generative AI model to automatically generate news articles. The generative AI model uses a large-scale language model trained with machine learning algorithms.

[0040] 3. Credibility assessment tools

[0041] The server runs a credibility assessment algorithm on the generated news articles, which calculates a credibility score for each source and selects the most credible information.

[0042] 4. Means of predicting the future

[0043] The server launches an AI model for future prediction, simulating good and bad future scenarios based on the generated news, using a time series forecasting model.

[0044] 5. News distribution methods

[0045] The server delivers the generated news articles and future prediction scenarios to the user's device, where the user can view the delivered news.

[0046] Specific operation example

[0047] 1. The user installs the dedicated app and creates an account.

[0048] 2. The server periodically uses the Twitter API to collect posts related to the keywords "earthquake" or "earthquake."

[0049] 3. The server preprocesses the collected posts and extracts important information such as epicenter information and damage reports.

[0050] 4. The server uses the generative AI model to create a news article stating, "Today's earthquake had its epicenter in XX location, and damage is concentrated in the □□ region."

[0051] 5. The server runs a credibility assessment algorithm to prioritize information from government agencies and trusted media.

[0052] 6. The server launches a future prediction AI model and generates a scenario in which prompt rescue operations are carried out as a "good future" and a scenario in which rescue operations are delayed as a "bad future."

[0053] 7. The server delivers the generated news articles and future prediction scenarios to the user's device.

[0054] 8. The device displays a news notification, which the user taps to view a detailed news article and future prediction scenarios.

[0055] Through the above process, users can not only receive reliable news in real time, but also plan their actions based on future scenarios. Compared to conventional news distribution methods, this system provides faster and more reliable information, increasing user peace of mind and convenience.

[0056] The processing flow will be explained below.

[0057] Step 1:

[0058] The server uses social media APIs to collect posts based on specific keywords or hashtags, such as "earthquake" or "earthquake," and performs real-time searches using the Twitter API or Facebook API.

[0059] Step 2:

[0060] The server preprocesses the collected posts, which includes denoising (removing spam and irrelevant posts) and normalizing (lowercasing text, removing special characters, etc.).

[0061] Step 3:

[0062] The server analyzes the preprocessed information, specifically using text mining technology to extract important information (e.g., epicenter, damage status, evacuation shelter information, etc.).

[0063] Step 4:

[0064] The server inputs the extracted information into a generative AI model, which automatically generates news articles. The generative AI model uses a large-scale language model such as GPT-4.

[0065] Step 5:

[0066] The server runs a credibility assessment algorithm on the generated news articles, weighting data from official and trusted sources to calculate a credibility score.

[0067] Step 6:

[0068] The server launches a future prediction model and simulates future scenarios based on the generated news. It simulates both good and bad futures and generates each scenario.

[0069] Step 7:

[0070] The server integrates the generated news articles with future prediction scenarios and formats them in a way that is easy for users to understand.

[0071] Step 8:

[0072] The server delivers news articles and future prediction scenarios to users' devices via push notifications, emails, and other methods.

[0073] Step 9:

[0074] The device displays a news notification to the user, which includes a brief summary and provides a link for the user to view more details.

[0075] Step 10:

[0076] Users can interact with their devices and tap on notifications to view detailed news articles and future scenarios, providing fast and reliable information about current situations and future possibilities.

[0077] Through the above steps, the present invention builds a system that simultaneously provides highly reliable news in real time and makes future predictions.

[0078] Example 1

[0079] 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."

[0080] Conventional news gathering and distribution systems lack the ability to assess the credibility of information or predict the future, which means there is a risk of providing unreliable information to users. Furthermore, the inability to quickly gather and analyze information makes it difficult to provide information in real time, which means users are unable to enjoy peace of mind and convenience.

[0081] 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.

[0082] In this invention, the server

[0083] A means of collecting various information from SNS,

[0084] means for preprocessing the collected information;

[0085] a means for inputting the preprocessed information into a generative AI model to generate news articles;

[0086] a means for assessing the credibility of the generated news articles;

[0087] A means of making future predictions and simulating good and bad news futures;

[0088] A means for delivering news articles and future prediction scenarios to a user terminal;

[0089] This allows users to receive reliable news in real time and plan optimal actions based on future scenarios.

[0090] "SNS" is an abbreviation for social networking service, an online platform that allows users to interact with each other and share information via the Internet.

[0091] "Information collection means" refers to a means for obtaining various information from social media, etc., and is a system that uses an API to automatically collect posts based on specific keywords or hashtags.

[0092] The "preprocessing means" is a means for removing noise and unnecessary data from collected information and for processing the data to standardize its format.

[0093] A "generative AI model" is a large-scale language model trained using machine learning algorithms that automatically generates news articles by inputting preprocessed data.

[0094] A "credibility assessment tool" is an algorithm that evaluates the reliability of generated news articles and is a tool for calculating the reliability score of information sources and selecting highly credible information.

[0095] A "future prediction tool" is an AI model for simulating future scenarios based on generated news, and is a tool for generating good and bad future scenarios.

[0096] The "news distribution means" is a means for transmitting the generated news articles and future prediction scenarios to the user's terminal so that the user can view them.

[0097] This invention is a system that collects various information from social media, analyzes it, and generates news articles in real time. This system utilizes a generative AI model, has a means to evaluate the credibility of the collected information, and provides only highly reliable information. Furthermore, it predicts the future and simulates good and bad news, allowing users to prepare for the worst-case scenario.

[0098] The following configuration will be described as a specific embodiment of the present invention.

[0099] 1. Information gathering methods

[0100] The server uses social media APIs to collect various posts based on specific keywords and hashtags. This collection method is implemented using Python libraries, and social media platforms include Twitter, Facebook, etc. For example, the Tweepy library is used to access the Twitter API and collect information based on keywords such as "earthquake."

[0101] 2. Data preprocessing methods

[0102] The server preprocesses the collected data, removing noise and unnecessary data and standardizing the data format. This preprocessing method includes, for example, removing non-ASCII characters from the collected tweets and standardizing the encoding to UTF-8.

[0103] 3. News article generation method

[0104] The server then inputs the preprocessed data into a generative AI model to generate a news article. This generative AI model is a large-scale language model trained using a machine learning algorithm, such as OpenAI's GPT-3. This method generates a news article such as, "Today's earthquake had its epicenter in XX location, and damage was concentrated in XX region."

[0105] 4. Credibility assessment tools

[0106] The server runs algorithms to assess the credibility of generated news articles, for example calculating a credibility score for each source and prioritizing information from government agencies and reputable media outlets.

[0107] 5. Means of predicting the future

[0108] The server launches an AI model for future prediction, simulating good and bad future scenarios based on the generated news. This future prediction method uses a time series prediction model, such as an LSTM (long short-term memory) model. Specifically, it generates a "scenario in which relief efforts are carried out quickly" and a "scenario in which relief efforts are delayed."

[0109] 6. News distribution methods

[0110] Finally, the server delivers the generated news articles and future prediction scenarios to the user's device. The device displays the received news notification, and the user can tap it to view detailed news articles and future prediction scenarios. This news delivery uses a RESTful API and employs a mechanism to send push notifications to the user's smartphone.

[0111] Prompt Sentence Examples

[0112] Examples of prompts to input to a generative AI model include:

[0113] "Generate reliable news articles based on the latest earthquake information. Include the following information: epicenter, affected areas, and local conditions. Also, generate rescue scenarios as future predictions."

[0114] With the above configuration, users can receive reliable news in real time and plan optimal actions based on future scenarios. This system provides faster and more reliable information than conventional news distribution methods, increasing user peace of mind and convenience.

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

[0116] Step 1: Gather information

[0117] The server uses the SNS API to collect posts based on specific keywords and hashtags. For example, a Python library (Tweepy) is used to access the Twitter API and retrieve tweets related to the keywords "earthquake." The input is keywords, hashtags, and SNS API authentication information, and the output is the collected post data.

[0118] Specifically, the server runs the script every hour to retrieve the latest 50 tweets from the Twitter API.

[0119] Step 2: Data Preprocessing

[0120] The data collected by the server is preprocessed. The input is the collected social media post data, and the output is the preprocessed clean data. Specific data processing includes removing noise, deleting non-ASCII characters, and unifying the encoding (UTF-8).

[0121] Specifically, the server creates a data frame using the Panada library and performs cleaning processing.

[0122] Step 3: News article generation

[0123] The server then inputs the preprocessed data into a generative AI model to generate news articles. The input is the preprocessed, clean data, and the output is the generated news article. This is done using a large-scale language model such as OpenAI's GPT-3.

[0124] Specifically, the server inputs preprocessed data into the GPT-3 API and retrieves news articles in the format "Today's earthquake had its epicenter in XX location, and damage is concentrated in the □□ region."

[0125] Step 4: Credibility assessment

[0126] The server evaluates the credibility of the generated news articles. The input is the generated news article, and the output is a news article with a credibility score. To evaluate credibility, an algorithm is used to calculate the credibility score of the source and select information with a high score.

[0127] Specifically, the server identifies government agencies and trusted media sources and runs a scoring algorithm based on them.

[0128] Step 5: Predict the future

[0129] The server generates scenarios using a future prediction AI model. The input is news articles with confidence scores, and the output is good and bad future scenarios. A time series prediction model (e.g., LSTM model) is used to simulate future scenarios.

[0130] Specifically, the server inputs data into the LSTM model and generates a "scenario in which rescue operations are carried out quickly" and a "scenario in which rescue operations are delayed."

[0131] Step 6: News distribution

[0132] The server delivers the generated news articles and future prediction scenarios to the user's device. The input is the generated news articles and future prediction scenarios, and the output is the delivered news notification. Push notifications are sent to the user's smartphone via a RESTful API.

[0133] Specifically, the server sends a notification to the user's smartphone saying, "New earthquake information is available," the device displays the notification, and the user taps it to view a detailed news article and future prediction scenario.

[0134] This series of processing steps allows users to receive reliable news in real time and plan optimal actions based on future scenarios.

[0135] (Application example 1)

[0136] 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."

[0137] In modern society, a large amount of information is circulated in real time through social media, but it is difficult to immediately determine the credibility and accuracy of that information. Furthermore, news articles are required to go beyond simply reporting past and present events and instead provide future scenarios to help users plan their actions more appropriately. Furthermore, content distribution services need to be able to deliver information quickly and reliably to user devices.

[0138] 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.

[0139] In this invention, the server includes means for collecting various information from SNS, means for analyzing the collected information to generate news articles, means for evaluating the credibility of the generated news articles, means for making future predictions and simulating good and bad futures for the news, means for delivering the news articles and future prediction scenarios to user terminals, and means for delivering the news and future prediction scenarios to the user's computer terminals, thereby enabling users to receive highly reliable information in real time and plan for preparations for future events.

[0140] "SNS" stands for Social Networking Service, a web-based platform that enables users to build online communities and networks, share information, and interact.

[0141] "Diverse information" includes all types of data provided in multiple formats, such as text, images, videos, and links.

[0142] "Analysis" is the process of processing and analyzing collected data to understand meaning and patterns in the information.

[0143] A "news article" is a document in article format that compiles and provides information about current events and topics to users.

[0144] "Credibility" is a measure of the accuracy and reliability of information.

[0145] "Forecasting" is the process of estimating future events or scenarios based on collected data.

[0146] "Simulation" is a technical method of modeling real-world events or scenarios and predicting and analyzing their outcomes.

[0147] A "user terminal" is a device that a user uses to directly operate and receive information, and includes a computer, smartphone, tablet, etc.

[0148] "Distribution" refers to the process of transmitting the generated information to a user terminal via a network so that the user can view it.

[0149] A "generative AI model" is a type of machine learning algorithm that uses artificial intelligence techniques to train it to generate useful output from input data.

[0150] A "content distribution system" is a system consisting of a series of hardware and software for distributing generated content to users.

[0151] The present invention is a system that collects various information from social media, analyzes it, and generates news articles in real time. This system utilizes a generative AI model, has a means to evaluate the credibility of the collected information, and provides only highly reliable information. Furthermore, it predicts the future and simulates good and bad news, allowing users to prepare for the worst-case scenario. Specific embodiments of the system are described below.

[0152] The server first uses social media APIs to collect various posts based on specific keywords or hashtags. This includes posts from multiple social media platforms, such as Twitter and Facebook. The collected data is then preprocessed and saved as a large dataset, including noise removal and data normalization.

[0153] The server then uses a generative AI model, such as OpenAI GPT-3, to automatically generate news articles from the preprocessed data. The model can be a machine learning algorithm, and produces news articles with the same quality as human-written text.

[0154] The generated news articles are then evaluated by a credibility assessment algorithm, which calculates a credibility score for each source and selects only those with a credibility score above a certain threshold. For example, information from government agencies or major media outlets is prioritized.

[0155] The server then launches an AI model for future prediction, simulating good and bad future scenarios based on the generated news articles. For this prediction, a time series prediction model is used. For example, based on earthquake information, it generates a scenario in which rescue efforts are carried out quickly and a scenario in which rescue efforts are delayed.

[0156] Finally, the server delivers the generated news articles and future prediction scenarios to user devices, which can include smartphones, computers, tablets, etc. The delivered news can be easily viewed on the user device, and a notification function is also provided if necessary.

[0157] Specific examples

[0158] The user installs a dedicated app and creates an account. The server periodically uses the Twitter API to collect posts related to the keywords "earthquake" and "earthquake." The collected posts are preprocessed to extract important information such as epicenter information and damage reports. The server uses a generative AI model to create a news article stating, "Today's earthquake occurred at an epicenter in XX location, with damage concentrated in the XX region." A credibility assessment algorithm is run to prioritize and select information from government agencies and reliable media. A future prediction AI model is launched to generate a scenario in which prompt relief efforts are carried out as a "good future," and a scenario in which relief efforts are delayed as a "bad future." The generated news article and future prediction scenario are then delivered to the user's device.

[0159] Prompt Sentence Examples

[0160] Generate a news article based on the following information: The epicenter of today's earthquake is in XX location, and damage is concentrated in the □□ area.

[0161] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0162] Step 1:

[0163] The server collects information using a social networking API. Specific keywords or hashtags (e.g., "earthquake" or "earthquake") are specified as input. The server connects to the social networking API (e.g., Twitter API) and collects posts related to these keywords. The collected post data is returned as output.

[0164] Step 2:

[0165] The data collected by the server is preprocessed. The submitted data collected by the server is used as input. Preprocessing includes noise removal (removal of unnecessary information) and data normalization (standardization of text). The preprocessed data is obtained as output.

[0166] Step 3:

[0167] The server automatically generates news articles using a generative AI model. Preprocessed data is given as input to the generative AI model (e.g., OpenAI GPT-3). A prompt (e.g., "Generate a news article based on the following information: Today's earthquake occurred at a certain location, with damage concentrated in the □□ region") is used to generate the news article. The generated news article is obtained as output.

[0168] Step 4:

[0169] The server evaluates the credibility of the generated news article. As input, the generated news article is given to the credibility evaluation algorithm. The algorithm calculates the credibility score of the source and considers it to be reliable if it exceeds a certain threshold. As output, the credibility-evaluated news article is obtained.

[0170] Step 5:

[0171] The server simulates future scenarios using a future prediction AI model. As input, news articles that have passed the credibility assessment are given to the future prediction AI model (time series prediction model). Simulations based on different assumptions are performed to generate good and bad future scenarios. As output, good and bad future scenarios are obtained.

[0172] Step 6:

[0173] The server distributes the generated news articles and future prediction scenarios to the user's device. The generated news articles and future prediction scenarios are used as input. Notifications and distribution are made to the user's device (e.g., smartphone, computer) via the network. As output, the news articles and future prediction scenarios are displayed on the user's device.

[0174] Step 7:

[0175] The user reads news articles and future prediction scenarios and plans appropriate actions. The news articles and future prediction scenarios delivered to the user's device are used as input. The user prepares for future events based on this. The output is the user's planned actions.

[0176] 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.

[0177] This invention is a system that collects diverse information from social media, analyzes it, and generates news articles in real time. This system utilizes a generative AI model, has a means of evaluating the credibility of the collected information, and provides only highly reliable information. Furthermore, it predicts the future and simulates good and bad news scenarios, allowing users to prepare for the worst-case scenario. Additionally, by combining it with an emotion engine that recognizes the user's emotions, it delivers appropriate information according to the user's emotions.

[0178] Program processing overview

[0179] 1. Information gathering methods

[0180] The server uses social media APIs to collect posts based on specific keywords or hashtags, including posts from multiple social media platforms such as Twitter and Facebook.

[0181] 2. Creating news articles using generative AI models

[0182] The server preprocesses the collected data (denoising, normalising) and then inputs it into a generative AI model to automatically generate news articles. The generative AI model uses a large-scale language model such as GPT-4.

[0183] 3. Credibility assessment tools

[0184] The server runs a credibility assessment algorithm on the generated news articles, weighting data from official and trusted sources to calculate a credibility score.

[0185] 4. Means of predicting the future

[0186] The server launches an AI model for future prediction and simulates future scenarios based on the generated news. It simulates both good and bad futures and generates each scenario.

[0187] 5. Emotion Engine

[0188] The server is equipped with an emotion engine that recognizes the user's emotions, and analyzes the emotional impact that collected data and news articles have on the user.

[0189] 6. News distribution methods

[0190] The server delivers the generated news articles and future prediction scenarios to the user's device, and the delivered news is adjusted according to the user's emotions.

[0191] Specific operation example

[0192] 1. The user installs the dedicated app and creates an account.

[0193] 2. The server periodically uses the Twitter API to collect posts related to the keywords "earthquake" or "earthquake."

[0194] 3. The server preprocesses the collected posts and extracts important information such as epicenter information and damage reports.

[0195] 4. The server uses the generative AI model to create a news article stating, "Today's earthquake had its epicenter in XX location, and damage is concentrated in the □□ region."

[0196] 5. The server runs a credibility assessment algorithm to prioritize information from government agencies and trusted media.

[0197] 6. The server launches a future prediction AI model and generates a scenario in which prompt rescue operations are carried out as a "good future" and a scenario in which rescue operations are delayed as a "bad future."

[0198] 7. The server uses an emotion engine to analyze the user's current emotional state and tailor the news article accordingly, for example, emphasizing reassuring information if the user is feeling anxious.

[0199] 8. The server delivers the generated news articles and future prediction scenarios to the user's device. Possible delivery methods include push notifications and emails.

[0200] 9. The device displays a news notification to the user, which includes a brief summary and a link for the user to view more details.

[0201] 10. The user interacts with their device and taps the notification to view a detailed news article and future scenario, providing the user with fast and reliable information about the current situation and future possibilities.

[0202] Through the above process, the present invention not only provides highly reliable news and future predictions in real time, but also uses an emotion engine to deliver information that responds to the user's emotions. It also improves the user experience by providing appropriate feedback on the anxiety and stress the user is feeling. Compared to conventional news delivery methods, this system enables more personalized information delivery, enhancing user peace of mind and convenience.

[0203] The processing flow will be explained below.

[0204] Step 1:

[0205] The server uses social media APIs to collect posts based on specific keywords or hashtags, specifically using the Twitter API or Facebook API to perform real-time searches for keywords like "earthquake."

[0206] Step 2:

[0207] The server preprocesses the collected posts, which includes denoising (removing spam and irrelevant posts) and normalizing (lowercasing text, removing special characters, etc.).

[0208] Step 3:

[0209] The server analyzes the preprocessed information, specifically using text mining technology to extract important information (e.g., epicenter, damage status, evacuation shelter information, etc.).

[0210] Step 4:

[0211] The server inputs the extracted information into a generative AI model, which automatically generates news articles. The generative AI model uses a large-scale language model such as GPT-4.

[0212] Step 5:

[0213] The server runs a credibility assessment algorithm on the generated news articles, which calculates a credibility score for each source and prioritizes data from official institutions and trusted media.

[0214] Step 6:

[0215] The server launches a future prediction model and simulates future scenarios based on the generated news. It simulates both good and bad futures and generates each scenario.

[0216] Step 7:

[0217] The server activates an emotion engine to recognize the user's emotions, which analyzes the user's emotions based on the user's past browsing history and current emotional state.

[0218] Step 8:

[0219] The server uses an emotion engine to tailor the generated news articles, for example, emphasizing more reassuring information if the user is feeling anxious.

[0220] Step 9:

[0221] The server delivers the generated news articles and future prediction scenarios to the user's device via push notifications, email, and other methods.

[0222] Step 10:

[0223] The device displays a news notification to the user, which includes a brief summary and provides a link for the user to view more details.

[0224] Step 11:

[0225] Users interact with their devices and tap the notification to view detailed news articles and future scenarios, providing fast and reliable information about current situations and future possibilities.

[0226] Through these steps, the present invention not only provides reliable news and future predictions in real time, but also uses an emotion engine to deliver information according to the user's emotions. It also improves the user experience by providing appropriate feedback for the anxiety and stress the user is feeling.

[0227] Example 2

[0228] 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."

[0229] Conventional news distribution systems have difficulty in providing reliable information quickly, and do not take into account the emotional state of the user. As a result, the quality of the information users receive is declining, and they are not adequately prepared for future uncertainties.

[0230] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting various information from online platforms, means for preprocessing the collected information and then generating news articles, evaluation means for evaluating the credibility of the generated news articles, means for making future predictions and simulating good and bad news futures, and means for delivering the generated news articles and future prediction scenarios to a user terminal. This makes it possible to provide highly credible news and future predictions, as well as deliver information according to the user's emotions.

[0231] "Online platform" refers to a website or service that provides information or services via the Internet.

[0232] "Means of collecting information" refers to the operations and techniques used to obtain the necessary data from various sources on the Internet.

[0233] "Preprocessing" refers to a series of steps that remove noise from raw data and convert it into a form suitable for analysis and generative models.

[0234] "Means for generating news articles" refers to techniques and operations for automatically creating news articles based on collected and pre-processed data.

[0235] "Evaluation methods" refer to technologies and algorithms used to assess the credibility and accuracy of generated news articles and determine their quality.

[0236] "Methods of forecasting the future" refers to techniques and operations that use current data to predict future scenarios or events.

[0237] "User terminal" refers to a device, such as a smartphone or computer, that a user uses to view news articles and future prediction scenarios.

[0238] An "emotion recognition engine" refers to technology and algorithms that analyze a user's emotional state and optimize information delivery based on the results.

[0239] A "generative AI model" refers to an algorithm or system that uses artificial intelligence techniques to generate natural language text from data.

[0240] A "prompt sentence" is a string or text that is input into a generative AI model, and refers to the instructions for generating a sentence based on that string.

[0241] The present invention is a system that collects various information from online platforms, analyzes it, and generates news articles. Specifically, the system evaluates the credibility of the collected information, makes future predictions, and delivers appropriate news according to the user's emotional state. Specific embodiments for implementing the present invention are described below.

[0242] Information gathering methods

[0243] The server collects information from online platforms, using APIs to retrieve posts from social networking sites such as Twitter and Facebook, for example by searching for specific keywords or hashtags.

[0244] Specific working example:

[0245] The server uses the Twitter API to collect posts containing "earthquake" or "earthquake," using the Twitter API key and secret.

[0246] Data preprocessing and news article generation

[0247] The server preprocesses the collected data, removing noise and normalizing it to extract only the necessary information. The preprocessed data is then input into a generative AI model (e.g., GPT-4) to automatically generate news articles.

[0248] Specific working example:

[0249] The server removes unnecessary links and strings from the collected posts and converts them into text data.

[0250] The server inputs the following prompt sentence to the generated AI model:

[0251] "Generate a news article about today's earthquake. Include epicenter information, damage report, and confirmation from a reliable source."

[0252] Credibility assessment tools

[0253] The server runs a credibility assessment algorithm on the generated news articles, which references data from government agencies and other trusted sources to calculate a credibility score.

[0254] Specific working example:

[0255] The server compares the generated news articles with official government information and calculates a credibility score.

[0256] Future prediction methods

[0257] The server launches an AI model for future prediction and simulates future scenarios based on the generated news, generating a "good future" and a "bad future" as simulation results.

[0258] Specific working example:

[0259] The server generates both scenarios in which rescue efforts are rapid and scenarios in which rescue efforts are delayed.

[0260] Emotion Engine

[0261] The server uses an emotion engine to analyze the user's emotional state, thereby taking into account the emotional impact of collected data and news articles on the user.

[0262] Specific working example:

[0263] The server analyzes the interaction data acquired from the user's device and evaluates the user's current emotional state.

[0264] News distribution methods

[0265] The server delivers the generated news articles and future prediction scenarios to the user's device via push notifications, email, and other methods.

[0266] Specific working example:

[0267] The server sends a news article to the device via push notification as "Breaking News about Today's Earthquake."

[0268] The device will display a notification such as "The epicenter is at XX location. Click here for details."

[0269] User Interface

[0270] Users can tap on the notification to view a detailed news article and future scenarios, providing fast and reliable information about current conditions and future possibilities.

[0271] Specific working example:

[0272] Users can understand the situation by opening the news app and reading the generated news articles and future prediction scenarios.

[0273] As described above, the present invention realizes highly reliable news provision and future predictions, as well as personalized information delivery according to the user's emotions.

[0274] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0275] Step 1: Gather information

[0276] The server collects information from online platforms, using APIs to retrieve posts containing specific keywords or hashtags from social media platforms such as Twitter and Facebook.

[0277] Input: A specific keyword or hashtag (e.g., "earthquake").

[0278] Output: Collected social media post data.

[0279] Specific behavior:

[0280] The server authenticates using the Twitter API key and secret.

[0281] The server retrieves posts containing "earthquake" or "earthquake" and stores them in a database.

[0282] Step 2: Preprocessing the data

[0283] The server preprocesses the collected data, performing noise reduction and normalization to remove unnecessary information.

[0284] Input: Collected social media posting data.

[0285] Output: Preprocessed and clean data.

[0286] Specific behavior:

[0287] The server removes URLs and unnecessary strings from the collected posts.

[0288] The server normalizes the post and reformats it as text data.

[0289] Step 3: News article generation

[0290] The server uses a generative AI model (e.g., GPT-4) to generate news articles based on the preprocessed data.

[0291] Input: Preprocessed data, prompt (e.g., "Generate a news article about today's earthquake. Include epicenter information, damage report, and confirmation from a reliable source.").

[0292] Output: The generated news article.

[0293] Specific behavior:

[0294] The server inputs the preprocessed data into the generative AI model.

[0295] The server generates a news article using the prompt text.

[0296] Step 4: Credibility assessment

[0297] The server applies a credibility assessment algorithm to assess the credibility of the generated news article by comparing it with official and trusted sources.

[0298] Input: Generated news articles.

[0299] Output: News articles with credibility scores.

[0300] Specific behavior:

[0301] The server compares the generated news articles with official government information.

[0302] The server calculates an authenticity score and assigns it to the article.

[0303] Step 5: Predict the future

[0304] The server uses a future prediction AI model to simulate future scenarios based on the generated news, generating both good and bad futures.

[0305] Input: News articles with credibility scores.

[0306] Output: Future prediction scenario.

[0307] Specific behavior:

[0308] The server generates scenarios in which prompt rescue operations are carried out and scenarios in which rescue operations are delayed.

[0309] Step 6: Emotion Recognition

[0310] The server uses an emotion engine to analyze the user's emotional state, which determines what information is most useful to the user.

[0311] Input: Interaction data from the user device.

[0312] Output: Information provision plan according to the user's emotional state.

[0313] Specific behavior:

[0314] The server analyzes the user's browsing history and interaction data to assess their current emotional state.

[0315] Step 7: News distribution

[0316] The server generates news articles and future prediction scenarios and delivers them to the device according to the user's emotional state, using methods such as push notifications and emails.

[0317] Input: Information provision plans based on the user's emotional state, news articles, and future prediction scenarios.

[0318] Output: News articles and future prediction scenarios delivered to the user's device.

[0319] Specific behavior:

[0320] The server sends a news article to the device via push notification as "Breaking News about Today's Earthquake."

[0321] The device will display a notification such as "The epicenter is at XX location. Click here for details."

[0322] Step 8: Read the news article

[0323] Users interact with their devices and tap the notification to view detailed news articles and future scenarios, providing fast and reliable information about current situations and future possibilities.

[0324] Enter: news notifications on your device.

[0325] Output: A detailed news article and future scenarios for the user to view.

[0326] Specific behavior:

[0327] Users can understand the situation by opening the news app and reading the generated news articles and future prediction scenarios.

[0328] (Application example 2)

[0329] 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."

[0330] Conventional news distribution systems have not always provided a good user experience because the reliability of the information is uncertain and they are unable to provide information that reflects the user's emotions. In addition, there are only a limited number of systems that provide future predictions, making it difficult for users to predict and prepare for the future.

[0331] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting various information from SNS, means for analyzing the collected information to generate news articles, means for evaluating the credibility of the generated news articles, means for making future predictions and simulating good and bad news futures, means for recognizing user emotions and adjusting news articles in accordance with those emotions, and means for delivering news articles and future prediction scenarios to the user terminal. This enables the provision of highly reliable information in real time and personalized news delivery in accordance with the user's emotions.

[0332] "Means of collecting diverse information from social media" refers to a method of using social media APIs to collect posts based on specific keywords or hashtags.

[0333] "Means of analyzing collected information to generate news articles" refers to methods of preprocessing collected data and automatically creating news articles using generative AI models.

[0334] "Method for assessing the credibility of generated news articles" refers to a method for applying a credibility assessment algorithm to generated news articles and calculating a credibility score based on data from official institutions and reliable sources.

[0335] "Means for making future predictions and simulating good and bad news scenarios" refers to a method for simulating both good and bad future scenarios based on news generated using a future prediction AI model.

[0336] "Means for recognizing users' emotions and adjusting news articles according to those emotions" refers to a method of using an emotion engine to analyze a user's current emotional state and adjust the content and delivery method of news articles according to those emotions.

[0337] "Means for delivering news articles and future prediction scenarios to user devices" refers to methods for delivering the generated news articles and future prediction scenarios to users' devices and notifying them via push notifications or email.

[0338] The system for implementing the invention aims to collect various information from social media, generate news articles using a generative AI model, evaluate their credibility, make future predictions, and then deliver information based on user sentiment. The detailed process is described below.

[0339] The server uses social media APIs to collect posts based on specific keywords or hashtags. It can obtain data from major social media platforms such as Twitter and Facebook. This allows the server to collect the latest information in real time and preprocess the data.

[0340] The server then analyzes the collected data and automatically generates news articles using a generative AI model (e.g., GPT-4). The preprocessed data is tokenized and fed into the generative AI model, which generates news articles in natural language based on the input data.

[0341] The server then runs a credibility assessment algorithm on the generated news articles, which takes into account data from official and trusted sources and calculates a credibility score. Information with a higher credibility score is considered more trustworthy.

[0342] The server runs a future-prediction AI model that simulates both good and bad future scenarios based on the generated news. For example, in the case of a natural disaster, it generates scenarios in which rescue efforts are swift and in which they are delayed.

[0343] The server also has a built-in emotion engine that recognizes users' emotions and adjusts news articles accordingly. The emotion engine analyzes the user's current emotional state and adjusts the content and delivery method of the news article accordingly. For example, if the user is feeling anxious, it will emphasize information that will reassure them.

[0344] The server delivers the generated news articles and future prediction scenarios to the user's device. Possible delivery methods include push notifications and emails. The user's device displays a news notification containing a brief summary and a link to view the detailed news article and future prediction scenario.

[0345] As a concrete example, when collecting earthquake information, a user searches for the keyword "earthquake." The server uses the Twitter API to collect related posts and generates a news article based on them. It then evaluates their credibility and predicts future good scenarios (quick rescue) and bad scenarios (delayed rescue operations). If the user's emotional state is "anxious," the server will prioritize delivering information that provides reassurance.

[0346] This approach enables real-time, reliable information delivery and personalized news delivery based on user sentiment.

[0347] An example prompt is:

[0348] "Get the latest earthquake information from current tweets."

[0349] "Generate news articles from this data."

[0350] "Evaluate the credibility of the news generated."

[0351] "Based on this, predict good and bad scenarios for the future."

[0352] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0353] Step 1:

[0354] The server uses a social media API (e.g., Twitter API) to collect posts based on a specific keyword (e.g., "earthquake") or hashtag. At this point, it sends an API request to retrieve the relevant post data. The input is the social media API endpoint and keyword, and the output is the collected post data.

[0355] Step 2:

[0356] The server preprocesses the collected submission data. This includes noise removal and data normalization. For example, it removes unnecessary symbols and links and extracts important information (e.g., place names, damage information). The input is the collected submission data, and the output is the preprocessed, clean data.

[0357] Step 3:

[0358] The server feeds the preprocessed data to a generative AI model (e.g., GPT-4) to automatically generate news articles. It uses a tokenizer to tokenize the data and input it into the generative AI model. It decodes and outputs the news articles generated by the model. The input is the preprocessed data, and the output is the generated news articles.

[0359] Step 4:

[0360] The server runs a credibility assessment algorithm on the generated news articles. The algorithm calculates a credibility score based on data obtained from official and trusted sources. The input is the generated news article, and the output is the news article with the assigned credibility score.

[0361] Step 5:

[0362] The server runs a future prediction AI model based on news articles that have undergone credibility assessment, simulating both positive and negative future scenarios. For example, it predicts the impact of rapid relief efforts versus delays. The input is news articles with credibility scores, and the output is future prediction scenarios.

[0363] Step 6:

[0364] The server uses an emotion engine to analyze the user's emotional state and adjust the news article accordingly. For example, if the user is feeling anxious, it will emphasize reassuring information. The input is the user's emotional data and a news article, and the output is a news article adjusted according to the emotion.

[0365] Step 7:

[0366] The server delivers the final adjusted news article and future prediction scenario to the user's device. The device displays a news notification to the user, which includes a brief summary and a link to a detailed article. The input is the adjusted news article and future prediction scenario, and the output is the notification displayed on the user's device.

[0367] 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.

[0368] 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.

[0369] 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.

[0370] [Second embodiment]

[0371] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0372] 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.

[0373] 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).

[0374] 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.

[0375] 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.

[0376] 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).

[0377] 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.

[0378] 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.

[0379] 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.

[0380] 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.

[0381] 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.

[0382] 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."

[0383] This invention is a system that collects various information from social media, analyzes it, and generates news articles in real time. The system utilizes a generative AI model, has a means to evaluate the credibility of the collected information, and provides only highly reliable information. Furthermore, it predicts the future and simulates good and bad news, allowing users to prepare for the worst-case scenario.

[0384] Program processing overview

[0385] 1. Information gathering methods

[0386] The server uses social media APIs to collect various posts based on specific keywords or hashtags, including those from multiple social media platforms such as Twitter and Facebook.

[0387] 2. Creating news articles using generative AI models

[0388] The server preprocesses the collected data (denoising, normalising) and then inputs it into a generative AI model to automatically generate news articles. The generative AI model uses a large-scale language model trained with machine learning algorithms.

[0389] 3. Credibility assessment tools

[0390] The server runs a credibility assessment algorithm on the generated news articles, which calculates a credibility score for each source and selects the most credible information.

[0391] 4. Means of predicting the future

[0392] The server launches an AI model for future prediction, simulating good and bad future scenarios based on the generated news, using a time series forecasting model.

[0393] 5. News distribution methods

[0394] The server delivers the generated news articles and future prediction scenarios to the user's device, where the user can view the delivered news.

[0395] Specific operation example

[0396] 1. The user installs the dedicated app and creates an account.

[0397] 2. The server periodically uses the Twitter API to collect posts related to the keywords "earthquake" or "earthquake."

[0398] 3. The server preprocesses the collected posts and extracts important information such as epicenter information and damage reports.

[0399] 4. The server uses the generative AI model to create a news article stating, "Today's earthquake had its epicenter in XX location, and damage is concentrated in the □□ region."

[0400] 5. The server runs a credibility assessment algorithm to prioritize information from government agencies and trusted media.

[0401] 6. The server launches a future prediction AI model and generates a scenario in which prompt rescue operations are carried out as a "good future" and a scenario in which rescue operations are delayed as a "bad future."

[0402] 7. The server delivers the generated news articles and future prediction scenarios to the user's device.

[0403] 8. The device displays a news notification, which the user taps to view a detailed news article and future prediction scenarios.

[0404] Through the above process, users can not only receive reliable news in real time, but also plan their actions based on future scenarios. Compared to conventional news distribution methods, this system provides faster and more reliable information, increasing user peace of mind and convenience.

[0405] The processing flow will be explained below.

[0406] Step 1:

[0407] The server uses social media APIs to collect posts based on specific keywords or hashtags, such as "earthquake" or "earthquake," and performs real-time searches using the Twitter API or Facebook API.

[0408] Step 2:

[0409] The server preprocesses the collected posts, which includes denoising (removing spam and irrelevant posts) and normalizing (lowercasing text, removing special characters, etc.).

[0410] Step 3:

[0411] The server analyzes the preprocessed information, specifically using text mining technology to extract important information (e.g., epicenter, damage status, evacuation shelter information, etc.).

[0412] Step 4:

[0413] The server inputs the extracted information into a generative AI model, which automatically generates news articles. The generative AI model uses a large-scale language model such as GPT-4.

[0414] Step 5:

[0415] The server runs a credibility assessment algorithm on the generated news articles, weighting data from official and trusted sources to calculate a credibility score.

[0416] Step 6:

[0417] The server launches a future prediction model and simulates future scenarios based on the generated news. It simulates both good and bad futures and generates each scenario.

[0418] Step 7:

[0419] The server integrates the generated news articles with future prediction scenarios and formats them in a way that is easy for users to understand.

[0420] Step 8:

[0421] The server delivers news articles and future prediction scenarios to users' devices via push notifications, emails, and other methods.

[0422] Step 9:

[0423] The device displays a news notification to the user, which includes a brief summary and provides a link for the user to view more details.

[0424] Step 10:

[0425] Users can interact with their devices and tap on notifications to view detailed news articles and future scenarios, providing fast and reliable information about current situations and future possibilities.

[0426] Through the above steps, the present invention builds a system that simultaneously provides highly reliable news in real time and makes future predictions.

[0427] Example 1

[0428] 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."

[0429] Conventional news gathering and distribution systems lack the ability to assess the credibility of information or predict the future, which means there is a risk of providing unreliable information to users. Furthermore, the inability to quickly gather and analyze information makes it difficult to provide information in real time, which means users are unable to enjoy peace of mind and convenience.

[0430] 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.

[0431] In this invention, the server

[0432] A means of collecting various information from SNS,

[0433] means for preprocessing the collected information;

[0434] a means for inputting the preprocessed information into a generative AI model to generate news articles;

[0435] a means for assessing the credibility of the generated news articles;

[0436] A means of making future predictions and simulating good and bad news futures;

[0437] A means for delivering news articles and future prediction scenarios to a user terminal;

[0438] This allows users to receive reliable news in real time and plan optimal actions based on future scenarios.

[0439] "SNS" is an abbreviation for social networking service, an online platform that allows users to interact with each other and share information via the Internet.

[0440] "Information collection means" refers to a means for obtaining various information from social media, etc., and is a system that uses an API to automatically collect posts based on specific keywords or hashtags.

[0441] The "preprocessing means" is a means for removing noise and unnecessary data from collected information and for processing the data to standardize its format.

[0442] A "generative AI model" is a large-scale language model trained using machine learning algorithms that automatically generates news articles by inputting preprocessed data.

[0443] A "credibility assessment tool" is an algorithm that evaluates the reliability of generated news articles and is a tool for calculating the reliability score of information sources and selecting highly credible information.

[0444] A "future prediction tool" is an AI model for simulating future scenarios based on generated news, and is a tool for generating good and bad future scenarios.

[0445] The "news distribution means" is a means for transmitting the generated news articles and future prediction scenarios to the user's terminal so that the user can view them.

[0446] This invention is a system that collects various information from social media, analyzes it, and generates news articles in real time. This system utilizes a generative AI model, has a means to evaluate the credibility of the collected information, and provides only highly reliable information. Furthermore, it predicts the future and simulates good and bad news, allowing users to prepare for the worst-case scenario.

[0447] The following configuration will be described as a specific embodiment of the present invention.

[0448] 1. Information gathering methods

[0449] The server uses social media APIs to collect various posts based on specific keywords and hashtags. This collection method is implemented using Python libraries, and social media platforms include Twitter, Facebook, etc. For example, the Tweepy library is used to access the Twitter API and collect information based on keywords such as "earthquake."

[0450] 2. Data preprocessing methods

[0451] The server preprocesses the collected data, removing noise and unnecessary data and standardizing the data format. This preprocessing method includes, for example, removing non-ASCII characters from the collected tweets and standardizing the encoding to UTF-8.

[0452] 3. News article generation method

[0453] The server then inputs the preprocessed data into a generative AI model to generate a news article. This generative AI model is a large-scale language model trained using a machine learning algorithm, such as OpenAI's GPT-3. This method generates a news article such as, "Today's earthquake had its epicenter in XX location, and damage was concentrated in XX region."

[0454] 4. Credibility assessment tools

[0455] The server runs algorithms to assess the credibility of generated news articles, for example calculating a credibility score for each source and prioritizing information from government agencies and reputable media outlets.

[0456] 5. Means of predicting the future

[0457] The server launches an AI model for future prediction, simulating good and bad future scenarios based on the generated news. This future prediction method uses a time series prediction model, such as an LSTM (long short-term memory) model. Specifically, it generates a "scenario in which relief efforts are carried out quickly" and a "scenario in which relief efforts are delayed."

[0458] 6. News distribution methods

[0459] Finally, the server delivers the generated news articles and future prediction scenarios to the user's device. The device displays the received news notification, and the user can tap it to view detailed news articles and future prediction scenarios. This news delivery uses a RESTful API and employs a mechanism to send push notifications to the user's smartphone.

[0460] Prompt Sentence Examples

[0461] Examples of prompts to input to a generative AI model include:

[0462] "Generate reliable news articles based on the latest earthquake information. Include the following information: epicenter, affected areas, and local conditions. Also, generate rescue scenarios as future predictions."

[0463] With the above configuration, users can receive reliable news in real time and plan optimal actions based on future scenarios. This system provides faster and more reliable information than conventional news distribution methods, increasing user peace of mind and convenience.

[0464] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0465] Step 1: Gather information

[0466] The server uses the SNS API to collect posts based on specific keywords and hashtags. For example, a Python library (Tweepy) is used to access the Twitter API and retrieve tweets related to the keywords "earthquake." The input is keywords, hashtags, and SNS API authentication information, and the output is the collected post data.

[0467] Specifically, the server runs the script every hour to retrieve the latest 50 tweets from the Twitter API.

[0468] Step 2: Data Preprocessing

[0469] The data collected by the server is preprocessed. The input is the collected social media post data, and the output is the preprocessed clean data. Specific data processing includes removing noise, deleting non-ASCII characters, and unifying the encoding (UTF-8).

[0470] Specifically, the server creates a data frame using the Panada library and performs cleaning processing.

[0471] Step 3: News article generation

[0472] The server then inputs the preprocessed data into a generative AI model to generate news articles. The input is the preprocessed, clean data, and the output is the generated news article. This is done using a large-scale language model such as OpenAI's GPT-3.

[0473] Specifically, the server inputs preprocessed data into the GPT-3 API and retrieves news articles in the format "Today's earthquake had its epicenter in XX location, and damage is concentrated in the □□ region."

[0474] Step 4: Credibility assessment

[0475] The server evaluates the credibility of the generated news articles. The input is the generated news article, and the output is a news article with a credibility score. To evaluate credibility, an algorithm is used to calculate the credibility score of the source and select information with a high score.

[0476] Specifically, the server identifies government agencies and trusted media sources and runs a scoring algorithm based on them.

[0477] Step 5: Predict the future

[0478] The server generates scenarios using a future prediction AI model. The input is news articles with confidence scores, and the output is good and bad future scenarios. A time series prediction model (e.g., LSTM model) is used to simulate future scenarios.

[0479] Specifically, the server inputs data into the LSTM model and generates a "scenario in which rescue operations are carried out quickly" and a "scenario in which rescue operations are delayed."

[0480] Step 6: News distribution

[0481] The server delivers the generated news articles and future prediction scenarios to the user's device. The input is the generated news articles and future prediction scenarios, and the output is the delivered news notification. Push notifications are sent to the user's smartphone via a RESTful API.

[0482] Specifically, the server sends a notification to the user's smartphone saying, "New earthquake information is available," the device displays the notification, and the user taps it to view a detailed news article and future prediction scenario.

[0483] This series of processing steps allows users to receive reliable news in real time and plan optimal actions based on future scenarios.

[0484] (Application example 1)

[0485] 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."

[0486] In modern society, a large amount of information is circulated in real time through social media, but it is difficult to immediately determine the credibility and accuracy of that information. Furthermore, news articles are required to go beyond simply reporting past and present events and instead provide future scenarios to help users plan their actions more appropriately. Furthermore, content distribution services need to be able to deliver information quickly and reliably to user devices.

[0487] 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.

[0488] In this invention, the server includes means for collecting various information from SNS, means for analyzing the collected information to generate news articles, means for evaluating the credibility of the generated news articles, means for making future predictions and simulating good and bad futures for the news, means for delivering the news articles and future prediction scenarios to user terminals, and means for delivering the news and future prediction scenarios to the user's computer terminals, thereby enabling users to receive highly reliable information in real time and plan for preparations for future events.

[0489] "SNS" stands for Social Networking Service, a web-based platform that enables users to build online communities and networks, share information, and interact.

[0490] "Diverse information" includes all types of data provided in multiple formats, such as text, images, videos, and links.

[0491] "Analysis" is the process of processing and analyzing collected data to understand meaning and patterns in the information.

[0492] A "news article" is a document in article format that compiles and provides information about current events and topics to users.

[0493] "Credibility" is a measure of the accuracy and reliability of information.

[0494] "Forecasting" is the process of estimating future events or scenarios based on collected data.

[0495] "Simulation" is a technical method of modeling real-world events or scenarios and predicting and analyzing their outcomes.

[0496] A "user terminal" is a device that a user uses to directly operate and receive information, and includes a computer, smartphone, tablet, etc.

[0497] "Distribution" refers to the process of transmitting the generated information to a user terminal via a network so that the user can view it.

[0498] A "generative AI model" is a type of machine learning algorithm that uses artificial intelligence techniques to train it to generate useful output from input data.

[0499] A "content distribution system" is a system consisting of a series of hardware and software for distributing generated content to users.

[0500] The present invention is a system that collects various information from social media, analyzes it, and generates news articles in real time. This system utilizes a generative AI model, has a means to evaluate the credibility of the collected information, and provides only highly reliable information. Furthermore, it predicts the future and simulates good and bad news, allowing users to prepare for the worst-case scenario. Specific embodiments of the system are described below.

[0501] The server first uses social media APIs to collect various posts based on specific keywords or hashtags. This includes posts from multiple social media platforms, such as Twitter and Facebook. The collected data is then preprocessed and saved as a large dataset, including noise removal and data normalization.

[0502] The server then uses a generative AI model, such as OpenAI GPT-3, to automatically generate news articles from the preprocessed data. The model can be a machine learning algorithm, and produces news articles with the same quality as human-written text.

[0503] The generated news articles are then evaluated by a credibility assessment algorithm, which calculates a credibility score for each source and selects only those with a credibility score above a certain threshold. For example, information from government agencies or major media outlets is prioritized.

[0504] The server then launches an AI model for future prediction, simulating good and bad future scenarios based on the generated news articles. For this prediction, a time series prediction model is used. For example, based on earthquake information, it generates a scenario in which rescue efforts are carried out quickly and a scenario in which rescue efforts are delayed.

[0505] Finally, the server delivers the generated news articles and future prediction scenarios to user devices, which can include smartphones, computers, tablets, etc. The delivered news can be easily viewed on the user device, and a notification function is also provided if necessary.

[0506] Specific examples

[0507] The user installs a dedicated app and creates an account. The server periodically uses the Twitter API to collect posts related to the keywords "earthquake" and "earthquake." The collected posts are preprocessed to extract important information such as epicenter information and damage reports. The server uses a generative AI model to create a news article stating, "Today's earthquake occurred at an epicenter in XX location, with damage concentrated in the XX region." A credibility assessment algorithm is run to prioritize and select information from government agencies and reliable media. A future prediction AI model is launched to generate a scenario in which prompt relief efforts are carried out as a "good future," and a scenario in which relief efforts are delayed as a "bad future." The generated news article and future prediction scenario are then delivered to the user's device.

[0508] Prompt Sentence Examples

[0509] Generate a news article based on the following information: The epicenter of today's earthquake is in XX location, and damage is concentrated in the □□ area.

[0510] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0511] Step 1:

[0512] The server collects information using a social networking API. Specific keywords or hashtags (e.g., "earthquake" or "earthquake") are specified as input. The server connects to the social networking API (e.g., Twitter API) and collects posts related to these keywords. The collected post data is returned as output.

[0513] Step 2:

[0514] The data collected by the server is preprocessed. The submitted data collected by the server is used as input. Preprocessing includes noise removal (removal of unnecessary information) and data normalization (standardization of text). The preprocessed data is obtained as output.

[0515] Step 3:

[0516] The server automatically generates news articles using a generative AI model. Preprocessed data is given as input to the generative AI model (e.g., OpenAI GPT-3). A prompt (e.g., "Generate a news article based on the following information: Today's earthquake occurred at a certain location, with damage concentrated in the □□ region") is used to generate the news article. The generated news article is obtained as output.

[0517] Step 4:

[0518] The server evaluates the credibility of the generated news article. As input, the generated news article is given to the credibility evaluation algorithm. The algorithm calculates the credibility score of the source and considers it to be reliable if it exceeds a certain threshold. As output, the credibility-evaluated news article is obtained.

[0519] Step 5:

[0520] The server simulates future scenarios using a future prediction AI model. As input, news articles that have passed the credibility assessment are given to the future prediction AI model (time series prediction model). Simulations based on different assumptions are performed to generate good and bad future scenarios. As output, good and bad future scenarios are obtained.

[0521] Step 6:

[0522] The server distributes the generated news articles and future prediction scenarios to the user's device. The generated news articles and future prediction scenarios are used as input. Notifications and distribution are made to the user's device (e.g., smartphone, computer) via the network. As output, the news articles and future prediction scenarios are displayed on the user's device.

[0523] Step 7:

[0524] The user reads news articles and future prediction scenarios and plans appropriate actions. The news articles and future prediction scenarios delivered to the user's device are used as input. The user prepares for future events based on this. The output is the user's planned actions.

[0525] 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.

[0526] This invention is a system that collects diverse information from social media, analyzes it, and generates news articles in real time. This system utilizes a generative AI model, has a means of evaluating the credibility of the collected information, and provides only highly reliable information. Furthermore, it predicts the future and simulates good and bad news scenarios, allowing users to prepare for the worst-case scenario. Additionally, by combining it with an emotion engine that recognizes the user's emotions, it delivers appropriate information according to the user's emotions.

[0527] Program processing overview

[0528] 1. Information gathering methods

[0529] The server uses social media APIs to collect posts based on specific keywords or hashtags, including posts from multiple social media platforms such as Twitter and Facebook.

[0530] 2. Creating news articles using generative AI models

[0531] The server preprocesses the collected data (denoising, normalising) and then inputs it into a generative AI model to automatically generate news articles. The generative AI model uses a large-scale language model such as GPT-4.

[0532] 3. Credibility assessment tools

[0533] The server runs a credibility assessment algorithm on the generated news articles, weighting data from official and trusted sources to calculate a credibility score.

[0534] 4. Means of predicting the future

[0535] The server launches an AI model for future prediction and simulates future scenarios based on the generated news. It simulates both good and bad futures and generates each scenario.

[0536] 5. Emotion Engine

[0537] The server is equipped with an emotion engine that recognizes the user's emotions, and analyzes the emotional impact that collected data and news articles have on the user.

[0538] 6. News distribution methods

[0539] The server delivers the generated news articles and future prediction scenarios to the user's device, and the delivered news is adjusted according to the user's emotions.

[0540] Specific operation example

[0541] 1. The user installs the dedicated app and creates an account.

[0542] 2. The server periodically uses the Twitter API to collect posts related to the keywords "earthquake" or "earthquake."

[0543] 3. The server preprocesses the collected posts and extracts important information such as epicenter information and damage reports.

[0544] 4. The server uses the generative AI model to create a news article stating, "Today's earthquake had its epicenter in XX location, and damage is concentrated in the □□ region."

[0545] 5. The server runs a credibility assessment algorithm to prioritize information from government agencies and trusted media.

[0546] 6. The server launches a future prediction AI model and generates a scenario in which prompt rescue operations are carried out as a "good future" and a scenario in which rescue operations are delayed as a "bad future."

[0547] 7. The server uses an emotion engine to analyze the user's current emotional state and tailor the news article accordingly, for example, emphasizing reassuring information if the user is feeling anxious.

[0548] 8. The server delivers the generated news articles and future prediction scenarios to the user's device. Possible delivery methods include push notifications and emails.

[0549] 9. The device displays a news notification to the user, which includes a brief summary and a link for the user to view more details.

[0550] 10. The user interacts with their device and taps the notification to view a detailed news article and future scenario, providing the user with fast and reliable information about the current situation and future possibilities.

[0551] Through the above process, the present invention not only provides highly reliable news and future predictions in real time, but also uses an emotion engine to deliver information that responds to the user's emotions. It also improves the user experience by providing appropriate feedback on the anxiety and stress the user is feeling. Compared to conventional news delivery methods, this system enables more personalized information delivery, enhancing user peace of mind and convenience.

[0552] The processing flow will be explained below.

[0553] Step 1:

[0554] The server uses social media APIs to collect posts based on specific keywords or hashtags, specifically using the Twitter API or Facebook API to perform real-time searches for keywords like "earthquake."

[0555] Step 2:

[0556] The server preprocesses the collected posts, which includes denoising (removing spam and irrelevant posts) and normalizing (lowercasing text, removing special characters, etc.).

[0557] Step 3:

[0558] The server analyzes the preprocessed information, specifically using text mining technology to extract important information (e.g., epicenter, damage status, evacuation shelter information, etc.).

[0559] Step 4:

[0560] The server inputs the extracted information into a generative AI model, which automatically generates news articles. The generative AI model uses a large-scale language model such as GPT-4.

[0561] Step 5:

[0562] The server runs a credibility assessment algorithm on the generated news articles, which calculates a credibility score for each source and prioritizes data from official institutions and trusted media.

[0563] Step 6:

[0564] The server launches a future prediction model and simulates future scenarios based on the generated news. It simulates both good and bad futures and generates each scenario.

[0565] Step 7:

[0566] The server activates an emotion engine to recognize the user's emotions, which analyzes the user's emotions based on the user's past browsing history and current emotional state.

[0567] Step 8:

[0568] The server uses an emotion engine to tailor the generated news articles, for example, emphasizing more reassuring information if the user is feeling anxious.

[0569] Step 9:

[0570] The server delivers the generated news articles and future prediction scenarios to the user's device via push notifications, email, and other methods.

[0571] Step 10:

[0572] The device displays a news notification to the user, which includes a brief summary and provides a link for the user to view more details.

[0573] Step 11:

[0574] Users interact with their devices and tap the notification to view detailed news articles and future scenarios, providing fast and reliable information about current situations and future possibilities.

[0575] Through these steps, the present invention not only provides reliable news and future predictions in real time, but also uses an emotion engine to deliver information according to the user's emotions. It also improves the user experience by providing appropriate feedback for the anxiety and stress the user is feeling.

[0576] Example 2

[0577] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0578] Conventional news distribution systems have difficulty in providing reliable information quickly, and do not take into account the emotional state of the user. As a result, the quality of the information users receive is declining, and they are not adequately prepared for future uncertainties.

[0579] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting various information from online platforms, means for preprocessing the collected information and then generating news articles, evaluation means for evaluating the credibility of the generated news articles, means for making future predictions and simulating good and bad news futures, and means for delivering the generated news articles and future prediction scenarios to a user terminal. This makes it possible to provide highly credible news and future predictions, as well as deliver information according to the user's emotions.

[0580] "Online platform" refers to a website or service that provides information or services via the Internet.

[0581] "Means of collecting information" refers to the operations and techniques used to obtain the necessary data from various sources on the Internet.

[0582] "Preprocessing" refers to a series of steps that remove noise from raw data and convert it into a form suitable for analysis and generative models.

[0583] "Means for generating news articles" refers to techniques and operations for automatically creating news articles based on collected and pre-processed data.

[0584] "Evaluation methods" refer to technologies and algorithms used to assess the credibility and accuracy of generated news articles and determine their quality.

[0585] "Methods of forecasting the future" refers to techniques and operations that use current data to predict future scenarios or events.

[0586] "User terminal" refers to a device, such as a smartphone or computer, that a user uses to view news articles and future prediction scenarios.

[0587] An "emotion recognition engine" refers to technology and algorithms that analyze a user's emotional state and optimize information delivery based on the results.

[0588] A "generative AI model" refers to an algorithm or system that uses artificial intelligence techniques to generate natural language text from data.

[0589] A "prompt sentence" is a string or text that is input into a generative AI model, and refers to the instructions for generating a sentence based on that string.

[0590] The present invention is a system that collects various information from online platforms, analyzes it, and generates news articles. Specifically, the system evaluates the credibility of the collected information, makes future predictions, and delivers appropriate news according to the user's emotional state. Specific embodiments for implementing the present invention are described below.

[0591] Information gathering methods

[0592] The server collects information from online platforms, using APIs to retrieve posts from social networking sites such as Twitter and Facebook, for example by searching for specific keywords or hashtags.

[0593] Specific working example:

[0594] The server uses the Twitter API to collect posts containing "earthquake" or "earthquake," using the Twitter API key and secret.

[0595] Data preprocessing and news article generation

[0596] The server preprocesses the collected data, removing noise and normalizing it to extract only the necessary information. The preprocessed data is then input into a generative AI model (e.g., GPT-4) to automatically generate news articles.

[0597] Specific working example:

[0598] The server removes unnecessary links and strings from the collected posts and converts them into text data.

[0599] The server inputs the following prompt sentence to the generated AI model:

[0600] "Generate a news article about today's earthquake. Include epicenter information, damage report, and confirmation from a reliable source."

[0601] Credibility assessment tools

[0602] The server runs a credibility assessment algorithm on the generated news articles, which references data from government agencies and other trusted sources to calculate a credibility score.

[0603] Specific working example:

[0604] The server compares the generated news articles with official government information and calculates a credibility score.

[0605] Future prediction methods

[0606] The server launches an AI model for future prediction and simulates future scenarios based on the generated news, generating a "good future" and a "bad future" as simulation results.

[0607] Specific working example:

[0608] The server generates both scenarios in which rescue efforts are rapid and scenarios in which rescue efforts are delayed.

[0609] Emotion Engine

[0610] The server uses an emotion engine to analyze the user's emotional state, thereby taking into account the emotional impact of collected data and news articles on the user.

[0611] Specific working example:

[0612] The server analyzes the interaction data acquired from the user's device and evaluates the user's current emotional state.

[0613] News distribution methods

[0614] The server delivers the generated news articles and future prediction scenarios to the user's device via push notifications, email, and other methods.

[0615] Specific working example:

[0616] The server sends a news article to the device via push notification as "Breaking News about Today's Earthquake."

[0617] The device will display a notification such as "The epicenter is at XX location. Click here for details."

[0618] User Interface

[0619] Users can tap on the notification to view a detailed news article and future scenarios, providing fast and reliable information about current conditions and future possibilities.

[0620] Specific working example:

[0621] Users can understand the situation by opening the news app and reading the generated news articles and future prediction scenarios.

[0622] As described above, the present invention realizes highly reliable news provision and future predictions, as well as personalized information delivery according to the user's emotions.

[0623] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0624] Step 1: Gather information

[0625] The server collects information from online platforms, using APIs to retrieve posts containing specific keywords or hashtags from social media platforms such as Twitter and Facebook.

[0626] Input: A specific keyword or hashtag (e.g., "earthquake").

[0627] Output: Collected social media post data.

[0628] Specific behavior:

[0629] The server authenticates using the Twitter API key and secret.

[0630] The server retrieves posts containing "earthquake" or "earthquake" and stores them in a database.

[0631] Step 2: Preprocessing the data

[0632] The server preprocesses the collected data, performing noise reduction and normalization to remove unnecessary information.

[0633] Input: Collected social media posting data.

[0634] Output: Preprocessed and clean data.

[0635] Specific behavior:

[0636] The server removes URLs and unnecessary strings from the collected posts.

[0637] The server normalizes the post and reformats it as text data.

[0638] Step 3: News article generation

[0639] The server uses a generative AI model (e.g., GPT-4) to generate news articles based on the preprocessed data.

[0640] Input: Preprocessed data, prompt (e.g., "Generate a news article about today's earthquake. Include epicenter information, damage report, and confirmation from a reliable source.").

[0641] Output: The generated news article.

[0642] Specific behavior:

[0643] The server inputs the preprocessed data into the generative AI model.

[0644] The server generates a news article using the prompt text.

[0645] Step 4: Credibility assessment

[0646] The server applies a credibility assessment algorithm to assess the credibility of the generated news article by comparing it with official and trusted sources.

[0647] Input: Generated news articles.

[0648] Output: News articles with credibility scores.

[0649] Specific behavior:

[0650] The server compares the generated news articles with official government information.

[0651] The server calculates an authenticity score and assigns it to the article.

[0652] Step 5: Predict the future

[0653] The server uses a future prediction AI model to simulate future scenarios based on the generated news, generating both good and bad futures.

[0654] Input: News articles with credibility scores.

[0655] Output: Future prediction scenario.

[0656] Specific behavior:

[0657] The server generates scenarios in which prompt rescue operations are carried out and scenarios in which rescue operations are delayed.

[0658] Step 6: Emotion Recognition

[0659] The server uses an emotion engine to analyze the user's emotional state, which determines what information is most useful to the user.

[0660] Input: Interaction data from the user device.

[0661] Output: Information provision plan according to the user's emotional state.

[0662] Specific behavior:

[0663] The server analyzes the user's browsing history and interaction data to assess their current emotional state.

[0664] Step 7: News distribution

[0665] The server generates news articles and future prediction scenarios and delivers them to the device according to the user's emotional state, using methods such as push notifications and emails.

[0666] Input: Information provision plans based on the user's emotional state, news articles, and future prediction scenarios.

[0667] Output: News articles and future prediction scenarios delivered to the user's device.

[0668] Specific behavior:

[0669] The server sends a news article to the device via push notification as "Breaking News about Today's Earthquake."

[0670] The device will display a notification such as "The epicenter is at XX location. Click here for details."

[0671] Step 8: Read the news article

[0672] Users interact with their devices and tap the notification to view detailed news articles and future scenarios, providing fast and reliable information about current situations and future possibilities.

[0673] Enter: news notifications on your device.

[0674] Output: A detailed news article and future scenarios for the user to view.

[0675] Specific behavior:

[0676] Users can understand the situation by opening the news app and reading the generated news articles and future prediction scenarios.

[0677] (Application example 2)

[0678] 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."

[0679] Conventional news distribution systems have not always provided a good user experience because the reliability of the information is uncertain and they are unable to provide information that reflects the user's emotions. In addition, there are only a limited number of systems that provide future predictions, making it difficult for users to predict and prepare for the future.

[0680] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting various information from SNS, means for analyzing the collected information to generate news articles, means for evaluating the credibility of the generated news articles, means for making future predictions and simulating good and bad news futures, means for recognizing user emotions and adjusting news articles in accordance with those emotions, and means for delivering news articles and future prediction scenarios to the user terminal. This enables the provision of highly reliable information in real time and personalized news delivery in accordance with the user's emotions.

[0681] "Means of collecting diverse information from social media" refers to a method of using social media APIs to collect posts based on specific keywords or hashtags.

[0682] "Means of analyzing collected information to generate news articles" refers to methods of preprocessing collected data and automatically creating news articles using generative AI models.

[0683] "Method for assessing the credibility of generated news articles" refers to a method for applying a credibility assessment algorithm to generated news articles and calculating a credibility score based on data from official institutions and reliable sources.

[0684] "Means for making future predictions and simulating good and bad news scenarios" refers to a method for simulating both good and bad future scenarios based on news generated using a future prediction AI model.

[0685] "Means for recognizing users' emotions and adjusting news articles according to those emotions" refers to a method of using an emotion engine to analyze a user's current emotional state and adjust the content and delivery method of news articles according to those emotions.

[0686] "Means for delivering news articles and future prediction scenarios to user devices" refers to methods for delivering the generated news articles and future prediction scenarios to users' devices and notifying them via push notifications or email.

[0687] The system for implementing the invention aims to collect various information from social media, generate news articles using a generative AI model, evaluate their credibility, make future predictions, and then deliver information based on user sentiment. The detailed process is described below.

[0688] The server uses social media APIs to collect posts based on specific keywords or hashtags. It can obtain data from major social media platforms such as Twitter and Facebook. This allows the server to collect the latest information in real time and preprocess the data.

[0689] The server then analyzes the collected data and automatically generates news articles using a generative AI model (e.g., GPT-4). The preprocessed data is tokenized and fed into the generative AI model, which generates news articles in natural language based on the input data.

[0690] The server then runs a credibility assessment algorithm on the generated news articles, which takes into account data from official and trusted sources and calculates a credibility score. Information with a higher credibility score is considered more trustworthy.

[0691] The server runs a future-prediction AI model that simulates both good and bad future scenarios based on the generated news. For example, in the case of a natural disaster, it generates scenarios in which rescue efforts are swift and in which they are delayed.

[0692] The server also has a built-in emotion engine that recognizes users' emotions and adjusts news articles accordingly. The emotion engine analyzes the user's current emotional state and adjusts the content and delivery method of the news article accordingly. For example, if the user is feeling anxious, it will emphasize information that will reassure them.

[0693] The server delivers the generated news articles and future prediction scenarios to the user's device. Possible delivery methods include push notifications and emails. The user's device displays a news notification containing a brief summary and a link to view the detailed news article and future prediction scenario.

[0694] As a concrete example, when collecting earthquake information, a user searches for the keyword "earthquake." The server uses the Twitter API to collect related posts and generates a news article based on them. It then evaluates their credibility and predicts future good scenarios (quick rescue) and bad scenarios (delayed rescue operations). If the user's emotional state is "anxious," the server will prioritize delivering information that provides reassurance.

[0695] This approach enables real-time, reliable information delivery and personalized news delivery based on user sentiment.

[0696] An example prompt is:

[0697] "Get the latest earthquake information from current tweets."

[0698] "Generate news articles from this data."

[0699] "Evaluate the credibility of the news generated."

[0700] "Based on this, predict good and bad scenarios for the future."

[0701] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0702] Step 1:

[0703] The server uses a social media API (e.g., Twitter API) to collect posts based on a specific keyword (e.g., "earthquake") or hashtag. At this point, it sends an API request to retrieve the relevant post data. The input is the social media API endpoint and keyword, and the output is the collected post data.

[0704] Step 2:

[0705] The server preprocesses the collected submission data. This includes noise removal and data normalization. For example, it removes unnecessary symbols and links and extracts important information (e.g., place names, damage information). The input is the collected submission data, and the output is the preprocessed, clean data.

[0706] Step 3:

[0707] The server feeds the preprocessed data to a generative AI model (e.g., GPT-4) to automatically generate news articles. It uses a tokenizer to tokenize the data and input it into the generative AI model. It decodes and outputs the news articles generated by the model. The input is the preprocessed data, and the output is the generated news articles.

[0708] Step 4:

[0709] The server runs a credibility assessment algorithm on the generated news articles. The algorithm calculates a credibility score based on data obtained from official and trusted sources. The input is the generated news article, and the output is the news article with the assigned credibility score.

[0710] Step 5:

[0711] The server runs a future prediction AI model based on news articles that have undergone credibility assessment, simulating both positive and negative future scenarios. For example, it predicts the impact of rapid relief efforts versus delays. The input is news articles with credibility scores, and the output is future prediction scenarios.

[0712] Step 6:

[0713] The server uses an emotion engine to analyze the user's emotional state and adjust the news article accordingly. For example, if the user is feeling anxious, it will emphasize reassuring information. The input is the user's emotional data and a news article, and the output is a news article adjusted according to the emotion.

[0714] Step 7:

[0715] The server delivers the final adjusted news article and future prediction scenario to the user's device. The device displays a news notification to the user, which includes a brief summary and a link to a detailed article. The input is the adjusted news article and future prediction scenario, and the output is the notification displayed on the user's device.

[0716] 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.

[0717] 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.

[0718] 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.

[0719] [Third embodiment]

[0720] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0721] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0722] 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).

[0723] 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.

[0724] 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.

[0725] 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).

[0726] 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.

[0727] 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.

[0728] 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.

[0729] 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.

[0730] 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.

[0731] 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."

[0732] This invention is a system that collects various information from social media, analyzes it, and generates news articles in real time. The system utilizes a generative AI model, has a means to evaluate the credibility of the collected information, and provides only highly reliable information. Furthermore, it predicts the future and simulates good and bad news, allowing users to prepare for the worst-case scenario.

[0733] Program processing overview

[0734] 1. Information gathering methods

[0735] The server uses social media APIs to collect various posts based on specific keywords or hashtags, including those from multiple social media platforms such as Twitter and Facebook.

[0736] 2. Creating news articles using generative AI models

[0737] The server preprocesses the collected data (denoising, normalising) and then inputs it into a generative AI model to automatically generate news articles. The generative AI model uses a large-scale language model trained with machine learning algorithms.

[0738] 3. Credibility assessment tools

[0739] The server runs a credibility assessment algorithm on the generated news articles, which calculates a credibility score for each source and selects the most credible information.

[0740] 4. Means of predicting the future

[0741] The server launches an AI model for future prediction, simulating good and bad future scenarios based on the generated news, using a time series forecasting model.

[0742] 5. News distribution methods

[0743] The server delivers the generated news articles and future prediction scenarios to the user's device, where the user can view the delivered news.

[0744] Specific operation example

[0745] 1. The user installs the dedicated app and creates an account.

[0746] 2. The server periodically uses the Twitter API to collect posts related to the keywords "earthquake" or "earthquake."

[0747] 3. The server preprocesses the collected posts and extracts important information such as epicenter information and damage reports.

[0748] 4. The server uses the generative AI model to create a news article stating, "Today's earthquake had its epicenter in XX location, and damage is concentrated in the □□ region."

[0749] 5. The server runs a credibility assessment algorithm to prioritize information from government agencies and trusted media.

[0750] 6. The server launches a future prediction AI model and generates a scenario in which prompt rescue operations are carried out as a "good future" and a scenario in which rescue operations are delayed as a "bad future."

[0751] 7. The server delivers the generated news articles and future prediction scenarios to the user's device.

[0752] 8. The device displays a news notification, which the user taps to view a detailed news article and future prediction scenarios.

[0753] Through the above process, users can not only receive reliable news in real time, but also plan their actions based on future scenarios. Compared to conventional news distribution methods, this system provides faster and more reliable information, increasing user peace of mind and convenience.

[0754] The processing flow will be explained below.

[0755] Step 1:

[0756] The server uses social media APIs to collect posts based on specific keywords or hashtags, such as "earthquake" or "earthquake," and performs real-time searches using the Twitter API or Facebook API.

[0757] Step 2:

[0758] The server preprocesses the collected posts, which includes denoising (removing spam and irrelevant posts) and normalizing (lowercasing text, removing special characters, etc.).

[0759] Step 3:

[0760] The server analyzes the preprocessed information, specifically using text mining technology to extract important information (e.g., epicenter, damage status, evacuation shelter information, etc.).

[0761] Step 4:

[0762] The server inputs the extracted information into a generative AI model, which automatically generates news articles. The generative AI model uses a large-scale language model such as GPT-4.

[0763] Step 5:

[0764] The server runs a credibility assessment algorithm on the generated news articles, weighting data from official and trusted sources to calculate a credibility score.

[0765] Step 6:

[0766] The server launches a future prediction model and simulates future scenarios based on the generated news. It simulates both good and bad futures and generates each scenario.

[0767] Step 7:

[0768] The server integrates the generated news articles with future prediction scenarios and formats them in a way that is easy for users to understand.

[0769] Step 8:

[0770] The server delivers news articles and future prediction scenarios to users' devices via push notifications, emails, and other methods.

[0771] Step 9:

[0772] The device displays a news notification to the user, which includes a brief summary and provides a link for the user to view more details.

[0773] Step 10:

[0774] Users can interact with their devices and tap on notifications to view detailed news articles and future scenarios, providing fast and reliable information about current situations and future possibilities.

[0775] Through the above steps, the present invention builds a system that simultaneously provides highly reliable news in real time and makes future predictions.

[0776] Example 1

[0777] 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."

[0778] Conventional news gathering and distribution systems lack the ability to assess the credibility of information or predict the future, which means there is a risk of providing unreliable information to users. Furthermore, the inability to quickly gather and analyze information makes it difficult to provide information in real time, which means users are unable to enjoy peace of mind and convenience.

[0779] 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.

[0780] In this invention, the server

[0781] A means of collecting various information from SNS,

[0782] means for preprocessing the collected information;

[0783] a means for inputting the preprocessed information into a generative AI model to generate news articles;

[0784] a means for assessing the credibility of the generated news articles;

[0785] A means of making future predictions and simulating good and bad news futures;

[0786] A means for delivering news articles and future prediction scenarios to a user terminal;

[0787] This allows users to receive reliable news in real time and plan optimal actions based on future scenarios.

[0788] "SNS" is an abbreviation for social networking service, an online platform that allows users to interact with each other and share information via the Internet.

[0789] "Information collection means" refers to a means for obtaining various information from social media, etc., and is a system that uses an API to automatically collect posts based on specific keywords or hashtags.

[0790] The "preprocessing means" is a means for removing noise and unnecessary data from collected information and for processing the data to standardize its format.

[0791] A "generative AI model" is a large-scale language model trained using machine learning algorithms that automatically generates news articles by inputting preprocessed data.

[0792] A "credibility assessment tool" is an algorithm that evaluates the reliability of generated news articles and is a tool for calculating the reliability score of information sources and selecting highly credible information.

[0793] A "future prediction tool" is an AI model for simulating future scenarios based on generated news, and is a tool for generating good and bad future scenarios.

[0794] The "news distribution means" is a means for transmitting the generated news articles and future prediction scenarios to the user's terminal so that the user can view them.

[0795] This invention is a system that collects various information from social media, analyzes it, and generates news articles in real time. This system utilizes a generative AI model, has a means to evaluate the credibility of the collected information, and provides only highly reliable information. Furthermore, it predicts the future and simulates good and bad news, allowing users to prepare for the worst-case scenario.

[0796] The following configuration will be described as a specific embodiment of the present invention.

[0797] 1. Information gathering methods

[0798] The server uses social media APIs to collect various posts based on specific keywords and hashtags. This collection method is implemented using Python libraries, and social media platforms include Twitter, Facebook, etc. For example, the Tweepy library is used to access the Twitter API and collect information based on keywords such as "earthquake."

[0799] 2. Data preprocessing methods

[0800] The server preprocesses the collected data, removing noise and unnecessary data and standardizing the data format. This preprocessing method includes, for example, removing non-ASCII characters from the collected tweets and standardizing the encoding to UTF-8.

[0801] 3. News article generation method

[0802] The server then inputs the preprocessed data into a generative AI model to generate a news article. This generative AI model is a large-scale language model trained using a machine learning algorithm, such as OpenAI's GPT-3. This method generates a news article such as, "Today's earthquake had its epicenter in XX location, and damage was concentrated in XX region."

[0803] 4. Credibility assessment tools

[0804] The server runs algorithms to assess the credibility of generated news articles, for example calculating a credibility score for each source and prioritizing information from government agencies and reputable media outlets.

[0805] 5. Means of predicting the future

[0806] The server launches an AI model for future prediction, simulating good and bad future scenarios based on the generated news. This future prediction method uses a time series prediction model, such as an LSTM (long short-term memory) model. Specifically, it generates a "scenario in which relief efforts are carried out quickly" and a "scenario in which relief efforts are delayed."

[0807] 6. News distribution methods

[0808] Finally, the server delivers the generated news articles and future prediction scenarios to the user's device. The device displays the received news notification, and the user can tap it to view detailed news articles and future prediction scenarios. This news delivery uses a RESTful API and employs a mechanism to send push notifications to the user's smartphone.

[0809] Prompt Sentence Examples

[0810] Examples of prompts to input to a generative AI model include:

[0811] "Generate reliable news articles based on the latest earthquake information. Include the following information: epicenter, affected areas, and local conditions. Also, generate rescue scenarios as future predictions."

[0812] With the above configuration, users can receive reliable news in real time and plan optimal actions based on future scenarios. This system provides faster and more reliable information than conventional news distribution methods, increasing user peace of mind and convenience.

[0813] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0814] Step 1: Gather information

[0815] The server uses the SNS API to collect posts based on specific keywords and hashtags. For example, a Python library (Tweepy) is used to access the Twitter API and retrieve tweets related to the keywords "earthquake." The input is keywords, hashtags, and SNS API authentication information, and the output is the collected post data.

[0816] Specifically, the server runs the script every hour to retrieve the latest 50 tweets from the Twitter API.

[0817] Step 2: Data Preprocessing

[0818] The data collected by the server is preprocessed. The input is the collected social media post data, and the output is the preprocessed clean data. Specific data processing includes removing noise, deleting non-ASCII characters, and unifying the encoding (UTF-8).

[0819] Specifically, the server creates a data frame using the Panada library and performs cleaning processing.

[0820] Step 3: News article generation

[0821] The server then inputs the preprocessed data into a generative AI model to generate news articles. The input is the preprocessed, clean data, and the output is the generated news article. This is done using a large-scale language model such as OpenAI's GPT-3.

[0822] Specifically, the server inputs preprocessed data into the GPT-3 API and retrieves news articles in the format "Today's earthquake had its epicenter in XX location, and damage is concentrated in the □□ region."

[0823] Step 4: Credibility assessment

[0824] The server evaluates the credibility of the generated news articles. The input is the generated news article, and the output is a news article with a credibility score. To evaluate credibility, an algorithm is used to calculate the credibility score of the source and select information with a high score.

[0825] Specifically, the server identifies government agencies and trusted media sources and runs a scoring algorithm based on them.

[0826] Step 5: Predict the future

[0827] The server generates scenarios using a future prediction AI model. The input is news articles with confidence scores, and the output is good and bad future scenarios. A time series prediction model (e.g., LSTM model) is used to simulate future scenarios.

[0828] Specifically, the server inputs data into the LSTM model and generates a "scenario in which rescue operations are carried out quickly" and a "scenario in which rescue operations are delayed."

[0829] Step 6: News distribution

[0830] The server delivers the generated news articles and future prediction scenarios to the user's device. The input is the generated news articles and future prediction scenarios, and the output is the delivered news notification. Push notifications are sent to the user's smartphone via a RESTful API.

[0831] Specifically, the server sends a notification to the user's smartphone saying, "New earthquake information is available," the device displays the notification, and the user taps it to view a detailed news article and future prediction scenario.

[0832] This series of processing steps allows users to receive reliable news in real time and plan optimal actions based on future scenarios.

[0833] (Application example 1)

[0834] 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."

[0835] In modern society, a large amount of information is circulated in real time through social media, but it is difficult to immediately determine the credibility and accuracy of that information. Furthermore, news articles are required to go beyond simply reporting past and present events and instead provide future scenarios to help users plan their actions more appropriately. Furthermore, content distribution services need to be able to deliver information quickly and reliably to user devices.

[0836] 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.

[0837] In this invention, the server includes means for collecting various information from SNS, means for analyzing the collected information to generate news articles, means for evaluating the credibility of the generated news articles, means for making future predictions and simulating good and bad futures for the news, means for delivering the news articles and future prediction scenarios to user terminals, and means for delivering the news and future prediction scenarios to the user's computer terminals, thereby enabling users to receive highly reliable information in real time and plan for preparations for future events.

[0838] "SNS" stands for Social Networking Service, a web-based platform that enables users to build online communities and networks, share information, and interact.

[0839] "Diverse information" includes all types of data provided in multiple formats, such as text, images, videos, and links.

[0840] "Analysis" is the process of processing and analyzing collected data to understand meaning and patterns in the information.

[0841] A "news article" is a document in article format that compiles and provides information about current events and topics to users.

[0842] "Credibility" is a measure of the accuracy and reliability of information.

[0843] "Forecasting" is the process of estimating future events or scenarios based on collected data.

[0844] "Simulation" is a technical method of modeling real-world events or scenarios and predicting and analyzing their outcomes.

[0845] A "user terminal" is a device that a user uses to directly operate and receive information, and includes a computer, smartphone, tablet, etc.

[0846] "Distribution" refers to the process of transmitting the generated information to a user terminal via a network so that the user can view it.

[0847] A "generative AI model" is a type of machine learning algorithm that uses artificial intelligence techniques to train it to generate useful output from input data.

[0848] A "content distribution system" is a system consisting of a series of hardware and software for distributing generated content to users.

[0849] The present invention is a system that collects various information from social media, analyzes it, and generates news articles in real time. This system utilizes a generative AI model, has a means to evaluate the credibility of the collected information, and provides only highly reliable information. Furthermore, it predicts the future and simulates good and bad news, allowing users to prepare for the worst-case scenario. Specific embodiments of the system are described below.

[0850] The server first uses social media APIs to collect various posts based on specific keywords or hashtags. This includes posts from multiple social media platforms, such as Twitter and Facebook. The collected data is then preprocessed and saved as a large dataset, including noise removal and data normalization.

[0851] The server then uses a generative AI model, such as OpenAI GPT-3, to automatically generate news articles from the preprocessed data. The model can be a machine learning algorithm, and produces news articles with the same quality as human-written text.

[0852] The generated news articles are then evaluated by a credibility assessment algorithm, which calculates a credibility score for each source and selects only those with a credibility score above a certain threshold. For example, information from government agencies or major media outlets is prioritized.

[0853] The server then launches an AI model for future prediction, simulating good and bad future scenarios based on the generated news articles. For this prediction, a time series prediction model is used. For example, based on earthquake information, it generates a scenario in which rescue efforts are carried out quickly and a scenario in which rescue efforts are delayed.

[0854] Finally, the server delivers the generated news articles and future prediction scenarios to user devices, which can include smartphones, computers, tablets, etc. The delivered news can be easily viewed on the user device, and a notification function is also provided if necessary.

[0855] Specific examples

[0856] The user installs a dedicated app and creates an account. The server periodically uses the Twitter API to collect posts related to the keywords "earthquake" and "earthquake." The collected posts are preprocessed to extract important information such as epicenter information and damage reports. The server uses a generative AI model to create a news article stating, "Today's earthquake occurred at an epicenter in XX location, with damage concentrated in the XX region." A credibility assessment algorithm is run to prioritize and select information from government agencies and reliable media. A future prediction AI model is launched to generate a scenario in which prompt relief efforts are carried out as a "good future," and a scenario in which relief efforts are delayed as a "bad future." The generated news article and future prediction scenario are then delivered to the user's device.

[0857] Prompt Sentence Examples

[0858] Generate a news article based on the following information: The epicenter of today's earthquake is in XX location, and damage is concentrated in the □□ area.

[0859] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0860] Step 1:

[0861] The server collects information using a social networking API. Specific keywords or hashtags (e.g., "earthquake" or "earthquake") are specified as input. The server connects to the social networking API (e.g., Twitter API) and collects posts related to these keywords. The collected post data is returned as output.

[0862] Step 2:

[0863] The data collected by the server is preprocessed. The submitted data collected by the server is used as input. Preprocessing includes noise removal (removal of unnecessary information) and data normalization (standardization of text). The preprocessed data is obtained as output.

[0864] Step 3:

[0865] The server automatically generates news articles using a generative AI model. Preprocessed data is given as input to the generative AI model (e.g., OpenAI GPT-3). A prompt (e.g., "Generate a news article based on the following information: Today's earthquake occurred at a certain location, with damage concentrated in the □□ region") is used to generate the news article. The generated news article is obtained as output.

[0866] Step 4:

[0867] The server evaluates the credibility of the generated news article. As input, the generated news article is given to the credibility evaluation algorithm. The algorithm calculates the credibility score of the source and considers it to be reliable if it exceeds a certain threshold. As output, the credibility-evaluated news article is obtained.

[0868] Step 5:

[0869] The server simulates future scenarios using a future prediction AI model. As input, news articles that have passed the credibility assessment are given to the future prediction AI model (time series prediction model). Simulations based on different assumptions are performed to generate good and bad future scenarios. As output, good and bad future scenarios are obtained.

[0870] Step 6:

[0871] The server distributes the generated news articles and future prediction scenarios to the user's device. The generated news articles and future prediction scenarios are used as input. Notifications and distribution are made to the user's device (e.g., smartphone, computer) via the network. As output, the news articles and future prediction scenarios are displayed on the user's device.

[0872] Step 7:

[0873] The user reads news articles and future prediction scenarios and plans appropriate actions. The news articles and future prediction scenarios delivered to the user's device are used as input. The user prepares for future events based on this. The output is the user's planned actions.

[0874] 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.

[0875] This invention is a system that collects diverse information from social media, analyzes it, and generates news articles in real time. This system utilizes a generative AI model, has a means of evaluating the credibility of the collected information, and provides only highly reliable information. Furthermore, it predicts the future and simulates good and bad news scenarios, allowing users to prepare for the worst-case scenario. Additionally, by combining it with an emotion engine that recognizes the user's emotions, it delivers appropriate information according to the user's emotions.

[0876] Program processing overview

[0877] 1. Information gathering methods

[0878] The server uses social media APIs to collect posts based on specific keywords or hashtags, including posts from multiple social media platforms such as Twitter and Facebook.

[0879] 2. Creating news articles using generative AI models

[0880] The server preprocesses the collected data (denoising, normalising) and then inputs it into a generative AI model to automatically generate news articles. The generative AI model uses a large-scale language model such as GPT-4.

[0881] 3. Credibility assessment tools

[0882] The server runs a credibility assessment algorithm on the generated news articles, weighting data from official and trusted sources to calculate a credibility score.

[0883] 4. Means of predicting the future

[0884] The server launches an AI model for future prediction and simulates future scenarios based on the generated news. It simulates both good and bad futures and generates each scenario.

[0885] 5. Emotion Engine

[0886] The server is equipped with an emotion engine that recognizes the user's emotions, and analyzes the emotional impact that collected data and news articles have on the user.

[0887] 6. News distribution methods

[0888] The server delivers the generated news articles and future prediction scenarios to the user's device, and the delivered news is adjusted according to the user's emotions.

[0889] Specific operation example

[0890] 1. The user installs the dedicated app and creates an account.

[0891] 2. The server periodically uses the Twitter API to collect posts related to the keywords "earthquake" or "earthquake."

[0892] 3. The server preprocesses the collected posts and extracts important information such as epicenter information and damage reports.

[0893] 4. The server uses the generative AI model to create a news article stating, "Today's earthquake had its epicenter in XX location, and damage is concentrated in the □□ region."

[0894] 5. The server runs a credibility assessment algorithm to prioritize information from government agencies and trusted media.

[0895] 6. The server launches a future prediction AI model and generates a scenario in which prompt rescue operations are carried out as a "good future" and a scenario in which rescue operations are delayed as a "bad future."

[0896] 7. The server uses an emotion engine to analyze the user's current emotional state and tailor the news article accordingly, for example, emphasizing reassuring information if the user is feeling anxious.

[0897] 8. The server delivers the generated news articles and future prediction scenarios to the user's device. Possible delivery methods include push notifications and emails.

[0898] 9. The device displays a news notification to the user, which includes a brief summary and a link for the user to view more details.

[0899] 10. The user interacts with their device and taps the notification to view a detailed news article and future scenario, providing the user with fast and reliable information about the current situation and future possibilities.

[0900] Through the above process, the present invention not only provides highly reliable news and future predictions in real time, but also uses an emotion engine to deliver information that responds to the user's emotions. It also improves the user experience by providing appropriate feedback on the anxiety and stress the user is feeling. Compared to conventional news delivery methods, this system enables more personalized information delivery, enhancing user peace of mind and convenience.

[0901] The processing flow will be explained below.

[0902] Step 1:

[0903] The server uses social media APIs to collect posts based on specific keywords or hashtags, specifically using the Twitter API or Facebook API to perform real-time searches for keywords like "earthquake."

[0904] Step 2:

[0905] The server preprocesses the collected posts, which includes denoising (removing spam and irrelevant posts) and normalizing (lowercasing text, removing special characters, etc.).

[0906] Step 3:

[0907] The server analyzes the preprocessed information, specifically using text mining technology to extract important information (e.g., epicenter, damage status, evacuation shelter information, etc.).

[0908] Step 4:

[0909] The server inputs the extracted information into a generative AI model, which automatically generates news articles. The generative AI model uses a large-scale language model such as GPT-4.

[0910] Step 5:

[0911] The server runs a credibility assessment algorithm on the generated news articles, which calculates a credibility score for each source and prioritizes data from official institutions and trusted media.

[0912] Step 6:

[0913] The server launches a future prediction model and simulates future scenarios based on the generated news. It simulates both good and bad futures and generates each scenario.

[0914] Step 7:

[0915] The server activates an emotion engine to recognize the user's emotions, which analyzes the user's emotions based on the user's past browsing history and current emotional state.

[0916] Step 8:

[0917] The server uses an emotion engine to tailor the generated news articles, for example, emphasizing more reassuring information if the user is feeling anxious.

[0918] Step 9:

[0919] The server delivers the generated news articles and future prediction scenarios to the user's device via push notifications, email, and other methods.

[0920] Step 10:

[0921] The device displays a news notification to the user, which includes a brief summary and provides a link for the user to view more details.

[0922] Step 11:

[0923] Users interact with their devices and tap the notification to view detailed news articles and future scenarios, providing fast and reliable information about current situations and future possibilities.

[0924] Through these steps, the present invention not only provides reliable news and future predictions in real time, but also uses an emotion engine to deliver information according to the user's emotions. It also improves the user experience by providing appropriate feedback for the anxiety and stress the user is feeling.

[0925] Example 2

[0926] 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."

[0927] Conventional news distribution systems have difficulty in providing reliable information quickly, and do not take into account the emotional state of the user. As a result, the quality of the information users receive is declining, and they are not adequately prepared for future uncertainties.

[0928] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting various information from online platforms, means for preprocessing the collected information and then generating news articles, evaluation means for evaluating the credibility of the generated news articles, means for making future predictions and simulating good and bad news futures, and means for delivering the generated news articles and future prediction scenarios to a user terminal. This makes it possible to provide highly credible news and future predictions, as well as deliver information according to the user's emotions.

[0929] "Online platform" refers to a website or service that provides information or services via the Internet.

[0930] "Means of collecting information" refers to the operations and techniques used to obtain the necessary data from various sources on the Internet.

[0931] "Preprocessing" refers to a series of steps that remove noise from raw data and convert it into a form suitable for analysis and generative models.

[0932] "Means for generating news articles" refers to techniques and operations for automatically creating news articles based on collected and pre-processed data.

[0933] "Evaluation methods" refer to technologies and algorithms used to assess the credibility and accuracy of generated news articles and determine their quality.

[0934] "Methods of forecasting the future" refers to techniques and operations that use current data to predict future scenarios or events.

[0935] "User terminal" refers to a device, such as a smartphone or computer, that a user uses to view news articles and future prediction scenarios.

[0936] An "emotion recognition engine" refers to technology and algorithms that analyze a user's emotional state and optimize information delivery based on the results.

[0937] A "generative AI model" refers to an algorithm or system that uses artificial intelligence techniques to generate natural language text from data.

[0938] A "prompt sentence" is a string or text that is input into a generative AI model, and refers to the instructions for generating a sentence based on that string.

[0939] The present invention is a system that collects various information from online platforms, analyzes it, and generates news articles. Specifically, the system evaluates the credibility of the collected information, makes future predictions, and delivers appropriate news according to the user's emotional state. Specific embodiments for implementing the present invention are described below.

[0940] Information gathering methods

[0941] The server collects information from online platforms, using APIs to retrieve posts from social networking sites such as Twitter and Facebook, for example by searching for specific keywords or hashtags.

[0942] Specific working example:

[0943] The server uses the Twitter API to collect posts containing "earthquake" or "earthquake," using the Twitter API key and secret.

[0944] Data preprocessing and news article generation

[0945] The server preprocesses the collected data, removing noise and normalizing it to extract only the necessary information. The preprocessed data is then input into a generative AI model (e.g., GPT-4) to automatically generate news articles.

[0946] Specific working example:

[0947] The server removes unnecessary links and strings from the collected posts and converts them into text data.

[0948] The server inputs the following prompt sentence to the generated AI model:

[0949] "Generate a news article about today's earthquake. Include epicenter information, damage report, and confirmation from a reliable source."

[0950] Credibility assessment tools

[0951] The server runs a credibility assessment algorithm on the generated news articles, which references data from government agencies and other trusted sources to calculate a credibility score.

[0952] Specific working example:

[0953] The server compares the generated news articles with official government information and calculates a credibility score.

[0954] Future prediction methods

[0955] The server launches an AI model for future prediction and simulates future scenarios based on the generated news, generating a "good future" and a "bad future" as simulation results.

[0956] Specific working example:

[0957] The server generates both scenarios in which rescue efforts are rapid and scenarios in which rescue efforts are delayed.

[0958] Emotion Engine

[0959] The server uses an emotion engine to analyze the user's emotional state, thereby taking into account the emotional impact of collected data and news articles on the user.

[0960] Specific working example:

[0961] The server analyzes the interaction data acquired from the user's device and evaluates the user's current emotional state.

[0962] News distribution methods

[0963] The server delivers the generated news articles and future prediction scenarios to the user's device via push notifications, email, and other methods.

[0964] Specific working example:

[0965] The server sends a news article to the device via push notification as "Breaking News about Today's Earthquake."

[0966] The device will display a notification such as "The epicenter is at XX location. Click here for details."

[0967] User Interface

[0968] Users can tap on the notification to view a detailed news article and future scenarios, providing fast and reliable information about current conditions and future possibilities.

[0969] Specific working example:

[0970] Users can understand the situation by opening the news app and reading the generated news articles and future prediction scenarios.

[0971] As described above, the present invention realizes highly reliable news provision and future predictions, as well as personalized information delivery according to the user's emotions.

[0972] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0973] Step 1: Gather information

[0974] The server collects information from online platforms, using APIs to retrieve posts containing specific keywords or hashtags from social media platforms such as Twitter and Facebook.

[0975] Input: A specific keyword or hashtag (e.g., "earthquake").

[0976] Output: Collected social media post data.

[0977] Specific behavior:

[0978] The server authenticates using the Twitter API key and secret.

[0979] The server retrieves posts containing "earthquake" or "earthquake" and stores them in a database.

[0980] Step 2: Preprocessing the data

[0981] The server preprocesses the collected data, performing noise reduction and normalization to remove unnecessary information.

[0982] Input: Collected social media posting data.

[0983] Output: Preprocessed and clean data.

[0984] Specific behavior:

[0985] The server removes URLs and unnecessary strings from the collected posts.

[0986] The server normalizes the post and reformats it as text data.

[0987] Step 3: News article generation

[0988] The server uses a generative AI model (e.g., GPT-4) to generate news articles based on the preprocessed data.

[0989] Input: Preprocessed data, prompt (e.g., "Generate a news article about today's earthquake. Include epicenter information, damage report, and confirmation from a reliable source.").

[0990] Output: The generated news article.

[0991] Specific behavior:

[0992] The server inputs the preprocessed data into the generative AI model.

[0993] The server generates a news article using the prompt text.

[0994] Step 4: Credibility assessment

[0995] The server applies a credibility assessment algorithm to assess the credibility of the generated news article by comparing it with official and trusted sources.

[0996] Input: Generated news articles.

[0997] Output: News articles with credibility scores.

[0998] Specific behavior:

[0999] The server compares the generated news articles with official government information.

[1000] The server calculates an authenticity score and assigns it to the article.

[1001] Step 5: Predict the future

[1002] The server uses a future prediction AI model to simulate future scenarios based on the generated news, generating both good and bad futures.

[1003] Input: News articles with credibility scores.

[1004] Output: Future prediction scenario.

[1005] Specific behavior:

[1006] The server generates scenarios in which prompt rescue operations are carried out and scenarios in which rescue operations are delayed.

[1007] Step 6: Emotion Recognition

[1008] The server uses an emotion engine to analyze the user's emotional state, which determines what information is most useful to the user.

[1009] Input: Interaction data from the user device.

[1010] Output: Information provision plan according to the user's emotional state.

[1011] Specific behavior:

[1012] The server analyzes the user's browsing history and interaction data to assess their current emotional state.

[1013] Step 7: News distribution

[1014] The server generates news articles and future prediction scenarios and delivers them to the device according to the user's emotional state, using methods such as push notifications and emails.

[1015] Input: Information provision plans based on the user's emotional state, news articles, and future prediction scenarios.

[1016] Output: News articles and future prediction scenarios delivered to the user's device.

[1017] Specific behavior:

[1018] The server sends a news article to the device via push notification as "Breaking News about Today's Earthquake."

[1019] The device will display a notification such as "The epicenter is at XX location. Click here for details."

[1020] Step 8: Read the news article

[1021] Users interact with their devices and tap the notification to view detailed news articles and future scenarios, providing fast and reliable information about current situations and future possibilities.

[1022] Enter: news notifications on your device.

[1023] Output: A detailed news article and future scenarios for the user to view.

[1024] Specific behavior:

[1025] Users can understand the situation by opening the news app and reading the generated news articles and future prediction scenarios.

[1026] (Application example 2)

[1027] 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."

[1028] Conventional news distribution systems have not always provided a good user experience because the reliability of the information is uncertain and they are unable to provide information that reflects the user's emotions. In addition, there are only a limited number of systems that provide future predictions, making it difficult for users to predict and prepare for the future.

[1029] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting various information from SNS, means for analyzing the collected information to generate news articles, means for evaluating the credibility of the generated news articles, means for making future predictions and simulating good and bad news futures, means for recognizing user emotions and adjusting news articles in accordance with those emotions, and means for delivering news articles and future prediction scenarios to the user terminal. This enables the provision of highly reliable information in real time and personalized news delivery in accordance with the user's emotions.

[1030] "Means of collecting diverse information from social media" refers to a method of using social media APIs to collect posts based on specific keywords or hashtags.

[1031] "Means of analyzing collected information to generate news articles" refers to methods of preprocessing collected data and automatically creating news articles using generative AI models.

[1032] "Method for assessing the credibility of generated news articles" refers to a method for applying a credibility assessment algorithm to generated news articles and calculating a credibility score based on data from official institutions and reliable sources.

[1033] "Means for making future predictions and simulating good and bad news scenarios" refers to a method for simulating both good and bad future scenarios based on news generated using a future prediction AI model.

[1034] "Means for recognizing users' emotions and adjusting news articles according to those emotions" refers to a method of using an emotion engine to analyze a user's current emotional state and adjust the content and delivery method of news articles according to those emotions.

[1035] "Means for delivering news articles and future prediction scenarios to user devices" refers to methods for delivering the generated news articles and future prediction scenarios to users' devices and notifying them via push notifications or email.

[1036] The system for implementing the invention aims to collect various information from social media, generate news articles using a generative AI model, evaluate their credibility, make future predictions, and then deliver information based on user sentiment. The detailed process is described below.

[1037] The server uses social media APIs to collect posts based on specific keywords or hashtags. It can obtain data from major social media platforms such as Twitter and Facebook. This allows the server to collect the latest information in real time and preprocess the data.

[1038] The server then analyzes the collected data and automatically generates news articles using a generative AI model (e.g., GPT-4). The preprocessed data is tokenized and fed into the generative AI model, which generates news articles in natural language based on the input data.

[1039] The server then runs a credibility assessment algorithm on the generated news articles, which takes into account data from official and trusted sources and calculates a credibility score. Information with a higher credibility score is considered more trustworthy.

[1040] The server runs a future-prediction AI model that simulates both good and bad future scenarios based on the generated news. For example, in the case of a natural disaster, it generates scenarios in which rescue efforts are swift and in which they are delayed.

[1041] The server also has a built-in emotion engine that recognizes users' emotions and adjusts news articles accordingly. The emotion engine analyzes the user's current emotional state and adjusts the content and delivery method of the news article accordingly. For example, if the user is feeling anxious, it will emphasize information that will reassure them.

[1042] The server delivers the generated news articles and future prediction scenarios to the user's device. Possible delivery methods include push notifications and emails. The user's device displays a news notification containing a brief summary and a link to view the detailed news article and future prediction scenario.

[1043] As a concrete example, when collecting earthquake information, a user searches for the keyword "earthquake." The server uses the Twitter API to collect related posts and generates a news article based on them. It then evaluates their credibility and predicts future good scenarios (quick rescue) and bad scenarios (delayed rescue operations). If the user's emotional state is "anxious," the server will prioritize delivering information that provides reassurance.

[1044] This approach enables real-time, reliable information delivery and personalized news delivery based on user sentiment.

[1045] An example prompt is:

[1046] "Get the latest earthquake information from current tweets."

[1047] "Generate news articles from this data."

[1048] "Evaluate the credibility of the news generated."

[1049] "Based on this, predict good and bad scenarios for the future."

[1050] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1051] Step 1:

[1052] The server uses a social media API (e.g., Twitter API) to collect posts based on a specific keyword (e.g., "earthquake") or hashtag. At this point, it sends an API request to retrieve the relevant post data. The input is the social media API endpoint and keyword, and the output is the collected post data.

[1053] Step 2:

[1054] The server preprocesses the collected submission data. This includes noise removal and data normalization. For example, it removes unnecessary symbols and links and extracts important information (e.g., place names, damage information). The input is the collected submission data, and the output is the preprocessed, clean data.

[1055] Step 3:

[1056] The server feeds the preprocessed data to a generative AI model (e.g., GPT-4) to automatically generate news articles. It uses a tokenizer to tokenize the data and input it into the generative AI model. It decodes and outputs the news articles generated by the model. The input is the preprocessed data, and the output is the generated news articles.

[1057] Step 4:

[1058] The server runs a credibility assessment algorithm on the generated news articles. The algorithm calculates a credibility score based on data obtained from official and trusted sources. The input is the generated news article, and the output is the news article with the assigned credibility score.

[1059] Step 5:

[1060] The server runs a future prediction AI model based on news articles that have undergone credibility assessment, simulating both positive and negative future scenarios. For example, it predicts the impact of rapid relief efforts versus delays. The input is news articles with credibility scores, and the output is future prediction scenarios.

[1061] Step 6:

[1062] The server uses an emotion engine to analyze the user's emotional state and adjust the news article accordingly. For example, if the user is feeling anxious, it will emphasize reassuring information. The input is the user's emotional data and a news article, and the output is a news article adjusted according to the emotion.

[1063] Step 7:

[1064] The server delivers the final adjusted news article and future prediction scenario to the user's device. The device displays a news notification to the user, which includes a brief summary and a link to a detailed article. The input is the adjusted news article and future prediction scenario, and the output is the notification displayed on the user's device.

[1065] 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.

[1066] 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.

[1067] 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.

[1068] [Fourth embodiment]

[1069] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1070] 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.

[1071] 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).

[1072] 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.

[1073] 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.

[1074] 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).

[1075] 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.

[1076] 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.

[1077] 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.

[1078] 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.

[1079] 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.

[1080] 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.

[1081] 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."

[1082] This invention is a system that collects various information from social media, analyzes it, and generates news articles in real time. The system utilizes a generative AI model, has a means to evaluate the credibility of the collected information, and provides only highly reliable information. Furthermore, it predicts the future and simulates good and bad news, allowing users to prepare for the worst-case scenario.

[1083] Program processing overview

[1084] 1. Information gathering methods

[1085] The server uses social media APIs to collect various posts based on specific keywords or hashtags, including those from multiple social media platforms such as Twitter and Facebook.

[1086] 2. Creating news articles using generative AI models

[1087] The server preprocesses the collected data (denoising, normalising) and then inputs it into a generative AI model to automatically generate news articles. The generative AI model uses a large-scale language model trained with machine learning algorithms.

[1088] 3. Credibility assessment tools

[1089] The server runs a credibility assessment algorithm on the generated news articles, which calculates a credibility score for each source and selects the most credible information.

[1090] 4. Means of predicting the future

[1091] The server launches an AI model for future prediction, simulating good and bad future scenarios based on the generated news, using a time series forecasting model.

[1092] 5. News distribution methods

[1093] The server delivers the generated news articles and future prediction scenarios to the user's device, where the user can view the delivered news.

[1094] Specific operation example

[1095] 1. The user installs the dedicated app and creates an account.

[1096] 2. The server periodically uses the Twitter API to collect posts related to the keywords "earthquake" or "earthquake."

[1097] 3. The server preprocesses the collected posts and extracts important information such as epicenter information and damage reports.

[1098] 4. The server uses the generative AI model to create a news article stating, "Today's earthquake had its epicenter in XX location, and damage is concentrated in the □□ region."

[1099] 5. The server runs a credibility assessment algorithm to prioritize information from government agencies and trusted media.

[1100] 6. The server launches a future prediction AI model and generates a scenario in which prompt rescue operations are carried out as a "good future" and a scenario in which rescue operations are delayed as a "bad future."

[1101] 7. The server delivers the generated news articles and future prediction scenarios to the user's device.

[1102] 8. The device displays a news notification, which the user taps to view a detailed news article and future prediction scenarios.

[1103] Through the above process, users can not only receive reliable news in real time, but also plan their actions based on future scenarios. Compared to conventional news distribution methods, this system provides faster and more reliable information, increasing user peace of mind and convenience.

[1104] The processing flow will be explained below.

[1105] Step 1:

[1106] The server uses social media APIs to collect posts based on specific keywords or hashtags, such as "earthquake" or "earthquake," and performs real-time searches using the Twitter API or Facebook API.

[1107] Step 2:

[1108] The server preprocesses the collected posts, which includes denoising (removing spam and irrelevant posts) and normalizing (lowercasing text, removing special characters, etc.).

[1109] Step 3:

[1110] The server analyzes the preprocessed information, specifically using text mining technology to extract important information (e.g., epicenter, damage status, evacuation shelter information, etc.).

[1111] Step 4:

[1112] The server inputs the extracted information into a generative AI model, which automatically generates news articles. The generative AI model uses a large-scale language model such as GPT-4.

[1113] Step 5:

[1114] The server runs a credibility assessment algorithm on the generated news articles, weighting data from official and trusted sources to calculate a credibility score.

[1115] Step 6:

[1116] The server launches a future prediction model and simulates future scenarios based on the generated news. It simulates both good and bad futures and generates each scenario.

[1117] Step 7:

[1118] The server integrates the generated news articles with future prediction scenarios and formats them in a way that is easy for users to understand.

[1119] Step 8:

[1120] The server delivers news articles and future prediction scenarios to users' devices via push notifications, emails, and other methods.

[1121] Step 9:

[1122] The device displays a news notification to the user, which includes a brief summary and provides a link for the user to view more details.

[1123] Step 10:

[1124] Users can interact with their devices and tap on notifications to view detailed news articles and future scenarios, providing fast and reliable information about current situations and future possibilities.

[1125] Through the above steps, the present invention builds a system that simultaneously provides highly reliable news in real time and makes future predictions.

[1126] Example 1

[1127] 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."

[1128] Conventional news gathering and distribution systems lack the ability to assess the credibility of information or predict the future, which means there is a risk of providing unreliable information to users. Furthermore, the inability to quickly gather and analyze information makes it difficult to provide information in real time, which means users are unable to enjoy peace of mind and convenience.

[1129] 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.

[1130] In this invention, the server

[1131] A means of collecting various information from SNS,

[1132] means for preprocessing the collected information;

[1133] a means for inputting the preprocessed information into a generative AI model to generate news articles;

[1134] a means for assessing the credibility of the generated news articles;

[1135] A means of making future predictions and simulating good and bad news futures;

[1136] A means for delivering news articles and future prediction scenarios to a user terminal;

[1137] This allows users to receive reliable news in real time and plan optimal actions based on future scenarios.

[1138] "SNS" is an abbreviation for social networking service, an online platform that allows users to interact with each other and share information via the Internet.

[1139] "Information collection means" refers to a means for obtaining various information from social media, etc., and is a system that uses an API to automatically collect posts based on specific keywords or hashtags.

[1140] The "preprocessing means" is a means for removing noise and unnecessary data from collected information and for processing the data to standardize its format.

[1141] A "generative AI model" is a large-scale language model trained using machine learning algorithms that automatically generates news articles by inputting preprocessed data.

[1142] A "credibility assessment tool" is an algorithm that evaluates the reliability of generated news articles and is a tool for calculating the reliability score of information sources and selecting highly credible information.

[1143] A "future prediction tool" is an AI model for simulating future scenarios based on generated news, and is a tool for generating good and bad future scenarios.

[1144] The "news distribution means" is a means for transmitting the generated news articles and future prediction scenarios to the user's terminal so that the user can view them.

[1145] This invention is a system that collects various information from social media, analyzes it, and generates news articles in real time. This system utilizes a generative AI model, has a means to evaluate the credibility of the collected information, and provides only highly reliable information. Furthermore, it predicts the future and simulates good and bad news, allowing users to prepare for the worst-case scenario.

[1146] The following configuration will be described as a specific embodiment of the present invention.

[1147] 1. Information gathering methods

[1148] The server uses social media APIs to collect various posts based on specific keywords and hashtags. This collection method is implemented using Python libraries, and social media platforms include Twitter, Facebook, etc. For example, the Tweepy library is used to access the Twitter API and collect information based on keywords such as "earthquake."

[1149] 2. Data preprocessing methods

[1150] The server preprocesses the collected data, removing noise and unnecessary data and standardizing the data format. This preprocessing method includes, for example, removing non-ASCII characters from the collected tweets and standardizing the encoding to UTF-8.

[1151] 3. News article generation method

[1152] The server then inputs the preprocessed data into a generative AI model to generate a news article. This generative AI model is a large-scale language model trained using a machine learning algorithm, such as OpenAI's GPT-3. This method generates a news article such as, "Today's earthquake had its epicenter in XX location, and damage was concentrated in XX region."

[1153] 4. Credibility assessment tools

[1154] The server runs algorithms to assess the credibility of generated news articles, for example calculating a credibility score for each source and prioritizing information from government agencies and reputable media outlets.

[1155] 5. Means of predicting the future

[1156] The server launches an AI model for future prediction, simulating good and bad future scenarios based on the generated news. This future prediction method uses a time series prediction model, such as an LSTM (long short-term memory) model. Specifically, it generates a "scenario in which relief efforts are carried out quickly" and a "scenario in which relief efforts are delayed."

[1157] 6. News distribution methods

[1158] Finally, the server delivers the generated news articles and future prediction scenarios to the user's device. The device displays the received news notification, and the user can tap it to view detailed news articles and future prediction scenarios. This news delivery uses a RESTful API and employs a mechanism to send push notifications to the user's smartphone.

[1159] Prompt Sentence Examples

[1160] Examples of prompts to input to a generative AI model include:

[1161] "Generate reliable news articles based on the latest earthquake information. Include the following information: epicenter, affected areas, and local conditions. Also, generate rescue scenarios as future predictions."

[1162] With the above configuration, users can receive reliable news in real time and plan optimal actions based on future scenarios. This system provides faster and more reliable information than conventional news distribution methods, increasing user peace of mind and convenience.

[1163] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1164] Step 1: Gather information

[1165] The server uses the SNS API to collect posts based on specific keywords and hashtags. For example, a Python library (Tweepy) is used to access the Twitter API and retrieve tweets related to the keywords "earthquake." The input is keywords, hashtags, and SNS API authentication information, and the output is the collected post data.

[1166] Specifically, the server runs the script every hour to retrieve the latest 50 tweets from the Twitter API.

[1167] Step 2: Data Preprocessing

[1168] The data collected by the server is preprocessed. The input is the collected social media post data, and the output is the preprocessed clean data. Specific data processing includes removing noise, deleting non-ASCII characters, and unifying the encoding (UTF-8).

[1169] Specifically, the server creates a data frame using the Panada library and performs cleaning processing.

[1170] Step 3: News article generation

[1171] The server then inputs the preprocessed data into a generative AI model to generate news articles. The input is the preprocessed, clean data, and the output is the generated news article. This is done using a large-scale language model such as OpenAI's GPT-3.

[1172] Specifically, the server inputs preprocessed data into the GPT-3 API and retrieves news articles in the format "Today's earthquake had its epicenter in XX location, and damage is concentrated in the □□ region."

[1173] Step 4: Credibility assessment

[1174] The server evaluates the credibility of the generated news articles. The input is the generated news article, and the output is a news article with a credibility score. To evaluate credibility, an algorithm is used to calculate the credibility score of the source and select information with a high score.

[1175] Specifically, the server identifies government agencies and trusted media sources and runs a scoring algorithm based on them.

[1176] Step 5: Predict the future

[1177] The server generates scenarios using a future prediction AI model. The input is news articles with confidence scores, and the output is good and bad future scenarios. A time series prediction model (e.g., LSTM model) is used to simulate future scenarios.

[1178] Specifically, the server inputs data into the LSTM model and generates a "scenario in which rescue operations are carried out quickly" and a "scenario in which rescue operations are delayed."

[1179] Step 6: News distribution

[1180] The server delivers the generated news articles and future prediction scenarios to the user's device. The input is the generated news articles and future prediction scenarios, and the output is the delivered news notification. Push notifications are sent to the user's smartphone via a RESTful API.

[1181] Specifically, the server sends a notification to the user's smartphone saying, "New earthquake information is available," the device displays the notification, and the user taps it to view a detailed news article and future prediction scenario.

[1182] This series of processing steps allows users to receive reliable news in real time and plan optimal actions based on future scenarios.

[1183] (Application example 1)

[1184] 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."

[1185] In modern society, a large amount of information is circulated in real time through social media, but it is difficult to immediately determine the credibility and accuracy of that information. Furthermore, news articles are required to go beyond simply reporting past and present events and instead provide future scenarios to help users plan their actions more appropriately. Furthermore, content distribution services need to be able to deliver information quickly and reliably to user devices.

[1186] 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.

[1187] In this invention, the server includes means for collecting various information from SNS, means for analyzing the collected information to generate news articles, means for evaluating the credibility of the generated news articles, means for making future predictions and simulating good and bad futures for the news, means for delivering the news articles and future prediction scenarios to user terminals, and means for delivering the news and future prediction scenarios to the user's computer terminals, thereby enabling users to receive highly reliable information in real time and plan for preparations for future events.

[1188] "SNS" stands for Social Networking Service, a web-based platform that enables users to build online communities and networks, share information, and interact.

[1189] "Diverse information" includes all types of data provided in multiple formats, such as text, images, videos, and links.

[1190] "Analysis" is the process of processing and analyzing collected data to understand meaning and patterns in the information.

[1191] A "news article" is a document in article format that compiles and provides information about current events and topics to users.

[1192] "Credibility" is a measure of the accuracy and reliability of information.

[1193] "Forecasting" is the process of estimating future events or scenarios based on collected data.

[1194] "Simulation" is a technical method of modeling real-world events or scenarios and predicting and analyzing their outcomes.

[1195] A "user terminal" is a device that a user uses to directly operate and receive information, and includes a computer, smartphone, tablet, etc.

[1196] "Distribution" refers to the process of transmitting the generated information to a user terminal via a network so that the user can view it.

[1197] A "generative AI model" is a type of machine learning algorithm that uses artificial intelligence techniques to train it to generate useful output from input data.

[1198] A "content distribution system" is a system consisting of a series of hardware and software for distributing generated content to users.

[1199] The present invention is a system that collects various information from social media, analyzes it, and generates news articles in real time. This system utilizes a generative AI model, has a means to evaluate the credibility of the collected information, and provides only highly reliable information. Furthermore, it predicts the future and simulates good and bad news, allowing users to prepare for the worst-case scenario. Specific embodiments of the system are described below.

[1200] The server first uses social media APIs to collect various posts based on specific keywords or hashtags. This includes posts from multiple social media platforms, such as Twitter and Facebook. The collected data is then preprocessed and saved as a large dataset, including noise removal and data normalization.

[1201] The server then uses a generative AI model, such as OpenAI GPT-3, to automatically generate news articles from the preprocessed data. The model can be a machine learning algorithm, and produces news articles with the same quality as human-written text.

[1202] The generated news articles are then evaluated by a credibility assessment algorithm, which calculates a credibility score for each source and selects only those with a credibility score above a certain threshold. For example, information from government agencies or major media outlets is prioritized.

[1203] The server then launches an AI model for future prediction, simulating good and bad future scenarios based on the generated news articles. For this prediction, a time series prediction model is used. For example, based on earthquake information, it generates a scenario in which rescue efforts are carried out quickly and a scenario in which rescue efforts are delayed.

[1204] Finally, the server delivers the generated news articles and future prediction scenarios to user devices, which can include smartphones, computers, tablets, etc. The delivered news can be easily viewed on the user device, and a notification function is also provided if necessary.

[1205] Specific examples

[1206] The user installs a dedicated app and creates an account. The server periodically uses the Twitter API to collect posts related to the keywords "earthquake" and "earthquake." The collected posts are preprocessed to extract important information such as epicenter information and damage reports. The server uses a generative AI model to create a news article stating, "Today's earthquake occurred at an epicenter in XX location, with damage concentrated in the XX region." A credibility assessment algorithm is run to prioritize and select information from government agencies and reliable media. A future prediction AI model is launched to generate a scenario in which prompt relief efforts are carried out as a "good future," and a scenario in which relief efforts are delayed as a "bad future." The generated news article and future prediction scenario are then delivered to the user's device.

[1207] Prompt Sentence Examples

[1208] Generate a news article based on the following information: The epicenter of today's earthquake is in XX location, and damage is concentrated in the □□ area.

[1209] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1210] Step 1:

[1211] The server collects information using a social networking API. Specific keywords or hashtags (e.g., "earthquake" or "earthquake") are specified as input. The server connects to the social networking API (e.g., Twitter API) and collects posts related to these keywords. The collected post data is returned as output.

[1212] Step 2:

[1213] The data collected by the server is preprocessed. The submitted data collected by the server is used as input. Preprocessing includes noise removal (removal of unnecessary information) and data normalization (standardization of text). The preprocessed data is obtained as output.

[1214] Step 3:

[1215] The server automatically generates news articles using a generative AI model. Preprocessed data is given as input to the generative AI model (e.g., OpenAI GPT-3). A prompt (e.g., "Generate a news article based on the following information: Today's earthquake occurred at a certain location, with damage concentrated in the □□ region") is used to generate the news article. The generated news article is obtained as output.

[1216] Step 4:

[1217] The server evaluates the credibility of the generated news article. As input, the generated news article is given to the credibility evaluation algorithm. The algorithm calculates the credibility score of the source and considers it to be reliable if it exceeds a certain threshold. As output, the credibility-evaluated news article is obtained.

[1218] Step 5:

[1219] The server simulates future scenarios using a future prediction AI model. As input, news articles that have passed the credibility assessment are given to the future prediction AI model (time series prediction model). Simulations based on different assumptions are performed to generate good and bad future scenarios. As output, good and bad future scenarios are obtained.

[1220] Step 6:

[1221] The server distributes the generated news articles and future prediction scenarios to the user's device. The generated news articles and future prediction scenarios are used as input. Notifications and distribution are made to the user's device (e.g., smartphone, computer) via the network. As output, the news articles and future prediction scenarios are displayed on the user's device.

[1222] Step 7:

[1223] The user reads news articles and future prediction scenarios and plans appropriate actions. The news articles and future prediction scenarios delivered to the user's device are used as input. The user prepares for future events based on this. The output is the user's planned actions.

[1224] 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.

[1225] This invention is a system that collects diverse information from social media, analyzes it, and generates news articles in real time. This system utilizes a generative AI model, has a means of evaluating the credibility of the collected information, and provides only highly reliable information. Furthermore, it predicts the future and simulates good and bad news scenarios, allowing users to prepare for the worst-case scenario. Additionally, by combining it with an emotion engine that recognizes the user's emotions, it delivers appropriate information according to the user's emotions.

[1226] Program processing overview

[1227] 1. Information gathering methods

[1228] The server uses social media APIs to collect posts based on specific keywords or hashtags, including posts from multiple social media platforms such as Twitter and Facebook.

[1229] 2. Creating news articles using generative AI models

[1230] The server preprocesses the collected data (denoising, normalising) and then inputs it into a generative AI model to automatically generate news articles. The generative AI model uses a large-scale language model such as GPT-4.

[1231] 3. Credibility assessment tools

[1232] The server runs a credibility assessment algorithm on the generated news articles, weighting data from official and trusted sources to calculate a credibility score.

[1233] 4. Means of predicting the future

[1234] The server launches an AI model for future prediction and simulates future scenarios based on the generated news. It simulates both good and bad futures and generates each scenario.

[1235] 5. Emotion Engine

[1236] The server is equipped with an emotion engine that recognizes the user's emotions, and analyzes the emotional impact that collected data and news articles have on the user.

[1237] 6. News distribution methods

[1238] The server delivers the generated news articles and future prediction scenarios to the user's device, and the delivered news is adjusted according to the user's emotions.

[1239] Specific operation example

[1240] 1. The user installs the dedicated app and creates an account.

[1241] 2. The server periodically uses the Twitter API to collect posts related to the keywords "earthquake" or "earthquake."

[1242] 3. The server preprocesses the collected posts and extracts important information such as epicenter information and damage reports.

[1243] 4. The server uses the generative AI model to create a news article stating, "Today's earthquake had its epicenter in XX location, and damage is concentrated in the □□ region."

[1244] 5. The server runs a credibility assessment algorithm to prioritize information from government agencies and trusted media.

[1245] 6. The server launches a future prediction AI model and generates a scenario in which prompt rescue operations are carried out as a "good future" and a scenario in which rescue operations are delayed as a "bad future."

[1246] 7. The server uses an emotion engine to analyze the user's current emotional state and tailor the news article accordingly, for example, emphasizing reassuring information if the user is feeling anxious.

[1247] 8. The server delivers the generated news articles and future prediction scenarios to the user's device. Possible delivery methods include push notifications and emails.

[1248] 9. The device displays a news notification to the user, which includes a brief summary and a link for the user to view more details.

[1249] 10. The user interacts with their device and taps the notification to view a detailed news article and future scenario, providing the user with fast and reliable information about the current situation and future possibilities.

[1250] Through the above process, the present invention not only provides highly reliable news and future predictions in real time, but also uses an emotion engine to deliver information that responds to the user's emotions. It also improves the user experience by providing appropriate feedback on the anxiety and stress the user is feeling. Compared to conventional news delivery methods, this system enables more personalized information delivery, enhancing user peace of mind and convenience.

[1251] The processing flow will be explained below.

[1252] Step 1:

[1253] The server uses social media APIs to collect posts based on specific keywords or hashtags, specifically using the Twitter API or Facebook API to perform real-time searches for keywords like "earthquake."

[1254] Step 2:

[1255] The server preprocesses the collected posts, which includes denoising (removing spam and irrelevant posts) and normalizing (lowercasing text, removing special characters, etc.).

[1256] Step 3:

[1257] The server analyzes the preprocessed information, specifically using text mining technology to extract important information (e.g., epicenter, damage status, evacuation shelter information, etc.).

[1258] Step 4:

[1259] The server inputs the extracted information into a generative AI model, which automatically generates news articles. The generative AI model uses a large-scale language model such as GPT-4.

[1260] Step 5:

[1261] The server runs a credibility assessment algorithm on the generated news articles, which calculates a credibility score for each source and prioritizes data from official institutions and trusted media.

[1262] Step 6:

[1263] The server launches a future prediction model and simulates future scenarios based on the generated news. It simulates both good and bad futures and generates each scenario.

[1264] Step 7:

[1265] The server activates an emotion engine to recognize the user's emotions, which analyzes the user's emotions based on the user's past browsing history and current emotional state.

[1266] Step 8:

[1267] The server uses an emotion engine to tailor the generated news articles, for example, emphasizing more reassuring information if the user is feeling anxious.

[1268] Step 9:

[1269] The server delivers the generated news articles and future prediction scenarios to the user's device via push notifications, email, and other methods.

[1270] Step 10:

[1271] The device displays a news notification to the user, which includes a brief summary and provides a link for the user to view more details.

[1272] Step 11:

[1273] Users interact with their devices and tap the notification to view detailed news articles and future scenarios, providing fast and reliable information about current situations and future possibilities.

[1274] Through these steps, the present invention not only provides reliable news and future predictions in real time, but also uses an emotion engine to deliver information according to the user's emotions. It also improves the user experience by providing appropriate feedback for the anxiety and stress the user is feeling.

[1275] Example 2

[1276] 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."

[1277] Conventional news distribution systems have difficulty in providing reliable information quickly, and do not take into account the emotional state of the user. As a result, the quality of the information users receive is declining, and they are not adequately prepared for future uncertainties.

[1278] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting various information from online platforms, means for preprocessing the collected information and then generating news articles, evaluation means for evaluating the credibility of the generated news articles, means for making future predictions and simulating good and bad news futures, and means for delivering the generated news articles and future prediction scenarios to a user terminal. This makes it possible to provide highly credible news and future predictions, as well as deliver information according to the user's emotions.

[1279] "Online platform" refers to a website or service that provides information or services via the Internet.

[1280] "Means of collecting information" refers to the operations and techniques used to obtain the necessary data from various sources on the Internet.

[1281] "Preprocessing" refers to a series of steps that remove noise from raw data and convert it into a form suitable for analysis and generative models.

[1282] "Means for generating news articles" refers to techniques and operations for automatically creating news articles based on collected and pre-processed data.

[1283] "Evaluation methods" refer to technologies and algorithms used to assess the credibility and accuracy of generated news articles and determine their quality.

[1284] "Methods of forecasting the future" refers to techniques and operations that use current data to predict future scenarios or events.

[1285] "User terminal" refers to a device, such as a smartphone or computer, that a user uses to view news articles and future prediction scenarios.

[1286] An "emotion recognition engine" refers to technology and algorithms that analyze a user's emotional state and optimize information delivery based on the results.

[1287] A "generative AI model" refers to an algorithm or system that uses artificial intelligence techniques to generate natural language text from data.

[1288] A "prompt sentence" is a string or text that is input into a generative AI model, and refers to the instructions for generating a sentence based on that string.

[1289] The present invention is a system that collects various information from online platforms, analyzes it, and generates news articles. Specifically, the system evaluates the credibility of the collected information, makes future predictions, and delivers appropriate news according to the user's emotional state. Specific embodiments for implementing the present invention are described below.

[1290] Information gathering methods

[1291] The server collects information from online platforms, using APIs to retrieve posts from social networking sites such as Twitter and Facebook, for example by searching for specific keywords or hashtags.

[1292] Specific working example:

[1293] The server uses the Twitter API to collect posts containing "earthquake" or "earthquake," using the Twitter API key and secret.

[1294] Data preprocessing and news article generation

[1295] The server preprocesses the collected data, removing noise and normalizing it to extract only the necessary information. The preprocessed data is then input into a generative AI model (e.g., GPT-4) to automatically generate news articles.

[1296] Specific working example:

[1297] The server removes unnecessary links and strings from the collected posts and converts them into text data.

[1298] The server inputs the following prompt sentence to the generated AI model:

[1299] "Generate a news article about today's earthquake. Include epicenter information, damage report, and confirmation from a reliable source."

[1300] Credibility assessment tools

[1301] The server runs a credibility assessment algorithm on the generated news articles, which references data from government agencies and other trusted sources to calculate a credibility score.

[1302] Specific working example:

[1303] The server compares the generated news articles with official government information and calculates a credibility score.

[1304] Future prediction methods

[1305] The server launches an AI model for future prediction and simulates future scenarios based on the generated news, generating a "good future" and a "bad future" as simulation results.

[1306] Specific working example:

[1307] The server generates both scenarios in which rescue efforts are rapid and scenarios in which rescue efforts are delayed.

[1308] Emotion Engine

[1309] The server uses an emotion engine to analyze the user's emotional state, thereby taking into account the emotional impact of collected data and news articles on the user.

[1310] Specific working example:

[1311] The server analyzes the interaction data acquired from the user's device and evaluates the user's current emotional state.

[1312] News distribution methods

[1313] The server delivers the generated news articles and future prediction scenarios to the user's device via push notifications, email, and other methods.

[1314] Specific working example:

[1315] The server sends a news article to the device via push notification as "Breaking News about Today's Earthquake."

[1316] The device will display a notification such as "The epicenter is at XX location. Click here for details."

[1317] User Interface

[1318] Users can tap on the notification to view a detailed news article and future scenarios, providing fast and reliable information about current conditions and future possibilities.

[1319] Specific working example:

[1320] Users can understand the situation by opening the news app and reading the generated news articles and future prediction scenarios.

[1321] As described above, the present invention realizes highly reliable news provision and future predictions, as well as personalized information delivery according to the user's emotions.

[1322] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1323] Step 1: Gather information

[1324] The server collects information from online platforms, using APIs to retrieve posts containing specific keywords or hashtags from social media platforms such as Twitter and Facebook.

[1325] Input: A specific keyword or hashtag (e.g., "earthquake").

[1326] Output: Collected social media post data.

[1327] Specific behavior:

[1328] The server authenticates using the Twitter API key and secret.

[1329] The server retrieves posts containing "earthquake" or "earthquake" and stores them in a database.

[1330] Step 2: Preprocessing the data

[1331] The server preprocesses the collected data, performing noise reduction and normalization to remove unnecessary information.

[1332] Input: Collected social media posting data.

[1333] Output: Preprocessed and clean data.

[1334] Specific behavior:

[1335] The server removes URLs and unnecessary strings from the collected posts.

[1336] The server normalizes the post and reformats it as text data.

[1337] Step 3: News article generation

[1338] The server uses a generative AI model (e.g., GPT-4) to generate news articles based on the preprocessed data.

[1339] Input: Preprocessed data, prompt (e.g., "Generate a news article about today's earthquake. Include epicenter information, damage report, and confirmation from a reliable source.").

[1340] Output: The generated news article.

[1341] Specific behavior:

[1342] The server inputs the preprocessed data into the generative AI model.

[1343] The server generates a news article using the prompt text.

[1344] Step 4: Credibility assessment

[1345] The server applies a credibility assessment algorithm to assess the credibility of the generated news article by comparing it with official and trusted sources.

[1346] Input: Generated news articles.

[1347] Output: News articles with credibility scores.

[1348] Specific behavior:

[1349] The server compares the generated news articles with official government information.

[1350] The server calculates an authenticity score and assigns it to the article.

[1351] Step 5: Predict the future

[1352] The server uses a future prediction AI model to simulate future scenarios based on the generated news, generating both good and bad futures.

[1353] Input: News articles with credibility scores.

[1354] Output: Future prediction scenario.

[1355] Specific behavior:

[1356] The server generates scenarios in which prompt rescue operations are carried out and scenarios in which rescue operations are delayed.

[1357] Step 6: Emotion Recognition

[1358] The server uses an emotion engine to analyze the user's emotional state, which determines what information is most useful to the user.

[1359] Input: Interaction data from the user device.

[1360] Output: Information provision plan according to the user's emotional state.

[1361] Specific behavior:

[1362] The server analyzes the user's browsing history and interaction data to assess their current emotional state.

[1363] Step 7: News distribution

[1364] The server generates news articles and future prediction scenarios and delivers them to the device according to the user's emotional state, using methods such as push notifications and emails.

[1365] Input: Information provision plans based on the user's emotional state, news articles, and future prediction scenarios.

[1366] Output: News articles and future prediction scenarios delivered to the user's device.

[1367] Specific behavior:

[1368] The server sends a news article to the device via push notification as "Breaking News about Today's Earthquake."

[1369] The device will display a notification such as "The epicenter is at XX location. Click here for details."

[1370] Step 8: Read the news article

[1371] Users interact with their devices and tap the notification to view detailed news articles and future scenarios, providing fast and reliable information about current situations and future possibilities.

[1372] Enter: news notifications on your device.

[1373] Output: A detailed news article and future scenarios for the user to view.

[1374] Specific behavior:

[1375] Users can understand the situation by opening the news app and reading the generated news articles and future prediction scenarios.

[1376] (Application example 2)

[1377] 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."

[1378] Conventional news distribution systems have not always provided a good user experience because the reliability of the information is uncertain and they are unable to provide information that reflects the user's emotions. In addition, there are only a limited number of systems that provide future predictions, making it difficult for users to predict and prepare for the future.

[1379] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting various information from SNS, means for analyzing the collected information to generate news articles, means for evaluating the credibility of the generated news articles, means for making future predictions and simulating good and bad news futures, means for recognizing user emotions and adjusting news articles in accordance with those emotions, and means for delivering news articles and future prediction scenarios to the user terminal. This enables the provision of highly reliable information in real time and personalized news delivery in accordance with the user's emotions.

[1380] "Means of collecting diverse information from social media" refers to a method of using social media APIs to collect posts based on specific keywords or hashtags.

[1381] "Means of analyzing collected information to generate news articles" refers to methods of preprocessing collected data and automatically creating news articles using generative AI models.

[1382] "Method for assessing the credibility of generated news articles" refers to a method for applying a credibility assessment algorithm to generated news articles and calculating a credibility score based on data from official institutions and reliable sources.

[1383] "Means for making future predictions and simulating good and bad news scenarios" refers to a method for simulating both good and bad future scenarios based on news generated using a future prediction AI model.

[1384] "Means for recognizing users' emotions and adjusting news articles according to those emotions" refers to a method of using an emotion engine to analyze a user's current emotional state and adjust the content and delivery method of news articles according to those emotions.

[1385] "Means for delivering news articles and future prediction scenarios to user devices" refers to methods for delivering the generated news articles and future prediction scenarios to users' devices and notifying them via push notifications or email.

[1386] The system for implementing the invention aims to collect various information from social media, generate news articles using a generative AI model, evaluate their credibility, make future predictions, and then deliver information based on user sentiment. The detailed process is described below.

[1387] The server uses social media APIs to collect posts based on specific keywords or hashtags. It can obtain data from major social media platforms such as Twitter and Facebook. This allows the server to collect the latest information in real time and preprocess the data.

[1388] The server then analyzes the collected data and automatically generates news articles using a generative AI model (e.g., GPT-4). The preprocessed data is tokenized and fed into the generative AI model, which generates news articles in natural language based on the input data.

[1389] The server then runs a credibility assessment algorithm on the generated news articles, which takes into account data from official and trusted sources and calculates a credibility score. Information with a higher credibility score is considered more trustworthy.

[1390] The server runs a future-prediction AI model that simulates both good and bad future scenarios based on the generated news. For example, in the case of a natural disaster, it generates scenarios in which rescue efforts are swift and in which they are delayed.

[1391] The server also has a built-in emotion engine that recognizes users' emotions and adjusts news articles accordingly. The emotion engine analyzes the user's current emotional state and adjusts the content and delivery method of the news article accordingly. For example, if the user is feeling anxious, it will emphasize information that will reassure them.

[1392] The server delivers the generated news articles and future prediction scenarios to the user's device. Possible delivery methods include push notifications and emails. The user's device displays a news notification containing a brief summary and a link to view the detailed news article and future prediction scenario.

[1393] As a concrete example, when collecting earthquake information, a user searches for the keyword "earthquake." The server uses the Twitter API to collect related posts and generates a news article based on them. It then evaluates their credibility and predicts future good scenarios (quick rescue) and bad scenarios (delayed rescue operations). If the user's emotional state is "anxious," the server will prioritize delivering information that provides reassurance.

[1394] This approach enables real-time, reliable information delivery and personalized news delivery based on user sentiment.

[1395] An example prompt is:

[1396] "Get the latest earthquake information from current tweets."

[1397] "Generate news articles from this data."

[1398] "Evaluate the credibility of the news generated."

[1399] "Based on this, predict good and bad scenarios for the future."

[1400] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1401] Step 1:

[1402] The server uses a social media API (e.g., Twitter API) to collect posts based on a specific keyword (e.g., "earthquake") or hashtag. At this point, it sends an API request to retrieve the relevant post data. The input is the social media API endpoint and keyword, and the output is the collected post data.

[1403] Step 2:

[1404] The server preprocesses the collected submission data. This includes noise removal and data normalization. For example, it removes unnecessary symbols and links and extracts important information (e.g., place names, damage information). The input is the collected submission data, and the output is the preprocessed, clean data.

[1405] Step 3:

[1406] The server feeds the preprocessed data to a generative AI model (e.g., GPT-4) to automatically generate news articles. It uses a tokenizer to tokenize the data and input it into the generative AI model. It decodes and outputs the news articles generated by the model. The input is the preprocessed data, and the output is the generated news articles.

[1407] Step 4:

[1408] The server runs a credibility assessment algorithm on the generated news articles. The algorithm calculates a credibility score based on data obtained from official and trusted sources. The input is the generated news article, and the output is the news article with the assigned credibility score.

[1409] Step 5:

[1410] The server runs a future prediction AI model based on news articles that have undergone credibility assessment, simulating both positive and negative future scenarios. For example, it predicts the impact of rapid relief efforts versus delays. The input is news articles with credibility scores, and the output is future prediction scenarios.

[1411] Step 6:

[1412] The server uses an emotion engine to analyze the user's emotional state and adjust the news article accordingly. For example, if the user is feeling anxious, it will emphasize reassuring information. The input is the user's emotional data and a news article, and the output is a news article adjusted according to the emotion.

[1413] Step 7:

[1414] The server delivers the final adjusted news article and future prediction scenario to the user's device. The device displays a news notification to the user, which includes a brief summary and a link to a detailed article. The input is the adjusted news article and future prediction scenario, and the output is the notification displayed on the user's device.

[1415] 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.

[1416] 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.

[1417] 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.

[1418] 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.

[1419] 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.

[1420] 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.

[1421] 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).

[1422] 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.

[1423] 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."

[1424] 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.

[1425] 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).

[1426] 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.

[1427] 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.

[1428] 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.

[1429] 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.

[1430] 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.

[1431] 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.

[1432] 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.

[1433] 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.

[1434] 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.

[1435] 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.

[1436] The following is further disclosed regarding the above embodiment.

[1437] (Claim 1)

[1438] A means of collecting various information from SNS,

[1439] a means for analyzing the collected information to generate news articles;

[1440] a means for assessing the credibility of the generated news articles;

[1441] A means of making future predictions and simulating good and bad news futures;

[1442] A system including a means for delivering news articles and future prediction scenarios to a user terminal.

[1443] (Claim 2)

[1444] 10. The system of claim 1, utilizing a generative AI model to generate news articles.

[1445] (Claim 3)

[1446] 10. The system of claim 1, comprising an algorithm for assessing the veracity of the collected information.

[1447] "Example 1"

[1448] (Claim 1)

[1449] A means of collecting various information from SNS,

[1450] means for preprocessing the collected information;

[1451] a means for inputting the preprocessed information into a generative AI model to generate news articles;

[1452] a means for assessing the credibility of the generated news articles;

[1453] A means of making future predictions and simulating good and bad news futures;

[1454] A system including a means for delivering news articles and future prediction scenarios to a user terminal.

[1455] (Claim 2)

[1456] 10. The system of claim 1, utilizing a generative AI model to generate news articles.

[1457] (Claim 3)

[1458] 10. The system of claim 1, further comprising means for pre-processing the collected information and an algorithm for assessing its veracity.

[1459] "Application Example 1"

[1460] (Claim 1)

[1461] A means of collecting various information from SNS,

[1462] a means for analyzing the collected information to generate news articles;

[1463] a means for assessing the credibility of the generated news articles;

[1464] A means of making future predictions and simulating good and bad news futures;

[1465] A means for delivering news articles and future prediction scenarios to a user terminal;

[1466] A content distribution system including means for distributing news and future prediction scenarios to a user's computer terminal.

[1467] (Claim 2)

[1468] The content distribution system of claim 1, which utilizes a generative AI model to generate news articles.

[1469] (Claim 3)

[1470] 10. The content distribution system of claim 1, further comprising an algorithm for assessing the authenticity of the collected information.

[1471] "Example 2: Combining Emotion Engines"

[1472] (Claim 1)

[1473] means of collecting diverse information from online platforms;

[1474] a means for preprocessing the collected information before generating news articles;

[1475] an evaluation means for evaluating the credibility of the generated news articles;

[1476] A means of making future predictions and simulating good and bad news futures;

[1477] A system including a means for delivering generated news articles and future prediction scenarios to a user terminal.

[1478] (Claim 2)

[1479] 10. The system of claim 1, wherein the generative AI model is used to generate news articles.

[1480] (Claim 3)

[1481] 10. The system of claim 1, comprising an algorithm for assessing the veracity of the collected information.

[1482] (Claim 4)

[1483] 10. The system of claim 1, utilizing an API to collect data from an online platform.

[1484] (Claim 5)

[1485] 10. The system of claim 1, further comprising an emotion recognition engine for analyzing the user's emotional state and providing information accordingly.

[1486] "Application example 2 when combining emotion engines"

[1487] (Claim 1)

[1488] A means of collecting various information from SNS,

[1489] a means for analyzing the collected information to generate news articles;

[1490] a means for assessing the credibility of the generated news articles;

[1491] A means of making future predictions and simulating good and bad news futures;

[1492] a means for recognizing a user's emotions and tailoring news articles accordingly;

[1493] A system including a means for delivering news articles and future prediction scenarios to user terminals.

[1494] (Claim 2)

[1495] 10. The system of claim 1, utilizing a generative AI model to generate news articles.

[1496] (Claim 3)

[1497] 10. The system of claim 1, comprising an algorithm for assessing the veracity of the collected information. [Explanation of symbols]

[1498] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting various information from SNS, a means for analyzing the collected information to generate news articles; a means for assessing the credibility of the generated news articles; A means of making future predictions and simulating good and bad news futures; A system including a means for delivering news articles and future prediction scenarios to a user terminal.

2. The system of claim 1 , which utilizes a generative AI model to generate news articles.

3. The system of claim 1 , further comprising an algorithm for assessing the authenticity of the collected information.

Images