system

Abstract

A system is provided.SOLUTION: Means for collecting timeline data from an SNS service, means for cleansing the collected timeline data and removing unnecessary data, means for extracting a keyword, a hashtag, and an entity from post content using a natural language processing technique, means for evaluating importance of a post based on the extracted data, means for automatically summarizing the evaluated important post, means for delivering the summarized information to a user, means for providing a link related to the delivered information, means for recording an operation of the user, and means for analyzing the recorded operation data, means for improving a summarization algorithm or a distribution method.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In modern society, social networking sites (SNS) have become an important source of information, but the vast amount of information disseminated means that users have to make significant efforts to select and discard information. There is also a high risk of missing important information. Therefore, there is a need for a method to efficiently extract necessary information from SNS, summarize it, and provide it to users. At the same time, protecting the privacy and ensuring the security of collected data are also important issues. The present invention aims to solve these issues and provide a system that allows users to efficiently gather information while freeing them from the stress of information overload. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems with a system that includes: means for collecting timeline data from social networking services; means for cleansing the collected timeline data and removing unnecessary data; means for extracting keywords, hashtags, and entities from post content using natural language processing technology; means for rating the importance of posts based on the extracted data; means for automatically summarizing the rated important posts; means for delivering the summarized information to users; means for providing links related to the delivered information; means for recording user operations; and means for analyzing the recorded operation data to improve the summarization algorithm and delivery method. This allows users to efficiently collect important information and check detailed information as needed. Furthermore, the quality of the information provided is continuously improved through analysis and improvement of the system.

[0006] "SNS service" is an abbreviation for social networking service, a platform for users to share and interact with information online.

[0007] "Timeline data" is a collection of data that displays the content posted by users on social networking services in chronological order.

[0008] "Cleansing" is the process of removing unnecessary parts from collected data and organizing only the necessary data.

[0009] "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language.

[0010] A "keyword" is a word or phrase that has significant meaning in the text data.

[0011] A "hashtag" is a keyword accompanied by the symbol () that is used to make it easier to organize and categorize posts on social media services.

[0012] "Entity" is a term that refers to a specific entity such as a person's name, place name, or product name.

[0013] "Importance" is an evaluation criterion that indicates how valuable the content of a post is to the user.

[0014] A "summary" refers to the essence of a long original text in a short form.

[0015] A "means" is a method or device used to achieve a particular purpose.

[0016] "Distribution" is the act of delivering information to users.

[0017] A "link" is a reference that connects to a related document or web page.

[0018] "Operation" refers to a specific action (click, input, etc.) that a user takes on the system.

[0019] "Analysis" is the process of examining and breaking down data in detail to find meaning and patterns.

[0020] An "algorithm" refers to a procedure or computational method for solving a specific problem.

[0021] A "system" is a comprehensive framework in which multiple elements and functions are combined to achieve a single purpose. [Brief explanation of the drawings]

[0022] [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

[0023] 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.

[0024] First, the terms used in the following description will be explained.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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."

[0030] [First embodiment]

[0031] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0032] 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.

[0033] 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).

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0039] 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.

[0040] 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.

[0041] 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.

[0042] 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."

[0043] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes embodiments of the present invention, which are merely illustrative and do not limit the present invention.

[0044] This invention is a system that collects timeline data from SNS services and efficiently provides important information to users. This system consists of three main components: a server, a terminal, and a user.

[0045] server

[0046] The server is responsible for collecting timeline data from SNS services. Specifically, it accesses the API of each SNS service and retrieves the timeline data using an authentication token. The collected data is stored in a database on the server.

[0047] The server cleanses the stored timeline data and removes unnecessary data, which improves data accuracy and makes subsequent processing more efficient.

[0048] The server uses natural language processing techniques to extract keywords, hashtags, and entities from posts, thereby identifying important information from the collected data.

[0049] The server evaluates the importance of posts based on the extracted data and selects the most important posts, taking into account engagement data (number of likes, retweets, comments, etc.).

[0050] The server automatically summarizes the selected important posts and generates summary data that is delivered to users in a format that is easy for users to understand.

[0051] The server provides links associated with the summarized information, allowing the user to view more detailed information.

[0052] The server records and analyzes user actions (clicks on summary information, links, etc.), which allows for continuous improvement of the summary algorithm and delivery method.

[0053] Terminal

[0054] A terminal is a device (such as a smartphone, tablet, or PC) that a user uses to access the system. The user can use the terminal to receive the collected summary information.

[0055] The device records the user's actions and sends them to the server, which provides feedback to the server and uses it to improve the system.

[0056] User

[0057] A user is an individual or a corporation who wants to efficiently obtain important information from an SNS service. A user can use the service by registering their SNS account information in the system and providing the necessary information.

[0058] The user receives and checks the summary information delivered from the server using a terminal, and can also refer to detailed information by clicking on related links.

[0059] Users can customize their own notification settings, such as the frequency of notifications and how they want to receive them (email notifications, app notifications, etc.).

[0060] Specific examples

[0061] For example, suppose User A has registered accounts for social networking services (e.g., Twitter and Facebook) in the system. The server accesses the APIs of these social networking services to collect User A's timeline data. The server then cleanses the collected data and extracts important keywords and hashtags using natural language processing technology. The server then evaluates the importance of posts based on the extracted data and selects particularly important posts. The server then summarizes the selected posts and provides them to User A in the form of emails or app notifications. The summaries also include links related to the original posts, allowing User A to view the details. Furthermore, any actions User A takes on notifications are recorded by the device and sent to the server. This feedback data is used to improve the system's summarization algorithm and delivery method.

[0062] As described above, the system of the present invention can efficiently extract important information from SNS services and provide it to users, thereby solving the problem of information overload and improving user convenience.

[0063] The processing flow will be explained below.

[0064] Step 1:

[0065] The server accesses the API of the SNS service registered by the user and requests timeline data using the authentication token. Specifically, it sends an API request to obtain the user's timeline data (post content, number of likes, number of retweets, etc.).

[0066] Step 2:

[0067] The server receives the timeline data returned from the API and stores it in an internal database, along with metadata such as timestamps and user IDs.

[0068] Step 3:

[0069] The server cleanses the stored timeline data, removing duplicates and unnecessary data (such as advertising posts and spam) and checking the integrity of the data.

[0070] Step 4:

[0071] The server then uses natural language processing techniques to extract keywords, hashtags, and entities from the cleansed data, including techniques such as tokenization, part-of-speech tagging, and entity recognition.

[0072] Step 5:

[0073] The server evaluates the importance of each post based on the extracted keywords and entities, and uses a scoring algorithm to select the most important posts, taking into account engagement data (number of likes, retweets, comments, etc.).

[0074] Step 6:

[0075] The server then summarises the ranked posts, using machine learning models and rule-based techniques to provide a short summary of the posts' key points.

[0076] Step 7:

[0077] The server collects links related to the summarized information (such as the original post, additional details, etc.) and adds them to the summary data, allowing users to easily check for more information.

[0078] Step 8:

[0079] The server prepares the summary information based on the user's delivery preferences (e.g. email, app notification, dashboard view) and formats the summary data accordingly.

[0080] Step 9:

[0081] The server delivers the summary information to the user in a manner that depends on the user's settings, such as by emailing the summary information via a mail server or by sending a push notification to the app.

[0082] Step 10:

[0083] The device records user operations (such as displaying summary information and clicking links), and this operation data is saved as a log.

[0084] Step 11:

[0085] The server collects and analyzes user operation data sent from the device, and uses this data to improve the summarization algorithm and delivery method.

[0086] Step 12:

[0087] The server reflects the analysis results and optimizes the information gathering, summarizing, and distribution process from the next time onwards, thereby improving the quality of information provided to users.

[0088] Example 1

[0089] 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."

[0090] Modern social networking services provide a vast amount of information, but it is difficult to efficiently extract and provide important information to users. In particular, because they contain a lot of unnecessary data and spam, it takes a lot of time and effort for users to find the information they truly need. In addition, there is a lack of a mechanism for continuously improving the system based on user operation history and delivering information that is more appropriate for users.

[0091] 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.

[0092] In this invention, the server includes means for collecting timeline data from social networking services, means for cleansing the collected timeline data and removing unnecessary data, and means for extracting keywords, hashtags, and entities from posted content using natural language processing technology. This improves information accuracy and removes unnecessary data, allowing only important information to be efficiently extracted and provided to users. Furthermore, adding a means for users to customize delivery frequency and notification method enables information delivery tailored to individual user needs. Furthermore, by recording user operations and analyzing the operation data, the system can continuously improve the summarization algorithm and delivery method, thereby improving the overall convenience of the system.

[0093] "SNS service" is an abbreviation for social networking service, which is an online platform that enables users to communicate and share information with other users via the Internet.

[0094] "Timeline data" refers to a series of messages and updates posted on a social networking service that relate to a specific user.

[0095] "Cleansing" is the process of removing unnecessary data and noise from collected data and making it usable.

[0096] "Unnecessary data" refers to information collected by the system that is not suitable for analysis or use, such as spam and advertisements.

[0097] "Natural language processing technology" is a technology that allows computers to analyze and understand human language, and it analyzes the meaning of documents using language models and algorithms.

[0098] A "keyword" refers to a word that is considered particularly important in text data and is used as a target for search and analysis.

[0099] A "hashtag" is a tag used on social media services to indicate a specific topic or theme, and usually refers to a word or phrase preceded by the " " symbol.

[0100] An "entity" is a word or phrase that has a specific meaning in natural language processing, and refers to a proper noun or a specific concept.

[0101] "Assessing importance" is the process of identifying particularly valuable information from the collected data and determining its priority.

[0102] A "summary" is a conversion of the entire original information into a short, concise, and simplified representation that includes the main points.

[0103] A "link" is a reference, in the form of a URL, to a web page or other Internet resource that can be clicked to access related information.

[0104] "Recording operations" means saving the actions (clicks, taps, etc.) that a user takes on the system as data.

[0105] "Analysis" is the process of examining recorded data in detail to understand its meaning and patterns.

[0106] "Customization" refers to adjusting system settings and features to suit the user's preferences and needs.

[0107] The present invention provides a system that collects timeline data from SNS services and efficiently provides important information to users. The following embodiment is an example and is not intended to limit the present invention.

[0108] server

[0109] Collection Steps

[0110] The server is responsible for collecting timeline data from social networking services. Specifically, it accesses the API of each social networking service and retrieves the timeline data using an authentication token. For example, it collects data using the Twitter API or Facebook API. The collected data is stored in a database on the server.

[0111] Cleansing Step

[0112] The server cleanses the stored timeline data and removes unnecessary data, using spam, advertisement, and other filtering methods, which improves the accuracy of the data and makes subsequent processing more efficient.

[0113] Natural Language Processing Step

[0114] The server uses natural language processing techniques to extract keywords, hashtags, and entities from posts, such as text analysis using natural language processing libraries NLTK and spaCy, to identify important information from the collected data.

[0115] Importance evaluation step

[0116] The server evaluates the importance of posts based on the extracted data and selects important posts. This process also takes into account engagement data (number of likes, retweets, comments, etc.). For example, a post with 100 retweets and 500 likes will be evaluated as having high importance.

[0117] Summary generation step

[0118] The server automatically summarizes selected important posts and generates summary data to be delivered to users using algorithms such as the BERT summarizer. The summaries are provided in a format that is easy for users to understand.

[0119] Related link provision steps

[0120] The server provides links related to the summarized information, for example adding a "Learn more" link at the end of the summary, allowing the user to view more detailed information.

[0121] Operation record and analysis steps

[0122] The server records and analyzes user actions (clicks on summary information, links, etc.), which allows for continuous improvement of the summary algorithm and delivery method.

[0123] Terminal

[0124] Access and Display Steps

[0125] The terminal is a device (smartphone, tablet, PC, etc.) through which the user accesses the system and can receive the collected summary information. For example, a message saying "New summary information has arrived" will be displayed in the notification bar of the smartphone.

[0126] Operation Record Steps

[0127] The device records the user's actions and sends them to the server, which provides feedback to the server and uses it to improve the system.

[0128] User

[0129] Account registration steps

[0130] A user is an individual or corporation who wants to efficiently obtain important information from a social networking service. A user can use the service by registering their social networking account information in the system and providing the necessary information. For example, they can provide "Twitter API token: xxxxxxxx."

[0131] Information Receipt and Confirmation Steps

[0132] The user receives the summary information delivered from the server using the terminal and checks it. For example, the user can click a details link in the notified summary information to check the details.

[0133] Delivery settings customization steps

[0134] Users can customize their own notification settings, such as the frequency of notifications and how they want to receive them (email notifications, app notifications, etc.).

[0135] Specific examples

[0136] For example, suppose User A has registered accounts for social networking services (e.g., Twitter and Facebook) in the system. The server accesses the APIs of these social networking services to collect User A's timeline data. The server then cleanses the collected data and extracts important keywords and hashtags using natural language processing technology. The server then evaluates the importance of posts based on the extracted data and selects particularly important posts. The server then summarizes the selected posts and provides them to User A in the form of emails or app notifications. The summaries also include links related to the original posts, allowing User A to view the details. Furthermore, any actions User A takes on notifications are recorded by the device and sent to the server. This feedback data is used to improve the system's summarization algorithm and delivery method.

[0137] Example prompt:

[0138] "Generate a program that cleanses timeline data collected from Twitter and Facebook, extracts important information, and summarizes it. Include relevant links in the summary and record user actions to use as feedback data."

[0139] As described above, the system of the present invention can efficiently extract important information from SNS services and provide it to users, thereby solving the problem of information overload and improving user convenience.

[0140] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0141] Step 1:

[0142] Initial settings (server, user)

[0143] The server starts and reads the SNS API key and database connection information from the configuration file. This is done as part of the server initialization process.

[0144] Input: config file

[0145] Output: Initialization completion status

[0146] Users register their social media account information through a web interface or app. For example, by registering "Twitter API token: xxxxxxxx", social media data collection is ready.

[0147] Input: User-entered social media account information

[0148] Output: Registration completion status

[0149] Step 2:

[0150] Data collection (server)

[0151] The server accesses the API of the SNS service using the authentication token and acquires the user's timeline data, for example, the latest tweets using the Twitter API.

[0152] Input: User's authentication token

[0153] Output: Social media timeline data

[0154] The server stores the acquired timeline data in a database.

[0155] Input: Social media timeline data

[0156] Output: Data stored in the database

[0157] Step 3:

[0158] Data cleansing (server)

[0159] The server reads the timeline data stored in the database and removes unnecessary data (spam, advertisements, etc.) using keyword matching and regular expressions as filtering methods.

[0160] Input: Timeline data stored in a database

[0161] Output: Cleansed data

[0162] Specifically, the server filters out posts containing keywords such as "spam" and "advertising."

[0163] Step 4:

[0164] Natural language processing (server)

[0165] The server parses the cleansed timeline data and extracts keywords, hashtags, and entities from posts using natural language processing libraries (NLTK and spaCy).

[0166] Input: Cleansed data

[0167] Output: Extracted keywords, hashtags, and entities

[0168] For example, extract "AI" and "future" from a tweet saying "AI will change the future."

[0169] Step 5:

[0170] Importance rating (server)

[0171] The server evaluates the importance of each post based on the extracted keywords and entities, and also uses engagement data (number of likes, retweets, comments, etc.) to determine the score.

[0172] Input: Extracted keywords, hashtags, entities, and engagement data

[0173] Output: Importance score

[0174] Specifically, the server evaluates posts with 100 retweets and 500 likes as having high importance.

[0175] Step 6:

[0176] Summary generation (server)

[0177] The server automatically summarizes posts that are rated as highly important using a summary generation algorithm (BERT summarizer).

[0178] Input: Posts with high importance scores

[0179] Output: Summary data

[0180] Specifically, it converts "Original post: A new AI technology has been announced. Learn more here." into "Summary: A new AI technology has been announced."

[0181] Step 7:

[0182] Related link provided (server)

[0183] The server provides links related to the summarized posts.

[0184] Input: Summary data

[0185] Output: Summary data with associated links

[0186] Specifically, a "Learn more" link will be added to the end of the summary.

[0187] Step 8:

[0188] Information distribution (server, terminal)

[0189] The server delivers the summary information and related links to the user's device via email, push notification, or other methods depending on the user's delivery settings.

[0190] Input: Summary data with related links, user distribution settings

[0191] Output: Summary information delivered

[0192] The device displays the received summary information to the user. For example, a message saying "New summary information has arrived" is displayed in the notification bar of the smartphone.

[0193] Input: Delivered summary information

[0194] Output: Summary information displayed on the user's screen

[0195] Step 9:

[0196] Operation record and analysis (terminal, server)

[0197] When a user clicks on summary information or related links, the action is recorded in real time on the device.

[0198] Input: User actions

[0199] Output: Operation record data

[0200] The terminal transmits the recorded operation data to the server.

[0201] Input: Operation record data

[0202] Output: Operation data sent to the server

[0203] The server analyzes the received operation data and uses it to improve the summarization algorithm and delivery method.

[0204] Input: Operation data sent to the server

[0205] Output: Analysis results, system improvement information

[0206] Step 10:

[0207] Customizing delivery settings (user)

[0208] Users can adjust the frequency of delivery and notification method to suit their preferences.

[0209] Input: User settings information

[0210] Output: Updated distribution settings

[0211] For example, set the delivery frequency to once a day and the notification method to email notification.

[0212] The above are the specific processing steps of this system.

[0213] (Application example 1)

[0214] 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."

[0215] In modern society, the amount of information disseminated on the Internet is enormous, and there is a high risk of missing important security-related information. This poses a challenge, making it difficult for individuals and companies to quickly implement security measures. There is also a need for a method to efficiently collect information scattered across social networking sites and extract and provide only the necessary information. A method is needed to solve this information overload problem and provide important security information quickly and efficiently.

[0216] 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.

[0217] In this invention, the server includes means for collecting timeline data from SNS services, means for cleansing the collected timeline data and removing unnecessary data, means for extracting keywords, hashtags, and entities from post content using natural language processing technology, means for evaluating the importance of posts based on the extracted data, means for automatically summarizing the evaluated important posts, means for delivering the summarized information to users, means for providing links related to the delivered information, means for recording user operations, means for analyzing the recorded operation data and improving the summarization algorithm and delivery method, and means for collecting data from security-related SNS accounts and providing notifications in real time. This makes it possible to efficiently collect important security-related information and quickly notify users.

[0218] "SNS service" is an abbreviation for social networking service, an online platform that makes it easy for users to share information over the Internet.

[0219] "Timeline data" is a continuous record of information posted by users and related accounts on social media services, and is data displayed in chronological order.

[0220] "Cleansing" is the process of removing unnecessary information and noise from collected data and organizing it to include only the necessary information.

[0221] "Natural language processing technology" refers to all technologies that allow computers to interpret, analyze, and process human language.

[0222] "Keywords" are words or phrases that are particularly important in text or data, and are used for search and analysis.

[0223] A "hashtag" is a short phrase used on social media to express a specific keyword or topic, and begins with the symbol "."

[0224] An "entity" is information that indicates an independent existence, such as a specific name or title, and refers to a specific item such as a store name, a person's name, or a place name.

[0225] "Importance" is a measure of the value and urgency of information in collected data or posts based on specific criteria.

[0226] A "summary" is a short, concise expression of long information that extracts and provides the essential content.

[0227] A "link" is a string of characters or a button that allows you to connect to a specific location or information on the Internet, and is a means of accessing other web pages or resources.

[0228] "Operation data" is a record of a series of actions a user performs while using a system, including actions such as clicking, scrolling, and typing.

[0229] An "authentication token" is a temporary string of characters that proves a user has been authenticated to a system and is used to ensure secure access.

[0230] "Delivery settings" are settings that allow users to customize how and how often they receive information.

[0231] "Real-time" refers to the instant display and reflection of current situations and actions, and refers to a state in which information is provided without delay.

[0232] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes embodiments of the present invention, which are merely illustrative and do not limit the present invention.

[0233] In this system, to obtain timeline data from a social networking service, the server first accesses the social networking service's API and collects the data using an authentication token. For example, the server uses the authentication token to obtain security-related timeline data from the Twitter or Facebook API.

[0234] The collected data is stored in a database on the server, where it undergoes a data cleansing process. This cleansing process removes unnecessary data and noise, leaving only the important security data. Next, natural language processing techniques are used to extract keywords, hashtags, and entities from the posts. For example, natural language processing libraries (e.g., NLTK, SpaCy) are used to extract important keywords such as "phishing attack" and "virus" from the posts.

[0235] The server then evaluates the importance of posts based on the extracted data. Specifically, it uses engagement data (e.g., the number of likes, retweets, and comments) to quantify the importance of each post. It also automatically selects particularly important posts based on these values ​​and generates summaries. For example, it might determine that "this post has received many likes and retweets, so it is highly important."

[0236] After selecting important posts, the server summarizes them and delivers them to users. This can be delivered via email or push notifications. The summaries also include links related to the original posts, allowing users to easily view more detailed information. The server also records the actions users take on the information they receive as notifications (e.g., clicks and scrolls) and sends the data to the server. This action data is analyzed and used to improve the summarization algorithm and delivery method.

[0237] Additionally, the system specifically collects data from security-related social media accounts and provides real-time notifications to users, who can view these notifications using their smartphones, tablets, PCs, or other devices.

[0238] As a concrete example, consider the case where a security officer uses this system. The officer registers his / her social media account in the system and configures it to collect security-related information in real time. The following prompt sentence is input to the generative AI model:

[0239] Username: @cybersecuritynews

[0240] Post content: Sharing important information about the latest phishing attacks. Click here for detailed countermeasures. [Link]

[0241] Engagement data: Likes 50, Retweets 20, Comments 10

[0242] Based on this prompt, the generative AI model summarizes important information and notifies the security personnel. The security personnel can then click on a link to view more detailed information if necessary. This process allows security personnel to take prompt action without missing any important information.

[0243] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0244] Step 1:

[0245] The server accesses the API of the SNS service and collects timeline data using the authentication token. The input is the API endpoint of the SNS service and the authentication token, and the output is the collected timeline data. Specifically, the server sends an HTTP request to retrieve authenticated user data.

[0246] Step 2:

[0247] The server cleanses the collected timeline data. The input is the timeline data collected in step 1, and the output is the cleansed data. Specifically, a filtering process is performed to remove noise and unnecessary information from the timeline data stored in the database.

[0248] Step 3:

[0249] The server uses natural language processing technology to extract keywords, hashtags, and entities from the post content. The input is the cleansed data from step 2, and the output is the extracted keywords, hashtags, and entities. Specifically, it uses a natural language processing library to perform text analysis and extract important words and phrases.

[0250] Step 4:

[0251] The server evaluates the importance of posts based on the extracted data. The input is the keywords, hashtags, entities, and engagement data extracted in step 3, and the output is an importance score for each post. Specifically, the server applies a scoring algorithm based on the number of likes, retweets, comments, etc. to calculate the importance.

[0252] Step 5:

[0253] The server automatically summarizes the rated important posts. The input is the posts with high importance scores obtained in step 4, and the output is the summarized information. Specifically, it uses a generative AI model to convert the post content into a summary sentence.

[0254] Step 6:

[0255] The server delivers the summarized information to the user. The input is the summarized information from step 5, and the output is a notification message to the user. Specifically, the information is delivered via email notification or the app's push notification function.

[0256] Step 7:

[0257] The server provides links related to the distributed information. The input is the summarized information from step 5, and the output is links related to the summarized information. Specifically, the server extracts links from the original post and adds them to the summary.

[0258] Step 8:

[0259] The device records user operations. The input is the user's operations on the device (clicks, scrolls, etc.), and the output is a record of those operations. Specifically, it sets up an event listener and records each operation event in a log.

[0260] Step 9:

[0261] The server analyzes the recorded operation data and improves the summarization algorithm and delivery method. The input is the operation data recorded in step 8, and the output is an improved summarization algorithm and delivery method. Specifically, the operation data is statistically analyzed and the algorithm is adjusted through a feedback loop.

[0262] Step 10:

[0263] The server collects data from security-related social media accounts and provides notifications in real time. The input is data from security-related social media accounts, and the output is security information notifications delivered in real time. Specifically, it prioritizes data posted from specific security-related accounts and immediately notifies users.

[0264] 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.

[0265] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following embodiments are illustrative and do not limit the present invention.

[0266] This invention combines a system that collects timeline data from SNS services and efficiently provides important information to users with an emotion engine. This system consists of four main components: a server, a device, a user, and an emotion engine.

[0267] server

[0268] The server is responsible for collecting timeline data from SNS services. Specifically, it accesses the API of each SNS service and retrieves the timeline data using an authentication token. The collected data is stored in a database on the server.

[0269] The server cleanses the stored timeline data and removes unnecessary data, which improves data accuracy and makes subsequent processing more efficient.

[0270] The server uses natural language processing techniques to extract keywords, hashtags, and entities from posts, thereby identifying important information from the collected data.

[0271] The server evaluates the importance of posts based on the extracted data and selects the most important posts, taking into account engagement data (number of likes, retweets, comments, etc.).

[0272] The server uses an emotion engine to analyze the user's emotions from the collected timeline data and the user's past operation data, and reflects the emotion data in the importance evaluation of the summary information.

[0273] The server then summarises the selected important posts, using machine learning models and rule-based techniques to create short summaries of the posts' key points.

[0274] The server collects links related to the summarized information (such as the original post, additional details, etc.) and adds them to the summary data, allowing users to easily find more information.

[0275] The server prepares the summary information based on the user's delivery preferences (e.g. email, app notification, dashboard view) and formats the summary data accordingly.

[0276] The server delivers the summary information to the user in a manner that depends on the user's settings, for example, by emailing the summary information via a mail server or by sending a push notification to the app.

[0277] The server records and analyzes user actions (viewing summary information, clicking links, etc.) to continually improve the summary algorithm and delivery method.

[0278] Terminal

[0279] A terminal is a device (such as a smartphone, tablet, or PC) that a user uses to access the system. The user can use the terminal to receive the collected summary information.

[0280] The device records the user's actions and sends them to the server, which provides feedback to the server and uses it to improve the system.

[0281] User

[0282] A user is an individual or a corporation who wants to efficiently obtain important information from an SNS service. A user can use the service by registering their SNS account information in the system and providing the necessary information.

[0283] The user receives and checks the summary information delivered from the server using a terminal, and can also refer to detailed information by clicking on related links.

[0284] Users can customize their own notification settings, such as the frequency of notifications and how they want to receive them (email notifications, app notifications, etc.).

[0285] Emotion Engine

[0286] The emotion engine is a component for recognizing user emotions, which allows us to analyze user emotions from collected timeline data and user operation data.

[0287] The emotion engine has an algorithm that determines the user's emotions (happiness, surprise, sadness, etc.) from the content of posts and operation data. The emotion data is sent to the server and used to evaluate the importance of summary information and improve delivery methods.

[0288] The sentiment engine analyzes how users feel about specific keywords or entities and reflects this in selecting and summarizing important information.

[0289] Specific examples

[0290] For example, suppose User B has registered accounts for social networking services (e.g., Twitter and Instagram) in the system. The server accesses the APIs of these social networking services to collect User B's timeline data. It then cleanses the collected data and extracts important keywords and hashtags using natural language processing technology. The server uses an emotion engine to analyze emotions from User B's timeline data and past operation data, and reflects the emotion data in the importance rating of the summary information. For example, User B may rate posts containing keywords that frequently indicate the emotion "joy" as highly important. The server then summarizes the important posts and provides them to User B in the form of emails or app notifications. The summaries also include links related to the original posts, allowing User B to view the details. The emotion engine also collects User B's emotion data, which is used for future system optimization.

[0291] As described above, the system of the present invention can efficiently extract important information from SNS services and provide information optimized to suit the user's emotions, thereby solving the problem of information overload and improving user convenience.

[0292] The processing flow will be explained below.

[0293] Step 1:

[0294] The server accesses the API of the SNS service registered by the user and requests timeline data using the authentication token. Specifically, it sends an API request to obtain the user's timeline data (post content, number of likes, number of retweets, etc.).

[0295] Step 2:

[0296] The server receives the timeline data returned from the API and stores it in an internal database, along with metadata such as timestamps and user IDs.

[0297] Step 3:

[0298] The server cleanses the stored timeline data, removing duplicates and unnecessary data (such as advertising posts and spam) and checking the integrity of the data.

[0299] Step 4:

[0300] The server then uses natural language processing techniques to extract keywords, hashtags, and entities from the cleansed data, including techniques such as tokenization, part-of-speech tagging, and entity recognition.

[0301] Step 5:

[0302] The server evaluates the importance of each post based on the extracted keywords and entities, and uses a scoring algorithm to select the most important posts, taking into account engagement data (number of likes, retweets, comments, etc.).

[0303] Step 6:

[0304] The server analyzes the user's emotions using an emotion engine, which uses an algorithm to determine the user's emotions (e.g., joy, surprise, sadness) based on specific posts and past activity data.

[0305] Step 7:

[0306] The server adjusts the importance rating based on the analysis results of the emotion engine. Posts containing keywords that users frequently express the emotion of "joy" are given a higher rating.

[0307] Step 8:

[0308] The server then summarises the ranked posts, using machine learning models and rule-based techniques to provide a short summary of the posts' key points.

[0309] Step 9:

[0310] The server collects links related to the summarized information (such as the original post, additional details, etc.) and adds them to the summary data, allowing users to easily find more information.

[0311] Step 10:

[0312] The server prepares the summary information based on the user's delivery preferences (e.g. email, app notification, dashboard view) and formats the summary data accordingly.

[0313] Step 11:

[0314] The server delivers the summary information to the user in a manner that depends on the user's settings, such as by emailing the summary information via a mail server or by sending a push notification to the app.

[0315] Step 12:

[0316] The device records user operations (such as displaying summary information and clicking links), and this operation data is saved as a log.

[0317] Step 13:

[0318] The server collects and analyzes user operation data sent from the device, and uses this data to improve the summarization algorithm and delivery method.

[0319] Step 14:

[0320] The server will then apply the analysis results to optimize the information gathering, summarizing, and distribution processes from the next time onward, thereby improving the quality of the information provided to users.

[0321] Example 2

[0322] 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."

[0323] Currently, there is a huge amount of information available on social networking services, making it difficult for users to efficiently obtain important information. Furthermore, information provided does not take into account the user's emotional state, so information that meets the user's needs is often not provided. This increases the likelihood that users will miss useful information in this information-overloaded world. Furthermore, there is a need to accurately evaluate the importance and relevance of the information provided and deliver it to users in an appropriate format.

[0324] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0325] In this invention, the server includes means for collecting timeline data from an SNS service, means for cleansing the collected timeline data and removing unnecessary data, means for extracting keywords, hashtags, and entities from the posted content using natural language processing technology, means for evaluating the importance of posts based on the extracted data, means for analyzing user emotion data and reflecting the results in the importance evaluation, means for automatically summarizing the evaluated important posts, means for providing links related to the summarized information, means for formatting the summarized information based on the user's distribution settings, means for providing the distributed information to the user, means for recording user operations, and means for analyzing the recorded operation data and improving the summarization algorithm and distribution method. This allows users to efficiently obtain important information from vast amounts of information and further enables the provision of appropriate information according to the user's emotional state.

[0326] "SNS service" refers to a social networking service, an online platform for people to communicate over the Internet.

[0327] "Timeline data" refers to data that shows the content posted by users on social networking services and the order in which they were posted.

[0328] "Cleansing" is the process of removing unnecessary information from collected timeline data and extracting important information.

[0329] "Natural language processing technology" is a technology that allows computers to analyze and understand human language.

[0330] "Keywords" are important words or phrases in your post.

[0331] A "hashtag" is a tag preceded by the " " symbol that is added to a post to indicate a particular topic or theme.

[0332] An "entity" is a proper noun such as a person's name, place name, or organization name contained in the posted content.

[0333] "Importance evaluation" is the process of measuring the value and importance of a post based on certain criteria and assigning a score.

[0334] "Emotional data" refers to information that indicates the emotional state of a user.

[0335] "Summarizing" refers to the process of briefly summarizing the main points of the posted content.

[0336] "Link" means a URL or hyperlink that provides a connection to related sources of information or further information.

[0337] "Delivery Preferences" refers to options that allow users to set how they wish to receive information.

[0338] "Operational Data" means records of actions and events performed by users on the system.

[0339] A "summarization algorithm" is a formula or method used to efficiently summarize a post's content.

[0340] "Delivery method" refers to the means or process used to provide information to users.

[0341] The present invention is configured by combining a system that collects timeline data from SNS services and efficiently provides important information to users with an emotion engine.

[0342] server

[0343] The server is responsible for collecting timeline data from SNS services. Specifically, the server accesses the API of each SNS service (e.g., social networking platform) and obtains timeline data using an authentication token. This data is then stored in the server's database.

[0344] The collected data goes through a cleansing process to remove unnecessary data. This process improves the accuracy of the data and makes subsequent processing more efficient. The server uses natural language processing techniques (e.g., natural language processing libraries) to extract keywords, hashtags, and entities from the posts, thereby identifying important information.

[0345] Next, the server evaluates the importance of posts based on the extracted data. The server considers engagement data (e.g., number of likes, retweets, and comments) and reflects this in the importance evaluation. Furthermore, it uses an emotion engine to analyze user emotion data and reflects this in the importance evaluation of the summary information.

[0346] The server uses machine learning models (e.g., generative AI models) to automatically summarize important posts that have been rated, and also includes relevant links to help users find more information.

[0347] The server formats the summary information based on the user's delivery settings and prepares it for delivery. For example, if the user selects email notification, the server formats the summary information in HTML format and prepares it for email transmission. Finally, the server uses a delivery method such as sending the summary information via email via a mail server.

[0348] The server also records and analyzes user actions (viewing summary information, clicking links), and the resulting data is used to improve the summary algorithm and delivery method.

[0349] Terminal

[0350] The terminal is a device (e.g., smartphone, tablet, or PC) that users use to access the system. The user can use the terminal to receive and check the summary information delivered to them. The terminal also records the user's actions and sends them to the server. This data is passed to the server as feedback and used to improve the system.

[0351] User

[0352] A user is an individual or a corporation who wants to efficiently obtain important information from an SNS service. A user can use this service by registering their SNS account information in the system and providing the necessary information.

[0353] Users can use their devices to check summary information delivered from the server and click on related links to view detailed information. Users can also customize their delivery settings to receive information in a way that suits their needs (e.g., email notifications, app notifications).

[0354] Specific examples

[0355] For example, suppose User B has registered an account for a social networking service (e.g., a social networking platform) in the system. The server accesses the APIs of these social networking services to collect User B's timeline data. The server then cleanses the collected data and uses natural language processing technology to extract important keywords and hashtags.

[0356] The server uses an emotion engine to analyze emotions from User B's timeline data and past operation data, and reflects that emotion data in the importance rating of the summary information. For example, User B rates posts containing keywords that frequently indicate the emotion of "joy" with a high importance rating. Next, the server summarizes the important posts using a generative AI model and provides them to User B in the form of an email or app notification. The summary also includes a link related to the original post, allowing User B to check the details.

[0357] The emotion engine also collects emotion data from User B, which will be used to optimize the system in the future. Specific examples of prompt sentences are as follows:

[0358] "Extract important keywords from User B's social networking platform timeline data, analyze the user's sentiment using a sentiment engine, and summarize the important information. Include relevant links in the summary and provide it in the form of an email notification."

[0359] In this way, the present invention is a system that efficiently extracts important information from SNS services and provides information optimized to the user's emotions, thereby solving the problem of information overload and improving user convenience.

[0360] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0361] Step 1:

[0362] The server calls the API of the SNS service to obtain timeline data. Specifically, it sends an API request using the API key and authentication token of each SNS service to obtain timeline data in JSON format. In this process, it uses the authentication token and API endpoint of each SNS service as input and saves the obtained timeline data as output in a database.

[0363] Step 2:

[0364] The server cleanses the acquired timeline data. Specifically, it removes unnecessary fields from the JSON data and extracts only important fields (e.g., post content, timestamp, and user information). It removes noise and duplicate data to generate a clean dataset. In this process, it uses the acquired timeline data as input and generates cleansed data as output.

[0365] Step 3:

[0366] The server uses natural language processing techniques to extract keywords, hashtags, and entities from the cleansed data. Specifically, it uses natural language processing libraries (e.g., spaCy, NLTK) to parse the text of posts and extract important words and phrases. This process uses the cleansed data as input and produces a list of extracted keywords, hashtags, and entities as output.

[0367] Step 4:

[0368] The server evaluates the importance of posts based on the extracted data. Specifically, it calculates a score taking into account engagement data (e.g., number of likes, retweets, and comments) and selects posts with high importance. In this process, it uses the extracted data and engagement data as input and generates an importance evaluation result as output.

[0369] Step 5:

[0370] The server uses an emotion engine to analyze the user's emotional data and reflects the results in the importance rating. Specifically, the emotion engine analyzes the user's emotional state from the post content and operation data and modifies the importance rating. In this process, the post content and operation data are used as input, and a modified importance rating result is generated as output.

[0371] Step 6:

[0372] The server automatically summarizes posts based on the importance assessment results. Specifically, it uses a generative AI model (e.g., GPT-3) to generate a summary by briefly summarizing the main points of each post. In this process, it uses the importance assessment results as input and generates summarized text as output.

[0373] Step 7:

[0374] The server collects and provides links related to the summarized information, specifically, links to the original post and additional details in the summary data. This process uses the summary text as input and generates the linked summary data as output.

[0375] Step 8:

[0376] The server formats the summary information based on the user's delivery settings. Specifically, it formats the summary information into a format such as email or app notification according to the delivery method selected by the user. In this process, the server uses the linked summary data and delivery setting information as input and generates formatted delivery data as output.

[0377] Step 9:

[0378] The server provides the formatted delivery data to the user, specifically by sending summary information to the user via a mail server or push notification system, using the formatted delivery data as input and generating the notification sent to the user as output.

[0379] Step 10:

[0380] The server records user actions and analyzes the recorded data. Specifically, it records user actions such as displaying summary information and clicking links, and analyzes the data to improve the system. In this process, it uses user action data as input and generates analysis results as output.

[0381] (Application example 2)

[0382] 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."

[0383] In recent years, with the spread of social networking services, users are surrounded by a vast amount of information. This makes it difficult for them to find the information they truly need. Furthermore, there is a need for systems that can provide information that responds to users' emotions, rather than simply collecting and summarizing information. Furthermore, there is a need for systems that can improve the shopping experience in virtual stores by analyzing users' emotions and suggesting products based on those emotions.

[0384] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0385] In this invention, the server includes means for collecting timeline data from an SNS service, means for cleansing the collected timeline data and removing unnecessary data, means for extracting keywords, hashtags, and entities from the posted content using natural language processing technology, means for evaluating the importance of posts based on the extracted data, means for automatically summarizing the evaluated important posts, means for delivering the summarized information to users, means for providing links related to the delivered information, means for recording user operations, means for analyzing the recorded operation data and improving the summarization algorithm and delivery method, means for analyzing emotions from the recorded operation data, and means for suggesting products based on the analyzed emotion data. This makes it possible to efficiently extract important information from an SNS service and provide information and product suggestions optimized to match the user's emotions.

[0386] "SNS service" is an abbreviation for social networking service, a platform that allows users to communicate with other users online.

[0387] "Timeline data" is data that displays the content posted by users on social media services and the actions (likes, retweets, etc.) taken by other users in chronological order.

[0388] "Cleansing" is a process of removing unnecessary information and noise from collected data, and is a preprocessing step to improve the quality of the data.

[0389] "Automatic summarization" refers to the process of shortening long posts and extracting only the main points in a concise manner.

[0390] "Natural language processing technology" is a technology that enables computers to understand, interpret, and process human language, specifically extracting keywords and entities, and analyzing sentiment.

[0391] "Emotional data" refers to data related to emotions such as joy, sadness, and surprise that are derived from users' posts and actions.

[0392] "Suggesting products" means selecting and presenting products that are highly relevant to the user based on analyzed emotional data and the user's past operation data.

[0393] A "summarization algorithm" is a method or formula for summarizing the content of a post in a concise manner, and includes machine learning models and rule-based methods.

[0394] "Delivery method" refers to the means by which summary information and product suggestions are provided to users, including email, app notifications, dashboard displays, etc.

[0395] The following describes in detail an embodiment of the present invention. The present invention is a system that collects timeline data from social networking services and efficiently provides important information to users. This system also incorporates a function to analyze users' emotions and make product recommendations based on those emotions.

[0396] The server first collects timeline data through the API of the social media service. At this time, it authenticates the user using an authentication token. The collected data undergoes a cleansing process to remove unnecessary information. Next, it uses natural language processing technology to extract keywords, hashtags, and entities from the post content.

[0397] Based on the extracted data, the server rates the posts' importance, taking into account engagement data (number of likes, retweets, comments, etc.). The ranked important posts are automatically summarized to generate a summary, which includes links to the original post and additional details.

[0398] The summarized information is formatted appropriately based on the user's delivery settings and delivered to the user via email, app notifications, etc. User actions (viewing the summary information, clicking links, etc.) are recorded and sent to a server. Analysis of this recorded data allows for improvements to the summarization algorithm and delivery method.

[0399] Furthermore, an emotion engine is used to analyze emotions from user posts and operation data. Emotional data extracted from the recorded operation data is reflected in the evaluation of the importance of information and product suggestions. Based on the emotional data, the most suitable products are selected from a product catalog and suggested to the user.

[0400] In this embodiment, a smartphone, smart glasses, or a head-mounted display can be used as hardware, and the Requests library, a natural language processing library (e.g., NLTK or spaCy), and a sentiment analysis library (e.g., VADER) are used as software.

[0401] For example, if a user posts on social media that they want a new smartphone, the server collects the post, cleansing it, and extracts keywords. The emotion engine then determines that the post is a "joy" message, generates summary information, and suggests suitable smartphones and accessories. This information is then sent via email or notification based on the user's settings.

[0402] Example prompt sentence:

[0403] Build a system program that analyzes emotions such as joy and sadness based on the content users post on social media and suggests the best products for them.

[0404] As described above, this system can improve user convenience by efficiently extracting important information from SNS services and providing information and product suggestions that match the user's emotions.

[0405] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0406] Step 1:

[0407] The server accesses the API of the SNS service and collects timeline data using the authentication token.

[0408] Input: SNS service API URL, authentication token

[0409] Output: A list of timeline data

[0410] Specific operation: The server sends an HTTP request to the API of each SNS service and retrieves the user's timeline data using the authentication token. The retrieved data is saved in list format.

[0411] Step 2:

[0412] The server cleanses the collected timeline data and removes unnecessary data.

[0413] Input: List of timeline data

[0414] Output: Cleansed timeline data

[0415] How it works: The server analyzes the collected timeline data and removes unnecessary information such as spam, advertisements, and duplicate data. The cleansed data is then passed on to the next processing step.

[0416] Step 3:

[0417] The server uses natural language processing technology to extract keywords, hashtags, and entities from the post content.

[0418] Input: Cleansed timeline data

[0419] Output: A list of extracted keywords, hashtags, and entities

[0420] How it works: The server uses a natural language processing library (such as NLTK or spaCy) to analyze the text data and extract important keywords and entities. The extracted information is saved in a list format.

[0421] Step 4:

[0422] The server evaluates the importance of the post based on the extracted data.

[0423] Input: List of keywords, hashtags, entities

[0424] Output: A list of posts with their importance ratings

[0425] Specific operation: The server calculates an importance score based on the extracted keywords and engagement data (number of likes, retweets, and comments) and evaluates the importance of each post. Posts with high importance are passed on to the next step.

[0426] Step 5:

[0427] The server automatically summarizes the most important posts that have been rated.

[0428] Input: A list of posts with importance ratings

[0429] Output: List of summary information

[0430] How it works: The server uses machine learning models and rule-based methods to extract and shorten the main points that summarize the post content. The generated summary information is saved in a list format.

[0431] Step 6:

[0432] The server collects links related to the summarized information and appends them to the summary data.

[0433] Input: List of summary information

[0434] Output: A list of summary data with link information added

[0435] What happens: The server collects links to the original post and additional details and adds them to the summary information. The linked data is passed on to the next step.

[0436] Step 7:

[0437] The server prepares the summary information based on the user's delivery preferences.

[0438] Input: User's delivery settings, list of summary data with link information

[0439] Output: Summary data formatted for delivery

[0440] Specific behavior: The server takes into account the user's delivery preferences (email, app notifications, dashboard display) and formats the summary data appropriately.

[0441] Step 8:

[0442] The server delivers the summary information to the user in a manner that depends on the settings.

[0443] Input: Summary data formatted for delivery

[0444] Output: Notifications and emails delivered to users

[0445] Specific operation: The server uses the mail server or push notification to send summary information to the user, who then receives the information on their device.

[0446] Step 9:

[0447] The device records user actions (displaying summary information, clicking links, etc.) and sends them to the server.

[0448] Input: User operation data

[0449] Output: Operation data sent to the server

[0450] Specific operation: When a user views summary information on their device and clicks on a link, the operation data is recorded and sent to the server.

[0451] Step 10:

[0452] The server analyzes the recorded operation data and improves the summarization algorithm and delivery method.

[0453] Input: User operation data

[0454] Output: Improved summarization algorithms and delivery methods

[0455] Specific operation: The server analyzes user operation data, evaluates the performance of the summarization algorithm and delivery method, and makes necessary adjustments and improvements to reflect them in future deliveries.

[0456] Step 11:

[0457] The server analyzes emotions from the recorded operation data.

[0458] Input: User operation data

[0459] Output: Emotion data

[0460] Specific operation: The server uses a sentiment analysis library (e.g., VADER) to calculate the user's sentiment score from the operation data. The calculated sentiment data is reflected in the information importance rating and product recommendations.

[0461] Step 12:

[0462] The server suggests products based on the analyzed emotion data.

[0463] Input: Emotion data, product catalog

[0464] Output: A list of suggested products for the user

[0465] Specific operation: The server selects the most suitable products from the product catalog based on the emotion data and proposes them to the user. The selected product list is then provided to the user along with summary information.

[0466] 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.

[0467] 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.

[0468] 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.

[0469] [Second embodiment]

[0470] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0471] 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.

[0472] 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).

[0473] 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.

[0474] 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.

[0475] 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).

[0476] 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.

[0477] 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.

[0478] 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.

[0479] 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.

[0480] 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.

[0481] 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."

[0482] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes embodiments of the present invention, which are merely illustrative and do not limit the present invention.

[0483] This invention is a system that collects timeline data from SNS services and efficiently provides important information to users. This system consists of three main components: a server, a terminal, and a user.

[0484] server

[0485] The server is responsible for collecting timeline data from SNS services. Specifically, it accesses the API of each SNS service and retrieves the timeline data using an authentication token. The collected data is stored in a database on the server.

[0486] The server cleanses the stored timeline data and removes unnecessary data, which improves data accuracy and makes subsequent processing more efficient.

[0487] The server uses natural language processing techniques to extract keywords, hashtags, and entities from posts, thereby identifying important information from the collected data.

[0488] The server evaluates the importance of posts based on the extracted data and selects the most important posts, taking into account engagement data (number of likes, retweets, comments, etc.).

[0489] The server automatically summarizes the selected important posts and generates summary data that is delivered to users in a format that is easy for users to understand.

[0490] The server provides links associated with the summarized information, allowing the user to view more detailed information.

[0491] The server records and analyzes user actions (clicks on summary information, links, etc.), which allows for continuous improvement of the summary algorithm and delivery method.

[0492] Terminal

[0493] A terminal is a device (such as a smartphone, tablet, or PC) that a user uses to access the system. The user can use the terminal to receive the collected summary information.

[0494] The device records the user's actions and sends them to the server, which provides feedback to the server and uses it to improve the system.

[0495] User

[0496] A user is an individual or a corporation who wants to efficiently obtain important information from an SNS service. A user can use the service by registering their SNS account information in the system and providing the necessary information.

[0497] The user receives and checks the summary information delivered from the server using a terminal, and can also refer to detailed information by clicking on related links.

[0498] Users can customize their own notification settings, such as the frequency of notifications and how they want to receive them (email notifications, app notifications, etc.).

[0499] Specific examples

[0500] For example, suppose User A has registered accounts for social networking services (e.g., Twitter and Facebook) in the system. The server accesses the APIs of these social networking services to collect User A's timeline data. The server then cleanses the collected data and extracts important keywords and hashtags using natural language processing technology. The server then evaluates the importance of posts based on the extracted data and selects particularly important posts. The server then summarizes the selected posts and provides them to User A in the form of emails or app notifications. The summaries also include links related to the original posts, allowing User A to view the details. Furthermore, any actions User A takes on notifications are recorded by the device and sent to the server. This feedback data is used to improve the system's summarization algorithm and delivery method.

[0501] As described above, the system of the present invention can efficiently extract important information from SNS services and provide it to users, thereby solving the problem of information overload and improving user convenience.

[0502] The processing flow will be explained below.

[0503] Step 1:

[0504] The server accesses the API of the SNS service registered by the user and requests timeline data using the authentication token. Specifically, it sends an API request to obtain the user's timeline data (post content, number of likes, number of retweets, etc.).

[0505] Step 2:

[0506] The server receives the timeline data returned from the API and stores it in an internal database, along with metadata such as timestamps and user IDs.

[0507] Step 3:

[0508] The server cleanses the stored timeline data, removing duplicates and unnecessary data (such as advertising posts and spam) and checking the integrity of the data.

[0509] Step 4:

[0510] The server then uses natural language processing techniques to extract keywords, hashtags, and entities from the cleansed data, including techniques such as tokenization, part-of-speech tagging, and entity recognition.

[0511] Step 5:

[0512] The server evaluates the importance of each post based on the extracted keywords and entities, and uses a scoring algorithm to select the most important posts, taking into account engagement data (number of likes, retweets, comments, etc.).

[0513] Step 6:

[0514] The server then summarises the ranked posts, using machine learning models and rule-based techniques to provide a short summary of the posts' key points.

[0515] Step 7:

[0516] The server collects links related to the summarized information (such as the original post, additional details, etc.) and adds them to the summary data, allowing users to easily check for more information.

[0517] Step 8:

[0518] The server prepares the summary information based on the user's delivery preferences (e.g. email, app notification, dashboard view) and formats the summary data accordingly.

[0519] Step 9:

[0520] The server delivers the summary information to the user in a manner that depends on the user's settings, such as by emailing the summary information via a mail server or by sending a push notification to the app.

[0521] Step 10:

[0522] The device records user operations (such as displaying summary information and clicking links), and this operation data is saved as a log.

[0523] Step 11:

[0524] The server collects and analyzes user operation data sent from the device, and uses this data to improve the summarization algorithm and delivery method.

[0525] Step 12:

[0526] The server reflects the analysis results and optimizes the information gathering, summarizing, and distribution process from the next time onwards, thereby improving the quality of information provided to users.

[0527] Example 1

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

[0529] Modern social networking services provide a vast amount of information, but it is difficult to efficiently extract and provide important information to users. In particular, because they contain a lot of unnecessary data and spam, it takes a lot of time and effort for users to find the information they truly need. In addition, there is a lack of a mechanism for continuously improving the system based on user operation history and delivering information that is more appropriate for users.

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

[0531] In this invention, the server includes means for collecting timeline data from social networking services, means for cleansing the collected timeline data and removing unnecessary data, and means for extracting keywords, hashtags, and entities from posted content using natural language processing technology. This improves information accuracy and removes unnecessary data, allowing only important information to be efficiently extracted and provided to users. Furthermore, adding a means for users to customize delivery frequency and notification method enables information delivery tailored to individual user needs. Furthermore, by recording user operations and analyzing the operation data, the system can continuously improve the summarization algorithm and delivery method, thereby improving the overall convenience of the system.

[0532] "SNS service" is an abbreviation for social networking service, which is an online platform that enables users to communicate and share information with other users via the Internet.

[0533] "Timeline data" refers to a series of messages and updates posted on a social networking service that relate to a specific user.

[0534] "Cleansing" is the process of removing unnecessary data and noise from collected data and making it usable.

[0535] "Unnecessary data" refers to information collected by the system that is not suitable for analysis or use, such as spam and advertisements.

[0536] "Natural language processing technology" is a technology that allows computers to analyze and understand human language, and it analyzes the meaning of documents using language models and algorithms.

[0537] A "keyword" refers to a word that is considered particularly important in text data and is used as a target for search and analysis.

[0538] A "hashtag" is a tag used on social media services to indicate a specific topic or theme, and usually refers to a word or phrase preceded by the " " symbol.

[0539] An "entity" is a word or phrase that has a specific meaning in natural language processing, and refers to a proper noun or a specific concept.

[0540] "Assessing importance" is the process of identifying particularly valuable information from the collected data and determining its priority.

[0541] A "summary" is a conversion of the entire original information into a short, concise, and simplified representation that includes the main points.

[0542] A "link" is a reference, in the form of a URL, to a web page or other Internet resource that can be clicked to access related information.

[0543] "Recording operations" means saving the actions (clicks, taps, etc.) that a user takes on the system as data.

[0544] "Analysis" is the process of examining recorded data in detail to understand its meaning and patterns.

[0545] "Customization" refers to adjusting system settings and features to suit the user's preferences and needs.

[0546] The present invention provides a system that collects timeline data from SNS services and efficiently provides important information to users. The following embodiment is an example and is not intended to limit the present invention.

[0547] server

[0548] Collection Steps

[0549] The server is responsible for collecting timeline data from social networking services. Specifically, it accesses the API of each social networking service and retrieves the timeline data using an authentication token. For example, it collects data using the Twitter API or Facebook API. The collected data is stored in a database on the server.

[0550] Cleansing Step

[0551] The server cleanses the stored timeline data and removes unnecessary data, using spam, advertisement, and other filtering methods, which improves the accuracy of the data and makes subsequent processing more efficient.

[0552] Natural Language Processing Step

[0553] The server uses natural language processing techniques to extract keywords, hashtags, and entities from posts, such as text analysis using natural language processing libraries NLTK and spaCy, to identify important information from the collected data.

[0554] Importance evaluation step

[0555] The server evaluates the importance of posts based on the extracted data and selects important posts. This process also takes into account engagement data (number of likes, retweets, comments, etc.). For example, a post with 100 retweets and 500 likes will be evaluated as having high importance.

[0556] Summary generation step

[0557] The server automatically summarizes selected important posts and generates summary data to be delivered to users using algorithms such as the BERT summarizer. The summaries are provided in a format that is easy for users to understand.

[0558] Related link provision steps

[0559] The server provides links related to the summarized information, for example adding a "Learn more" link at the end of the summary, allowing the user to view more detailed information.

[0560] Operation record and analysis steps

[0561] The server records and analyzes user actions (clicks on summary information, links, etc.), which allows for continuous improvement of the summary algorithm and delivery method.

[0562] Terminal

[0563] Access and Display Steps

[0564] The terminal is a device (smartphone, tablet, PC, etc.) through which the user accesses the system and can receive the collected summary information. For example, a message saying "New summary information has arrived" will be displayed in the notification bar of the smartphone.

[0565] Operation Record Steps

[0566] The device records the user's actions and sends them to the server, which provides feedback to the server and uses it to improve the system.

[0567] User

[0568] Account registration steps

[0569] A user is an individual or corporation who wants to efficiently obtain important information from a social networking service. A user can use the service by registering their social networking account information in the system and providing the necessary information. For example, they can provide "Twitter API token: xxxxxxxx."

[0570] Information Receipt and Confirmation Steps

[0571] The user receives the summary information delivered from the server using the terminal and checks it. For example, the user can click a details link in the notified summary information to check the details.

[0572] Delivery settings customization steps

[0573] Users can customize their own notification settings, such as the frequency of notifications and how they want to receive them (email notifications, app notifications, etc.).

[0574] Specific examples

[0575] For example, suppose User A has registered accounts for social networking services (e.g., Twitter and Facebook) in the system. The server accesses the APIs of these social networking services to collect User A's timeline data. The server then cleanses the collected data and extracts important keywords and hashtags using natural language processing technology. The server then evaluates the importance of posts based on the extracted data and selects particularly important posts. The server then summarizes the selected posts and provides them to User A in the form of emails or app notifications. The summaries also include links related to the original posts, allowing User A to view the details. Furthermore, any actions User A takes on notifications are recorded by the device and sent to the server. This feedback data is used to improve the system's summarization algorithm and delivery method.

[0576] Example prompt:

[0577] "Generate a program that cleanses timeline data collected from Twitter and Facebook, extracts important information, and summarizes it. Include relevant links in the summary and record user actions to use as feedback data."

[0578] As described above, the system of the present invention can efficiently extract important information from SNS services and provide it to users, thereby solving the problem of information overload and improving user convenience.

[0579] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0580] Step 1:

[0581] Initial settings (server, user)

[0582] The server starts and reads the SNS API key and database connection information from the configuration file. This is done as part of the server initialization process.

[0583] Input: config file

[0584] Output: Initialization completion status

[0585] Users register their social media account information through a web interface or app. For example, by registering "Twitter API token: xxxxxxxx", social media data collection is ready.

[0586] Input: User-entered social media account information

[0587] Output: Registration completion status

[0588] Step 2:

[0589] Data collection (server)

[0590] The server accesses the API of the SNS service using the authentication token and acquires the user's timeline data, for example, the latest tweets using the Twitter API.

[0591] Input: User's authentication token

[0592] Output: Social media timeline data

[0593] The server stores the acquired timeline data in a database.

[0594] Input: Social media timeline data

[0595] Output: Data stored in the database

[0596] Step 3:

[0597] Data cleansing (server)

[0598] The server reads the timeline data stored in the database and removes unnecessary data (spam, advertisements, etc.) using keyword matching and regular expressions as filtering methods.

[0599] Input: Timeline data stored in a database

[0600] Output: Cleansed data

[0601] Specifically, the server filters out posts containing keywords such as "spam" and "advertising."

[0602] Step 4:

[0603] Natural language processing (server)

[0604] The server parses the cleansed timeline data and extracts keywords, hashtags, and entities from posts using natural language processing libraries (NLTK and spaCy).

[0605] Input: Cleansed data

[0606] Output: Extracted keywords, hashtags, and entities

[0607] For example, extract "AI" and "future" from a tweet saying "AI will change the future."

[0608] Step 5:

[0609] Importance rating (server)

[0610] The server evaluates the importance of each post based on the extracted keywords and entities, and also uses engagement data (number of likes, retweets, comments, etc.) to determine the score.

[0611] Input: Extracted keywords, hashtags, entities, and engagement data

[0612] Output: Importance score

[0613] Specifically, the server evaluates posts with 100 retweets and 500 likes as having high importance.

[0614] Step 6:

[0615] Summary generation (server)

[0616] The server automatically summarizes posts that are rated as highly important using a summary generation algorithm (BERT summarizer).

[0617] Input: Posts with high importance scores

[0618] Output: Summary data

[0619] Specifically, it converts "Original post: A new AI technology has been announced. Learn more here." into "Summary: A new AI technology has been announced."

[0620] Step 7:

[0621] Related link provided (server)

[0622] The server provides links related to the summarized posts.

[0623] Input: Summary data

[0624] Output: Summary data with associated links

[0625] Specifically, a "Learn more" link will be added to the end of the summary.

[0626] Step 8:

[0627] Information distribution (server, terminal)

[0628] The server delivers the summary information and related links to the user's device via email, push notification, or other methods depending on the user's delivery settings.

[0629] Input: Summary data with related links, user distribution settings

[0630] Output: Summary information delivered

[0631] The device displays the received summary information to the user. For example, a message saying "New summary information has arrived" is displayed in the notification bar of the smartphone.

[0632] Input: Delivered summary information

[0633] Output: Summary information displayed on the user's screen

[0634] Step 9:

[0635] Operation record and analysis (terminal, server)

[0636] When a user clicks on summary information or related links, the action is recorded in real time on the device.

[0637] Input: User actions

[0638] Output: Operation record data

[0639] The terminal transmits the recorded operation data to the server.

[0640] Input: Operation record data

[0641] Output: Operation data sent to the server

[0642] The server analyzes the received operation data and uses it to improve the summarization algorithm and delivery method.

[0643] Input: Operation data sent to the server

[0644] Output: Analysis results, system improvement information

[0645] Step 10:

[0646] Customizing delivery settings (user)

[0647] Users can adjust the frequency of delivery and notification method to suit their preferences.

[0648] Input: User settings information

[0649] Output: Updated distribution settings

[0650] For example, set the delivery frequency to once a day and the notification method to email notification.

[0651] The above are the specific processing steps of this system.

[0652] (Application example 1)

[0653] 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."

[0654] In modern society, the amount of information disseminated on the Internet is enormous, and there is a high risk of missing important security-related information. This poses a challenge, making it difficult for individuals and companies to quickly implement security measures. There is also a need for a method to efficiently collect information scattered across social networking sites and extract and provide only the necessary information. A method is needed to solve this information overload problem and provide important security information quickly and efficiently.

[0655] 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.

[0656] In this invention, the server includes means for collecting timeline data from SNS services, means for cleansing the collected timeline data and removing unnecessary data, means for extracting keywords, hashtags, and entities from post content using natural language processing technology, means for evaluating the importance of posts based on the extracted data, means for automatically summarizing the evaluated important posts, means for delivering the summarized information to users, means for providing links related to the delivered information, means for recording user operations, means for analyzing the recorded operation data and improving the summarization algorithm and delivery method, and means for collecting data from security-related SNS accounts and providing notifications in real time. This makes it possible to efficiently collect important security-related information and quickly notify users.

[0657] "SNS service" is an abbreviation for social networking service, an online platform that makes it easy for users to share information over the Internet.

[0658] "Timeline data" is a continuous record of information posted by users and related accounts on social media services, and is data displayed in chronological order.

[0659] "Cleansing" is the process of removing unnecessary information and noise from collected data and organizing it to include only the necessary information.

[0660] "Natural language processing technology" refers to all technologies that allow computers to interpret, analyze, and process human language.

[0661] "Keywords" are words or phrases that are particularly important in text or data, and are used for search and analysis.

[0662] A "hashtag" is a short phrase used on social media to express a specific keyword or topic, and begins with the symbol "."

[0663] An "entity" is information that indicates an independent existence, such as a specific name or title, and refers to a specific item such as a store name, a person's name, or a place name.

[0664] "Importance" is a measure of the value and urgency of information in collected data or posts based on specific criteria.

[0665] A "summary" is a short, concise expression of long information that extracts and provides the essential content.

[0666] A "link" is a string of characters or a button that allows you to connect to a specific location or information on the Internet, and is a means of accessing other web pages or resources.

[0667] "Operation data" is a record of a series of actions a user performs while using a system, including actions such as clicking, scrolling, and typing.

[0668] An "authentication token" is a temporary string of characters that proves a user has been authenticated to a system and is used to ensure secure access.

[0669] "Delivery settings" are settings that allow users to customize how and how often they receive information.

[0670] "Real-time" refers to the instant display and reflection of current situations and actions, and refers to a state in which information is provided without delay.

[0671] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes embodiments of the present invention, which are merely illustrative and do not limit the present invention.

[0672] In this system, to obtain timeline data from a social networking service, the server first accesses the social networking service's API and collects the data using an authentication token. For example, the server uses the authentication token to obtain security-related timeline data from the Twitter or Facebook API.

[0673] The collected data is stored in a database on the server, where it undergoes a data cleansing process. This cleansing process removes unnecessary data and noise, leaving only the important security data. Next, natural language processing techniques are used to extract keywords, hashtags, and entities from the posts. For example, natural language processing libraries (e.g., NLTK, SpaCy) are used to extract important keywords such as "phishing attack" and "virus" from the posts.

[0674] The server then evaluates the importance of posts based on the extracted data. Specifically, it uses engagement data (e.g., the number of likes, retweets, and comments) to quantify the importance of each post. It also automatically selects particularly important posts based on these values ​​and generates summaries. For example, it might determine that "this post has received many likes and retweets, so it is highly important."

[0675] After selecting important posts, the server summarizes them and delivers them to users. This can be delivered via email or push notifications. The summaries also include links related to the original posts, allowing users to easily view more detailed information. The server also records the actions users take on the information they receive as notifications (e.g., clicks and scrolls) and sends the data to the server. This action data is analyzed and used to improve the summarization algorithm and delivery method.

[0676] Additionally, the system specifically collects data from security-related social media accounts and provides real-time notifications to users, who can view these notifications using their smartphones, tablets, PCs, or other devices.

[0677] As a concrete example, consider the case where a security officer uses this system. The officer registers his / her social media account in the system and configures it to collect security-related information in real time. The following prompt sentence is input to the generative AI model:

[0678] Username: @cybersecuritynews

[0679] Post content: Sharing important information about the latest phishing attacks. Click here for detailed countermeasures. [Link]

[0680] Engagement data: Likes 50, Retweets 20, Comments 10

[0681] Based on this prompt, the generative AI model summarizes important information and notifies the security personnel. The security personnel can then click on a link to view more detailed information if necessary. This process allows security personnel to take prompt action without missing any important information.

[0682] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0683] Step 1:

[0684] The server accesses the API of the SNS service and collects timeline data using the authentication token. The input is the API endpoint of the SNS service and the authentication token, and the output is the collected timeline data. Specifically, the server sends an HTTP request to retrieve authenticated user data.

[0685] Step 2:

[0686] The server cleanses the collected timeline data. The input is the timeline data collected in step 1, and the output is the cleansed data. Specifically, a filtering process is performed to remove noise and unnecessary information from the timeline data stored in the database.

[0687] Step 3:

[0688] The server uses natural language processing technology to extract keywords, hashtags, and entities from the post content. The input is the cleansed data from step 2, and the output is the extracted keywords, hashtags, and entities. Specifically, it uses a natural language processing library to perform text analysis and extract important words and phrases.

[0689] Step 4:

[0690] The server evaluates the importance of posts based on the extracted data. The input is the keywords, hashtags, entities, and engagement data extracted in step 3, and the output is an importance score for each post. Specifically, the server applies a scoring algorithm based on the number of likes, retweets, comments, etc. to calculate the importance.

[0691] Step 5:

[0692] The server automatically summarizes the rated important posts. The input is the posts with high importance scores obtained in step 4, and the output is the summarized information. Specifically, it uses a generative AI model to convert the post content into a summary sentence.

[0693] Step 6:

[0694] The server delivers the summarized information to the user. The input is the summarized information from step 5, and the output is a notification message to the user. Specifically, the information is delivered via email notification or the app's push notification function.

[0695] Step 7:

[0696] The server provides links related to the distributed information. The input is the summarized information from step 5, and the output is links related to the summarized information. Specifically, the server extracts links from the original post and adds them to the summary.

[0697] Step 8:

[0698] The device records user operations. The input is the user's operations on the device (clicks, scrolls, etc.), and the output is a record of those operations. Specifically, it sets up an event listener and records each operation event in a log.

[0699] Step 9:

[0700] The server analyzes the recorded operation data and improves the summarization algorithm and delivery method. The input is the operation data recorded in step 8, and the output is an improved summarization algorithm and delivery method. Specifically, the operation data is statistically analyzed and the algorithm is adjusted through a feedback loop.

[0701] Step 10:

[0702] The server collects data from security-related social media accounts and provides notifications in real time. The input is data from security-related social media accounts, and the output is security information notifications delivered in real time. Specifically, it prioritizes data posted from specific security-related accounts and immediately notifies users.

[0703] 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.

[0704] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following embodiments are illustrative and do not limit the present invention.

[0705] This invention combines a system that collects timeline data from SNS services and efficiently provides important information to users with an emotion engine. This system consists of four main components: a server, a device, a user, and an emotion engine.

[0706] server

[0707] The server is responsible for collecting timeline data from SNS services. Specifically, it accesses the API of each SNS service and retrieves the timeline data using an authentication token. The collected data is stored in a database on the server.

[0708] The server cleanses the stored timeline data and removes unnecessary data, which improves data accuracy and makes subsequent processing more efficient.

[0709] The server uses natural language processing techniques to extract keywords, hashtags, and entities from posts, thereby identifying important information from the collected data.

[0710] The server evaluates the importance of posts based on the extracted data and selects the most important posts, taking into account engagement data (number of likes, retweets, comments, etc.).

[0711] The server uses an emotion engine to analyze the user's emotions from the collected timeline data and the user's past operation data, and reflects the emotion data in the importance evaluation of the summary information.

[0712] The server then summarises the selected important posts, using machine learning models and rule-based techniques to create short summaries of the posts' key points.

[0713] The server collects links related to the summarized information (such as the original post, additional details, etc.) and adds them to the summary data, allowing users to easily find more information.

[0714] The server prepares the summary information based on the user's delivery preferences (e.g. email, app notification, dashboard view) and formats the summary data accordingly.

[0715] The server delivers the summary information to the user in a manner that depends on the user's settings, for example, by emailing the summary information via a mail server or by sending a push notification to the app.

[0716] The server records and analyzes user actions (viewing summary information, clicking links, etc.) to continually improve the summary algorithm and delivery method.

[0717] Terminal

[0718] A terminal is a device (such as a smartphone, tablet, or PC) that a user uses to access the system. The user can use the terminal to receive the collected summary information.

[0719] The device records the user's actions and sends them to the server, which provides feedback to the server and uses it to improve the system.

[0720] User

[0721] A user is an individual or a corporation who wants to efficiently obtain important information from an SNS service. A user can use the service by registering their SNS account information in the system and providing the necessary information.

[0722] The user receives and checks the summary information delivered from the server using a terminal, and can also refer to detailed information by clicking on related links.

[0723] Users can customize their own notification settings, such as the frequency of notifications and how they want to receive them (email notifications, app notifications, etc.).

[0724] Emotion Engine

[0725] The emotion engine is a component for recognizing user emotions, which allows us to analyze user emotions from collected timeline data and user operation data.

[0726] The emotion engine has an algorithm that determines the user's emotions (happiness, surprise, sadness, etc.) from the content of posts and operation data. The emotion data is sent to the server and used to evaluate the importance of summary information and improve delivery methods.

[0727] The sentiment engine analyzes how users feel about specific keywords or entities and reflects this in selecting and summarizing important information.

[0728] Specific examples

[0729] For example, suppose User B has registered accounts for social networking services (e.g., Twitter and Instagram) in the system. The server accesses the APIs of these social networking services to collect User B's timeline data. It then cleanses the collected data and extracts important keywords and hashtags using natural language processing technology. The server uses an emotion engine to analyze emotions from User B's timeline data and past operation data, and reflects the emotion data in the importance rating of the summary information. For example, User B may rate posts containing keywords that frequently indicate the emotion "joy" as highly important. The server then summarizes the important posts and provides them to User B in the form of emails or app notifications. The summaries also include links related to the original posts, allowing User B to view the details. The emotion engine also collects User B's emotion data, which is used for future system optimization.

[0730] As described above, the system of the present invention can efficiently extract important information from SNS services and provide information optimized to suit the user's emotions, thereby solving the problem of information overload and improving user convenience.

[0731] The processing flow will be explained below.

[0732] Step 1:

[0733] The server accesses the API of the SNS service registered by the user and requests timeline data using the authentication token. Specifically, it sends an API request to obtain the user's timeline data (post content, number of likes, number of retweets, etc.).

[0734] Step 2:

[0735] The server receives the timeline data returned from the API and stores it in an internal database, along with metadata such as timestamps and user IDs.

[0736] Step 3:

[0737] The server cleanses the stored timeline data, removing duplicates and unnecessary data (such as advertising posts and spam) and checking the integrity of the data.

[0738] Step 4:

[0739] The server then uses natural language processing techniques to extract keywords, hashtags, and entities from the cleansed data, including techniques such as tokenization, part-of-speech tagging, and entity recognition.

[0740] Step 5:

[0741] The server evaluates the importance of each post based on the extracted keywords and entities, and uses a scoring algorithm to select the most important posts, taking into account engagement data (number of likes, retweets, comments, etc.).

[0742] Step 6:

[0743] The server analyzes the user's emotions using an emotion engine, which uses an algorithm to determine the user's emotions (e.g., joy, surprise, sadness) based on specific posts and past activity data.

[0744] Step 7:

[0745] The server adjusts the importance rating based on the analysis results of the emotion engine. Posts containing keywords that users frequently express the emotion of "joy" are given a higher rating.

[0746] Step 8:

[0747] The server then summarises the ranked posts, using machine learning models and rule-based techniques to provide a short summary of the posts' key points.

[0748] Step 9:

[0749] The server collects links related to the summarized information (such as the original post, additional details, etc.) and adds them to the summary data, allowing users to easily find more information.

[0750] Step 10:

[0751] The server prepares the summary information based on the user's delivery preferences (e.g. email, app notification, dashboard view) and formats the summary data accordingly.

[0752] Step 11:

[0753] The server delivers the summary information to the user in a manner that depends on the user's settings, such as by emailing the summary information via a mail server or by sending a push notification to the app.

[0754] Step 12:

[0755] The device records user operations (such as displaying summary information and clicking links), and this operation data is saved as a log.

[0756] Step 13:

[0757] The server collects and analyzes user operation data sent from the device, and uses this data to improve the summarization algorithm and delivery method.

[0758] Step 14:

[0759] The server will then apply the analysis results to optimize the information gathering, summarizing, and distribution processes from the next time onward, thereby improving the quality of the information provided to users.

[0760] Example 2

[0761] 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."

[0762] Currently, there is a huge amount of information available on social networking services, making it difficult for users to efficiently obtain important information. Furthermore, information provided does not take into account the user's emotional state, so information that meets the user's needs is often not provided. This increases the likelihood that users will miss useful information in this information-overloaded world. Furthermore, there is a need to accurately evaluate the importance and relevance of the information provided and deliver it to users in an appropriate format.

[0763] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0764] In this invention, the server includes means for collecting timeline data from an SNS service, means for cleansing the collected timeline data and removing unnecessary data, means for extracting keywords, hashtags, and entities from the posted content using natural language processing technology, means for evaluating the importance of posts based on the extracted data, means for analyzing user emotion data and reflecting the results in the importance evaluation, means for automatically summarizing the evaluated important posts, means for providing links related to the summarized information, means for formatting the summarized information based on the user's distribution settings, means for providing the distributed information to the user, means for recording user operations, and means for analyzing the recorded operation data and improving the summarization algorithm and distribution method. This allows users to efficiently obtain important information from vast amounts of information and further enables the provision of appropriate information according to the user's emotional state.

[0765] "SNS service" refers to a social networking service, an online platform for people to communicate over the Internet.

[0766] "Timeline data" refers to data that shows the content posted by users on social networking services and the order in which they were posted.

[0767] "Cleansing" is the process of removing unnecessary information from collected timeline data and extracting important information.

[0768] "Natural language processing technology" is a technology that allows computers to analyze and understand human language.

[0769] "Keywords" are important words or phrases in your post.

[0770] A "hashtag" is a tag preceded by the " " symbol that is added to a post to indicate a particular topic or theme.

[0771] An "entity" is a proper noun such as a person's name, place name, or organization name contained in the posted content.

[0772] "Importance evaluation" is the process of measuring the value and importance of a post based on certain criteria and assigning a score.

[0773] "Emotional data" refers to information that indicates the emotional state of a user.

[0774] "Summarizing" refers to the process of briefly summarizing the main points of the posted content.

[0775] "Link" means a URL or hyperlink that provides a connection to related sources of information or further information.

[0776] "Delivery Preferences" refers to options that allow users to set how they wish to receive information.

[0777] "Operational Data" means records of actions and events performed by users on the system.

[0778] A "summarization algorithm" is a formula or method used to efficiently summarize a post's content.

[0779] "Delivery method" refers to the means or process used to provide information to users.

[0780] The present invention is configured by combining a system that collects timeline data from SNS services and efficiently provides important information to users with an emotion engine.

[0781] server

[0782] The server is responsible for collecting timeline data from SNS services. Specifically, the server accesses the API of each SNS service (e.g., social networking platform) and obtains timeline data using an authentication token. This data is then stored in the server's database.

[0783] The collected data goes through a cleansing process to remove unnecessary data. This process improves the accuracy of the data and makes subsequent processing more efficient. The server uses natural language processing techniques (e.g., natural language processing libraries) to extract keywords, hashtags, and entities from the posts, thereby identifying important information.

[0784] Next, the server evaluates the importance of posts based on the extracted data. The server considers engagement data (e.g., number of likes, retweets, and comments) and reflects this in the importance evaluation. Furthermore, it uses an emotion engine to analyze user emotion data and reflects this in the importance evaluation of the summary information.

[0785] The server uses machine learning models (e.g., generative AI models) to automatically summarize important posts that have been rated, and also includes relevant links to help users find more information.

[0786] The server formats the summary information based on the user's delivery settings and prepares it for delivery. For example, if the user selects email notification, the server formats the summary information in HTML format and prepares it for email transmission. Finally, the server uses a delivery method such as sending the summary information via email via a mail server.

[0787] The server also records and analyzes user actions (viewing summary information, clicking links), and the resulting data is used to improve the summary algorithm and delivery method.

[0788] Terminal

[0789] The terminal is a device (e.g., smartphone, tablet, or PC) that users use to access the system. The user can use the terminal to receive and check the summary information delivered to them. The terminal also records the user's actions and sends them to the server. This data is passed to the server as feedback and used to improve the system.

[0790] User

[0791] A user is an individual or a corporation who wants to efficiently obtain important information from an SNS service. A user can use this service by registering their SNS account information in the system and providing the necessary information.

[0792] Users can use their devices to check summary information delivered from the server and click on related links to view detailed information. Users can also customize their delivery settings to receive information in a way that suits their needs (e.g., email notifications, app notifications).

[0793] Specific examples

[0794] For example, suppose User B has registered an account for a social networking service (e.g., a social networking platform) in the system. The server accesses the APIs of these social networking services to collect User B's timeline data. The server then cleanses the collected data and uses natural language processing technology to extract important keywords and hashtags.

[0795] The server uses an emotion engine to analyze emotions from User B's timeline data and past operation data, and reflects that emotion data in the importance rating of the summary information. For example, User B rates posts containing keywords that frequently indicate the emotion of "joy" with a high importance rating. Next, the server summarizes the important posts using a generative AI model and provides them to User B in the form of an email or app notification. The summary also includes a link related to the original post, allowing User B to check the details.

[0796] The emotion engine also collects emotion data from User B, which will be used to optimize the system in the future. Specific examples of prompt sentences are as follows:

[0797] "Extract important keywords from User B's social networking platform timeline data, analyze the user's sentiment using a sentiment engine, and summarize the important information. Include relevant links in the summary and provide it in the form of an email notification."

[0798] In this way, the present invention is a system that efficiently extracts important information from SNS services and provides information optimized to the user's emotions, thereby solving the problem of information overload and improving user convenience.

[0799] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0800] Step 1:

[0801] The server calls the API of the SNS service to obtain timeline data. Specifically, it sends an API request using the API key and authentication token of each SNS service to obtain timeline data in JSON format. In this process, it uses the authentication token and API endpoint of each SNS service as input and saves the obtained timeline data as output in a database.

[0802] Step 2:

[0803] The server cleanses the acquired timeline data. Specifically, it removes unnecessary fields from the JSON data and extracts only important fields (e.g., post content, timestamp, and user information). It removes noise and duplicate data to generate a clean dataset. In this process, it uses the acquired timeline data as input and generates cleansed data as output.

[0804] Step 3:

[0805] The server uses natural language processing techniques to extract keywords, hashtags, and entities from the cleansed data. Specifically, it uses natural language processing libraries (e.g., spaCy, NLTK) to parse the text of posts and extract important words and phrases. This process uses the cleansed data as input and produces a list of extracted keywords, hashtags, and entities as output.

[0806] Step 4:

[0807] The server evaluates the importance of posts based on the extracted data. Specifically, it calculates a score taking into account engagement data (e.g., number of likes, retweets, and comments) and selects posts with high importance. In this process, it uses the extracted data and engagement data as input and generates an importance evaluation result as output.

[0808] Step 5:

[0809] The server uses an emotion engine to analyze the user's emotional data and reflects the results in the importance rating. Specifically, the emotion engine analyzes the user's emotional state from the post content and operation data and modifies the importance rating. In this process, the post content and operation data are used as input, and a modified importance rating result is generated as output.

[0810] Step 6:

[0811] The server automatically summarizes posts based on the importance assessment results. Specifically, it uses a generative AI model (e.g., GPT-3) to generate a summary by briefly summarizing the main points of each post. In this process, it uses the importance assessment results as input and generates summarized text as output.

[0812] Step 7:

[0813] The server collects and provides links related to the summarized information, specifically, links to the original post and additional details in the summary data. This process uses the summary text as input and generates the linked summary data as output.

[0814] Step 8:

[0815] The server formats the summary information based on the user's delivery settings. Specifically, it formats the summary information into a format such as email or app notification according to the delivery method selected by the user. In this process, the server uses the linked summary data and delivery setting information as input and generates formatted delivery data as output.

[0816] Step 9:

[0817] The server provides the formatted delivery data to the user, specifically by sending summary information to the user via a mail server or push notification system, using the formatted delivery data as input and generating the notification sent to the user as output.

[0818] Step 10:

[0819] The server records user actions and analyzes the recorded data. Specifically, it records user actions such as displaying summary information and clicking links, and analyzes the data to improve the system. In this process, it uses user action data as input and generates analysis results as output.

[0820] (Application example 2)

[0821] 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."

[0822] In recent years, with the spread of social networking services, users are surrounded by a vast amount of information. This makes it difficult for them to find the information they truly need. Furthermore, there is a need for systems that can provide information that responds to users' emotions, rather than simply collecting and summarizing information. Furthermore, there is a need for systems that can improve the shopping experience in virtual stores by analyzing users' emotions and suggesting products based on those emotions.

[0823] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0824] In this invention, the server includes means for collecting timeline data from an SNS service, means for cleansing the collected timeline data and removing unnecessary data, means for extracting keywords, hashtags, and entities from the posted content using natural language processing technology, means for evaluating the importance of posts based on the extracted data, means for automatically summarizing the evaluated important posts, means for delivering the summarized information to users, means for providing links related to the delivered information, means for recording user operations, means for analyzing the recorded operation data and improving the summarization algorithm and delivery method, means for analyzing emotions from the recorded operation data, and means for suggesting products based on the analyzed emotion data. This makes it possible to efficiently extract important information from an SNS service and provide information and product suggestions optimized to match the user's emotions.

[0825] "SNS service" is an abbreviation for social networking service, a platform that allows users to communicate with other users online.

[0826] "Timeline data" is data that displays the content posted by users on social media services and the actions (likes, retweets, etc.) taken by other users in chronological order.

[0827] "Cleansing" is a process of removing unnecessary information and noise from collected data, and is a preprocessing step to improve the quality of the data.

[0828] "Automatic summarization" refers to the process of shortening long posts and extracting only the main points in a concise manner.

[0829] "Natural language processing technology" is a technology that enables computers to understand, interpret, and process human language, specifically extracting keywords and entities, and analyzing sentiment.

[0830] "Emotional data" refers to data related to emotions such as joy, sadness, and surprise that are derived from users' posts and actions.

[0831] "Suggesting products" means selecting and presenting products that are highly relevant to the user based on analyzed emotional data and the user's past operation data.

[0832] A "summarization algorithm" is a method or formula for summarizing the content of a post in a concise manner, and includes machine learning models and rule-based methods.

[0833] "Delivery method" refers to the means by which summary information and product suggestions are provided to users, including email, app notifications, dashboard displays, etc.

[0834] The following describes in detail an embodiment of the present invention. The present invention is a system that collects timeline data from social networking services and efficiently provides important information to users. This system also incorporates a function to analyze users' emotions and make product recommendations based on those emotions.

[0835] The server first collects timeline data through the API of the social media service. At this time, it authenticates the user using an authentication token. The collected data undergoes a cleansing process to remove unnecessary information. Next, it uses natural language processing technology to extract keywords, hashtags, and entities from the post content.

[0836] Based on the extracted data, the server rates the posts' importance, taking into account engagement data (number of likes, retweets, comments, etc.). The ranked important posts are automatically summarized to generate a summary, which includes links to the original post and additional details.

[0837] The summarized information is formatted appropriately based on the user's delivery settings and delivered to the user via email, app notifications, etc. User actions (viewing the summary information, clicking links, etc.) are recorded and sent to a server. Analysis of this recorded data allows for improvements to the summarization algorithm and delivery method.

[0838] Furthermore, an emotion engine is used to analyze emotions from user posts and operation data. Emotional data extracted from the recorded operation data is reflected in the evaluation of the importance of information and product suggestions. Based on the emotional data, the most suitable products are selected from a product catalog and suggested to the user.

[0839] In this embodiment, a smartphone, smart glasses, or a head-mounted display can be used as hardware, and the Requests library, a natural language processing library (e.g., NLTK or spaCy), and a sentiment analysis library (e.g., VADER) are used as software.

[0840] For example, if a user posts on social media that they want a new smartphone, the server collects the post, cleansing it, and extracts keywords. The emotion engine then determines that the post is a "joy" message, generates summary information, and suggests suitable smartphones and accessories. This information is then sent via email or notification based on the user's settings.

[0841] Example prompt sentence:

[0842] Build a system program that analyzes emotions such as joy and sadness based on the content users post on social media and suggests the best products for them.

[0843] As described above, this system can improve user convenience by efficiently extracting important information from SNS services and providing information and product suggestions that match the user's emotions.

[0844] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0845] Step 1:

[0846] The server accesses the API of the SNS service and collects timeline data using the authentication token.

[0847] Input: SNS service API URL, authentication token

[0848] Output: A list of timeline data

[0849] Specific operation: The server sends an HTTP request to the API of each SNS service and retrieves the user's timeline data using the authentication token. The retrieved data is saved in list format.

[0850] Step 2:

[0851] The server cleanses the collected timeline data and removes unnecessary data.

[0852] Input: List of timeline data

[0853] Output: Cleansed timeline data

[0854] How it works: The server analyzes the collected timeline data and removes unnecessary information such as spam, advertisements, and duplicate data. The cleansed data is then passed on to the next processing step.

[0855] Step 3:

[0856] The server uses natural language processing technology to extract keywords, hashtags, and entities from the post content.

[0857] Input: Cleansed timeline data

[0858] Output: A list of extracted keywords, hashtags, and entities

[0859] How it works: The server uses a natural language processing library (such as NLTK or spaCy) to analyze the text data and extract important keywords and entities. The extracted information is saved in a list format.

[0860] Step 4:

[0861] The server evaluates the importance of the post based on the extracted data.

[0862] Input: List of keywords, hashtags, entities

[0863] Output: A list of posts with their importance ratings

[0864] Specific operation: The server calculates an importance score based on the extracted keywords and engagement data (number of likes, retweets, and comments) and evaluates the importance of each post. Posts with high importance are passed on to the next step.

[0865] Step 5:

[0866] The server automatically summarizes the most important posts that have been rated.

[0867] Input: A list of posts with importance ratings

[0868] Output: List of summary information

[0869] How it works: The server uses machine learning models and rule-based methods to extract and shorten the main points that summarize the post content. The generated summary information is saved in a list format.

[0870] Step 6:

[0871] The server collects links related to the summarized information and appends them to the summary data.

[0872] Input: List of summary information

[0873] Output: A list of summary data with link information added

[0874] What happens: The server collects links to the original post and additional details and adds them to the summary information. The linked data is passed on to the next step.

[0875] Step 7:

[0876] The server prepares the summary information based on the user's delivery preferences.

[0877] Input: User's delivery settings, list of summary data with link information

[0878] Output: Summary data formatted for delivery

[0879] Specific behavior: The server takes into account the user's delivery preferences (email, app notifications, dashboard display) and formats the summary data appropriately.

[0880] Step 8:

[0881] The server delivers the summary information to the user in a manner that depends on the settings.

[0882] Input: Summary data formatted for delivery

[0883] Output: Notifications and emails delivered to users

[0884] Specific operation: The server uses the mail server or push notification to send summary information to the user, who then receives the information on their device.

[0885] Step 9:

[0886] The device records user actions (displaying summary information, clicking links, etc.) and sends them to the server.

[0887] Input: User operation data

[0888] Output: Operation data sent to the server

[0889] Specific operation: When a user views summary information on their device and clicks on a link, the operation data is recorded and sent to the server.

[0890] Step 10:

[0891] The server analyzes the recorded operation data and improves the summarization algorithm and delivery method.

[0892] Input: User operation data

[0893] Output: Improved summarization algorithms and delivery methods

[0894] Specific operation: The server analyzes user operation data, evaluates the performance of the summarization algorithm and delivery method, and makes necessary adjustments and improvements to reflect them in future deliveries.

[0895] Step 11:

[0896] The server analyzes emotions from the recorded operation data.

[0897] Input: User operation data

[0898] Output: Emotion data

[0899] Specific operation: The server uses a sentiment analysis library (e.g., VADER) to calculate the user's sentiment score from the operation data. The calculated sentiment data is reflected in the information importance rating and product recommendations.

[0900] Step 12:

[0901] The server suggests products based on the analyzed emotion data.

[0902] Input: Emotion data, product catalog

[0903] Output: A list of suggested products for the user

[0904] Specific operation: The server selects the most suitable products from the product catalog based on the emotion data and proposes them to the user. The selected product list is then provided to the user along with summary information.

[0905] 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.

[0906] 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.

[0907] 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.

[0908] [Third embodiment]

[0909] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0910] 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.

[0911] 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).

[0912] 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.

[0913] 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.

[0914] 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).

[0915] 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.

[0916] 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.

[0917] 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.

[0918] 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.

[0919] 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.

[0920] 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."

[0921] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes embodiments of the present invention, which are merely illustrative and do not limit the present invention.

[0922] This invention is a system that collects timeline data from SNS services and efficiently provides important information to users. This system consists of three main components: a server, a terminal, and a user.

[0923] server

[0924] The server is responsible for collecting timeline data from SNS services. Specifically, it accesses the API of each SNS service and retrieves the timeline data using an authentication token. The collected data is stored in a database on the server.

[0925] The server cleanses the stored timeline data and removes unnecessary data, which improves data accuracy and makes subsequent processing more efficient.

[0926] The server uses natural language processing techniques to extract keywords, hashtags, and entities from posts, thereby identifying important information from the collected data.

[0927] The server evaluates the importance of posts based on the extracted data and selects the most important posts, taking into account engagement data (number of likes, retweets, comments, etc.).

[0928] The server automatically summarizes the selected important posts and generates summary data that is delivered to users in a format that is easy for users to understand.

[0929] The server provides links associated with the summarized information, allowing the user to view more detailed information.

[0930] The server records and analyzes user actions (clicks on summary information, links, etc.), which allows for continuous improvement of the summary algorithm and delivery method.

[0931] Terminal

[0932] A terminal is a device (such as a smartphone, tablet, or PC) that a user uses to access the system. The user can use the terminal to receive the collected summary information.

[0933] The device records the user's actions and sends them to the server, which provides feedback to the server and uses it to improve the system.

[0934] User

[0935] A user is an individual or a corporation who wants to efficiently obtain important information from an SNS service. A user can use the service by registering their SNS account information in the system and providing the necessary information.

[0936] The user receives and checks the summary information delivered from the server using a terminal, and can also refer to detailed information by clicking on related links.

[0937] Users can customize their own notification settings, such as the frequency of notifications and how they want to receive them (email notifications, app notifications, etc.).

[0938] Specific examples

[0939] For example, suppose User A has registered accounts for social networking services (e.g., Twitter and Facebook) in the system. The server accesses the APIs of these social networking services to collect User A's timeline data. The server then cleanses the collected data and extracts important keywords and hashtags using natural language processing technology. The server then evaluates the importance of posts based on the extracted data and selects particularly important posts. The server then summarizes the selected posts and provides them to User A in the form of emails or app notifications. The summaries also include links related to the original posts, allowing User A to view the details. Furthermore, any actions User A takes on notifications are recorded by the device and sent to the server. This feedback data is used to improve the system's summarization algorithm and delivery method.

[0940] As described above, the system of the present invention can efficiently extract important information from SNS services and provide it to users, thereby solving the problem of information overload and improving user convenience.

[0941] The processing flow will be explained below.

[0942] Step 1:

[0943] The server accesses the API of the SNS service registered by the user and requests timeline data using the authentication token. Specifically, it sends an API request to obtain the user's timeline data (post content, number of likes, number of retweets, etc.).

[0944] Step 2:

[0945] The server receives the timeline data returned from the API and stores it in an internal database, along with metadata such as timestamps and user IDs.

[0946] Step 3:

[0947] The server cleanses the stored timeline data, removing duplicates and unnecessary data (such as advertising posts and spam) and checking the integrity of the data.

[0948] Step 4:

[0949] The server then uses natural language processing techniques to extract keywords, hashtags, and entities from the cleansed data, including techniques such as tokenization, part-of-speech tagging, and entity recognition.

[0950] Step 5:

[0951] The server evaluates the importance of each post based on the extracted keywords and entities, and uses a scoring algorithm to select the most important posts, taking into account engagement data (number of likes, retweets, comments, etc.).

[0952] Step 6:

[0953] The server then summarises the ranked posts, using machine learning models and rule-based techniques to provide a short summary of the posts' key points.

[0954] Step 7:

[0955] The server collects links related to the summarized information (such as the original post, additional details, etc.) and adds them to the summary data, allowing users to easily check for more information.

[0956] Step 8:

[0957] The server prepares the summary information based on the user's delivery preferences (e.g. email, app notification, dashboard view) and formats the summary data accordingly.

[0958] Step 9:

[0959] The server delivers the summary information to the user in a manner that depends on the user's settings, such as by emailing the summary information via a mail server or by sending a push notification to the app.

[0960] Step 10:

[0961] The device records user operations (such as displaying summary information and clicking links), and this operation data is saved as a log.

[0962] Step 11:

[0963] The server collects and analyzes user operation data sent from the device, and uses this data to improve the summarization algorithm and delivery method.

[0964] Step 12:

[0965] The server reflects the analysis results and optimizes the information gathering, summarizing, and distribution process from the next time onwards, thereby improving the quality of information provided to users.

[0966] Example 1

[0967] 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."

[0968] Modern social networking services provide a vast amount of information, but it is difficult to efficiently extract and provide important information to users. In particular, because they contain a lot of unnecessary data and spam, it takes a lot of time and effort for users to find the information they truly need. In addition, there is a lack of a mechanism for continuously improving the system based on user operation history and delivering information that is more appropriate for users.

[0969] 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.

[0970] In this invention, the server includes means for collecting timeline data from social networking services, means for cleansing the collected timeline data and removing unnecessary data, and means for extracting keywords, hashtags, and entities from posted content using natural language processing technology. This improves information accuracy and removes unnecessary data, allowing only important information to be efficiently extracted and provided to users. Furthermore, adding a means for users to customize delivery frequency and notification method enables information delivery tailored to individual user needs. Furthermore, by recording user operations and analyzing the operation data, the system can continuously improve the summarization algorithm and delivery method, thereby improving the overall convenience of the system.

[0971] "SNS service" is an abbreviation for social networking service, which is an online platform that enables users to communicate and share information with other users via the Internet.

[0972] "Timeline data" refers to a series of messages and updates posted on a social networking service that relate to a specific user.

[0973] "Cleansing" is the process of removing unnecessary data and noise from collected data and making it usable.

[0974] "Unnecessary data" refers to information collected by the system that is not suitable for analysis or use, such as spam and advertisements.

[0975] "Natural language processing technology" is a technology that allows computers to analyze and understand human language, and it analyzes the meaning of documents using language models and algorithms.

[0976] A "keyword" refers to a word that is considered particularly important in text data and is used as a target for search and analysis.

[0977] A "hashtag" is a tag used on social media services to indicate a specific topic or theme, and usually refers to a word or phrase preceded by the " " symbol.

[0978] An "entity" is a word or phrase that has a specific meaning in natural language processing, and refers to a proper noun or a specific concept.

[0979] "Assessing importance" is the process of identifying particularly valuable information from the collected data and determining its priority.

[0980] A "summary" is a conversion of the entire original information into a short, concise, and simplified representation that includes the main points.

[0981] A "link" is a reference, in the form of a URL, to a web page or other Internet resource that can be clicked to access related information.

[0982] "Recording operations" means saving the actions (clicks, taps, etc.) that a user takes on the system as data.

[0983] "Analysis" is the process of examining recorded data in detail to understand its meaning and patterns.

[0984] "Customization" refers to adjusting system settings and features to suit the user's preferences and needs.

[0985] The present invention provides a system that collects timeline data from SNS services and efficiently provides important information to users. The following embodiment is an example and is not intended to limit the present invention.

[0986] server

[0987] Collection Steps

[0988] The server is responsible for collecting timeline data from social networking services. Specifically, it accesses the API of each social networking service and retrieves the timeline data using an authentication token. For example, it collects data using the Twitter API or Facebook API. The collected data is stored in a database on the server.

[0989] Cleansing Step

[0990] The server cleanses the stored timeline data and removes unnecessary data, using spam, advertisement, and other filtering methods, which improves the accuracy of the data and makes subsequent processing more efficient.

[0991] Natural Language Processing Step

[0992] The server uses natural language processing techniques to extract keywords, hashtags, and entities from posts, such as text analysis using natural language processing libraries NLTK and spaCy, to identify important information from the collected data.

[0993] Importance evaluation step

[0994] The server evaluates the importance of posts based on the extracted data and selects important posts. This process also takes into account engagement data (number of likes, retweets, comments, etc.). For example, a post with 100 retweets and 500 likes will be evaluated as having high importance.

[0995] Summary generation step

[0996] The server automatically summarizes selected important posts and generates summary data to be delivered to users using algorithms such as the BERT summarizer. The summaries are provided in a format that is easy for users to understand.

[0997] Related link provision steps

[0998] The server provides links related to the summarized information, for example adding a "Learn more" link at the end of the summary, allowing the user to view more detailed information.

[0999] Operation record and analysis steps

[1000] The server records and analyzes user actions (clicks on summary information, links, etc.), which allows for continuous improvement of the summary algorithm and delivery method.

[1001] Terminal

[1002] Access and Display Steps

[1003] The terminal is a device (smartphone, tablet, PC, etc.) through which the user accesses the system and can receive the collected summary information. For example, a message saying "New summary information has arrived" will be displayed in the notification bar of the smartphone.

[1004] Operation Record Steps

[1005] The device records the user's actions and sends them to the server, which provides feedback to the server and uses it to improve the system.

[1006] User

[1007] Account registration steps

[1008] A user is an individual or corporation who wants to efficiently obtain important information from a social networking service. A user can use the service by registering their social networking account information in the system and providing the necessary information. For example, they can provide "Twitter API token: xxxxxxxx."

[1009] Information Receipt and Confirmation Steps

[1010] The user receives the summary information delivered from the server using the terminal and checks it. For example, the user can click a details link in the notified summary information to check the details.

[1011] Delivery settings customization steps

[1012] Users can customize their own notification settings, such as the frequency of notifications and how they want to receive them (email notifications, app notifications, etc.).

[1013] Specific examples

[1014] For example, suppose User A has registered accounts for social networking services (e.g., Twitter and Facebook) in the system. The server accesses the APIs of these social networking services to collect User A's timeline data. The server then cleanses the collected data and extracts important keywords and hashtags using natural language processing technology. The server then evaluates the importance of posts based on the extracted data and selects particularly important posts. The server then summarizes the selected posts and provides them to User A in the form of emails or app notifications. The summaries also include links related to the original posts, allowing User A to view the details. Furthermore, any actions User A takes on notifications are recorded by the device and sent to the server. This feedback data is used to improve the system's summarization algorithm and delivery method.

[1015] Example prompt:

[1016] "Generate a program that cleanses timeline data collected from Twitter and Facebook, extracts important information, and summarizes it. Include relevant links in the summary and record user actions to use as feedback data."

[1017] As described above, the system of the present invention can efficiently extract important information from SNS services and provide it to users, thereby solving the problem of information overload and improving user convenience.

[1018] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1019] Step 1:

[1020] Initial settings (server, user)

[1021] The server starts and reads the SNS API key and database connection information from the configuration file. This is done as part of the server initialization process.

[1022] Input: config file

[1023] Output: Initialization completion status

[1024] Users register their social media account information through a web interface or app. For example, by registering "Twitter API token: xxxxxxxx", social media data collection is ready.

[1025] Input: User-entered social media account information

[1026] Output: Registration completion status

[1027] Step 2:

[1028] Data collection (server)

[1029] The server accesses the API of the SNS service using the authentication token and acquires the user's timeline data, for example, the latest tweets using the Twitter API.

[1030] Input: User's authentication token

[1031] Output: Social media timeline data

[1032] The server stores the acquired timeline data in a database.

[1033] Input: Social media timeline data

[1034] Output: Data stored in the database

[1035] Step 3:

[1036] Data cleansing (server)

[1037] The server reads the timeline data stored in the database and removes unnecessary data (spam, advertisements, etc.) using keyword matching and regular expressions as filtering methods.

[1038] Input: Timeline data stored in a database

[1039] Output: Cleansed data

[1040] Specifically, the server filters out posts containing keywords such as "spam" and "advertising."

[1041] Step 4:

[1042] Natural language processing (server)

[1043] The server parses the cleansed timeline data and extracts keywords, hashtags, and entities from posts using natural language processing libraries (NLTK and spaCy).

[1044] Input: Cleansed data

[1045] Output: Extracted keywords, hashtags, and entities

[1046] For example, extract "AI" and "future" from a tweet saying "AI will change the future."

[1047] Step 5:

[1048] Importance rating (server)

[1049] The server evaluates the importance of each post based on the extracted keywords and entities, and also uses engagement data (number of likes, retweets, comments, etc.) to determine the score.

[1050] Input: Extracted keywords, hashtags, entities, and engagement data

[1051] Output: Importance score

[1052] Specifically, the server evaluates posts with 100 retweets and 500 likes as having high importance.

[1053] Step 6:

[1054] Summary generation (server)

[1055] The server automatically summarizes posts that are rated as highly important using a summary generation algorithm (BERT summarizer).

[1056] Input: Posts with high importance scores

[1057] Output: Summary data

[1058] Specifically, it converts "Original post: A new AI technology has been announced. Learn more here." into "Summary: A new AI technology has been announced."

[1059] Step 7:

[1060] Related link provided (server)

[1061] The server provides links related to the summarized posts.

[1062] Input: Summary data

[1063] Output: Summary data with associated links

[1064] Specifically, a "Learn more" link will be added to the end of the summary.

[1065] Step 8:

[1066] Information distribution (server, terminal)

[1067] The server delivers the summary information and related links to the user's device via email, push notification, or other methods depending on the user's delivery settings.

[1068] Input: Summary data with related links, user distribution settings

[1069] Output: Summary information delivered

[1070] The device displays the received summary information to the user. For example, a message saying "New summary information has arrived" is displayed in the notification bar of the smartphone.

[1071] Input: Delivered summary information

[1072] Output: Summary information displayed on the user's screen

[1073] Step 9:

[1074] Operation record and analysis (terminal, server)

[1075] When a user clicks on summary information or related links, the action is recorded in real time on the device.

[1076] Input: User actions

[1077] Output: Operation record data

[1078] The terminal transmits the recorded operation data to the server.

[1079] Input: Operation record data

[1080] Output: Operation data sent to the server

[1081] The server analyzes the received operation data and uses it to improve the summarization algorithm and delivery method.

[1082] Input: Operation data sent to the server

[1083] Output: Analysis results, system improvement information

[1084] Step 10:

[1085] Customizing delivery settings (user)

[1086] Users can adjust the frequency of delivery and notification method to suit their preferences.

[1087] Input: User settings information

[1088] Output: Updated distribution settings

[1089] For example, set the delivery frequency to once a day and the notification method to email notification.

[1090] The above are the specific processing steps of this system.

[1091] (Application example 1)

[1092] 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."

[1093] In modern society, the amount of information disseminated on the Internet is enormous, and there is a high risk of missing important security-related information. This poses a challenge, making it difficult for individuals and companies to quickly implement security measures. There is also a need for a method to efficiently collect information scattered across social networking sites and extract and provide only the necessary information. A method is needed to solve this information overload problem and provide important security information quickly and efficiently.

[1094] 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.

[1095] In this invention, the server includes means for collecting timeline data from SNS services, means for cleansing the collected timeline data and removing unnecessary data, means for extracting keywords, hashtags, and entities from post content using natural language processing technology, means for evaluating the importance of posts based on the extracted data, means for automatically summarizing the evaluated important posts, means for delivering the summarized information to users, means for providing links related to the delivered information, means for recording user operations, means for analyzing the recorded operation data and improving the summarization algorithm and delivery method, and means for collecting data from security-related SNS accounts and providing notifications in real time. This makes it possible to efficiently collect important security-related information and quickly notify users.

[1096] "SNS service" is an abbreviation for social networking service, an online platform that makes it easy for users to share information over the Internet.

[1097] "Timeline data" is a continuous record of information posted by users and related accounts on social media services, and is data displayed in chronological order.

[1098] "Cleansing" is the process of removing unnecessary information and noise from collected data and organizing it to include only the necessary information.

[1099] "Natural language processing technology" refers to all technologies that allow computers to interpret, analyze, and process human language.

[1100] "Keywords" are words or phrases that are particularly important in text or data, and are used for search and analysis.

[1101] A "hashtag" is a short phrase used on social media to express a specific keyword or topic, and begins with the symbol "."

[1102] An "entity" is information that indicates an independent existence, such as a specific name or title, and refers to a specific item such as a store name, a person's name, or a place name.

[1103] "Importance" is a measure of the value and urgency of information in collected data or posts based on specific criteria.

[1104] A "summary" is a short, concise expression of long information that extracts and provides the essential content.

[1105] A "link" is a string of characters or a button that allows you to connect to a specific location or information on the Internet, and is a means of accessing other web pages or resources.

[1106] "Operation data" is a record of a series of actions a user performs while using a system, including actions such as clicking, scrolling, and typing.

[1107] An "authentication token" is a temporary string of characters that proves a user has been authenticated to a system and is used to ensure secure access.

[1108] "Delivery settings" are settings that allow users to customize how and how often they receive information.

[1109] "Real-time" refers to the instant display and reflection of current situations and actions, and refers to a state in which information is provided without delay.

[1110] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes embodiments of the present invention, which are merely illustrative and do not limit the present invention.

[1111] In this system, to obtain timeline data from a social networking service, the server first accesses the social networking service's API and collects the data using an authentication token. For example, the server uses the authentication token to obtain security-related timeline data from the Twitter or Facebook API.

[1112] The collected data is stored in a database on the server, where it undergoes a data cleansing process. This cleansing process removes unnecessary data and noise, leaving only the important security data. Next, natural language processing techniques are used to extract keywords, hashtags, and entities from the posts. For example, natural language processing libraries (e.g., NLTK, SpaCy) are used to extract important keywords such as "phishing attack" and "virus" from the posts.

[1113] The server then evaluates the importance of posts based on the extracted data. Specifically, it uses engagement data (e.g., the number of likes, retweets, and comments) to quantify the importance of each post. It also automatically selects particularly important posts based on these values ​​and generates summaries. For example, it might determine that "this post has received many likes and retweets, so it is highly important."

[1114] After selecting important posts, the server summarizes them and delivers them to users. This can be delivered via email or push notifications. The summaries also include links related to the original posts, allowing users to easily view more detailed information. The server also records the actions users take on the information they receive as notifications (e.g., clicks and scrolls) and sends the data to the server. This action data is analyzed and used to improve the summarization algorithm and delivery method.

[1115] Additionally, the system specifically collects data from security-related social media accounts and provides real-time notifications to users, who can view these notifications using their smartphones, tablets, PCs, or other devices.

[1116] As a concrete example, consider the case where a security officer uses this system. The officer registers his / her social media account in the system and configures it to collect security-related information in real time. The following prompt sentence is input to the generative AI model:

[1117] Username: @cybersecuritynews

[1118] Post content: Sharing important information about the latest phishing attacks. Click here for detailed countermeasures. [Link]

[1119] Engagement data: Likes 50, Retweets 20, Comments 10

[1120] Based on this prompt, the generative AI model summarizes important information and notifies the security personnel. The security personnel can then click on a link to view more detailed information if necessary. This process allows security personnel to take prompt action without missing any important information.

[1121] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1122] Step 1:

[1123] The server accesses the API of the SNS service and collects timeline data using the authentication token. The input is the API endpoint of the SNS service and the authentication token, and the output is the collected timeline data. Specifically, the server sends an HTTP request to retrieve authenticated user data.

[1124] Step 2:

[1125] The server cleanses the collected timeline data. The input is the timeline data collected in step 1, and the output is the cleansed data. Specifically, a filtering process is performed to remove noise and unnecessary information from the timeline data stored in the database.

[1126] Step 3:

[1127] The server uses natural language processing technology to extract keywords, hashtags, and entities from the post content. The input is the cleansed data from step 2, and the output is the extracted keywords, hashtags, and entities. Specifically, it uses a natural language processing library to perform text analysis and extract important words and phrases.

[1128] Step 4:

[1129] The server evaluates the importance of posts based on the extracted data. The input is the keywords, hashtags, entities, and engagement data extracted in step 3, and the output is an importance score for each post. Specifically, the server applies a scoring algorithm based on the number of likes, retweets, comments, etc. to calculate the importance.

[1130] Step 5:

[1131] The server automatically summarizes the rated important posts. The input is the posts with high importance scores obtained in step 4, and the output is the summarized information. Specifically, it uses a generative AI model to convert the post content into a summary sentence.

[1132] Step 6:

[1133] The server delivers the summarized information to the user. The input is the summarized information from step 5, and the output is a notification message to the user. Specifically, the information is delivered via email notification or the app's push notification function.

[1134] Step 7:

[1135] The server provides links related to the distributed information. The input is the summarized information from step 5, and the output is links related to the summarized information. Specifically, the server extracts links from the original post and adds them to the summary.

[1136] Step 8:

[1137] The device records user operations. The input is the user's operations on the device (clicks, scrolls, etc.), and the output is a record of those operations. Specifically, it sets up an event listener and records each operation event in a log.

[1138] Step 9:

[1139] The server analyzes the recorded operation data and improves the summarization algorithm and delivery method. The input is the operation data recorded in step 8, and the output is an improved summarization algorithm and delivery method. Specifically, the operation data is statistically analyzed and the algorithm is adjusted through a feedback loop.

[1140] Step 10:

[1141] The server collects data from security-related social media accounts and provides notifications in real time. The input is data from security-related social media accounts, and the output is security information notifications delivered in real time. Specifically, it prioritizes data posted from specific security-related accounts and immediately notifies users.

[1142] 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.

[1143] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following embodiments are illustrative and do not limit the present invention.

[1144] This invention combines a system that collects timeline data from SNS services and efficiently provides important information to users with an emotion engine. This system consists of four main components: a server, a device, a user, and an emotion engine.

[1145] server

[1146] The server is responsible for collecting timeline data from SNS services. Specifically, it accesses the API of each SNS service and retrieves the timeline data using an authentication token. The collected data is stored in a database on the server.

[1147] The server cleanses the stored timeline data and removes unnecessary data, which improves data accuracy and makes subsequent processing more efficient.

[1148] The server uses natural language processing techniques to extract keywords, hashtags, and entities from posts, thereby identifying important information from the collected data.

[1149] The server evaluates the importance of posts based on the extracted data and selects the most important posts, taking into account engagement data (number of likes, retweets, comments, etc.).

[1150] The server uses an emotion engine to analyze the user's emotions from the collected timeline data and the user's past operation data, and reflects the emotion data in the importance evaluation of the summary information.

[1151] The server then summarises the selected important posts, using machine learning models and rule-based techniques to create short summaries of the posts' key points.

[1152] The server collects links related to the summarized information (such as the original post, additional details, etc.) and adds them to the summary data, allowing users to easily find more information.

[1153] The server prepares the summary information based on the user's delivery preferences (e.g. email, app notification, dashboard view) and formats the summary data accordingly.

[1154] The server delivers the summary information to the user in a manner that depends on the user's settings, for example, by emailing the summary information via a mail server or by sending a push notification to the app.

[1155] The server records and analyzes user actions (viewing summary information, clicking links, etc.) to continually improve the summary algorithm and delivery method.

[1156] Terminal

[1157] A terminal is a device (such as a smartphone, tablet, or PC) that a user uses to access the system. The user can use the terminal to receive the collected summary information.

[1158] The device records the user's actions and sends them to the server, which provides feedback to the server and uses it to improve the system.

[1159] User

[1160] A user is an individual or a corporation who wants to efficiently obtain important information from an SNS service. A user can use the service by registering their SNS account information in the system and providing the necessary information.

[1161] The user receives and checks the summary information delivered from the server using a terminal, and can also refer to detailed information by clicking on related links.

[1162] Users can customize their own notification settings, such as the frequency of notifications and how they want to receive them (email notifications, app notifications, etc.).

[1163] Emotion Engine

[1164] The emotion engine is a component for recognizing user emotions, which allows us to analyze user emotions from collected timeline data and user operation data.

[1165] The emotion engine has an algorithm that determines the user's emotions (happiness, surprise, sadness, etc.) from the content of posts and operation data. The emotion data is sent to the server and used to evaluate the importance of summary information and improve delivery methods.

[1166] The sentiment engine analyzes how users feel about specific keywords or entities and reflects this in selecting and summarizing important information.

[1167] Specific examples

[1168] For example, suppose User B has registered accounts for social networking services (e.g., Twitter and Instagram) in the system. The server accesses the APIs of these social networking services to collect User B's timeline data. It then cleanses the collected data and extracts important keywords and hashtags using natural language processing technology. The server uses an emotion engine to analyze emotions from User B's timeline data and past operation data, and reflects the emotion data in the importance rating of the summary information. For example, User B may rate posts containing keywords that frequently indicate the emotion "joy" as highly important. The server then summarizes the important posts and provides them to User B in the form of emails or app notifications. The summaries also include links related to the original posts, allowing User B to view the details. The emotion engine also collects User B's emotion data, which is used for future system optimization.

[1169] As described above, the system of the present invention can efficiently extract important information from SNS services and provide information optimized to suit the user's emotions, thereby solving the problem of information overload and improving user convenience.

[1170] The processing flow will be explained below.

[1171] Step 1:

[1172] The server accesses the API of the SNS service registered by the user and requests timeline data using the authentication token. Specifically, it sends an API request to obtain the user's timeline data (post content, number of likes, number of retweets, etc.).

[1173] Step 2:

[1174] The server receives the timeline data returned from the API and stores it in an internal database, along with metadata such as timestamps and user IDs.

[1175] Step 3:

[1176] The server cleanses the stored timeline data, removing duplicates and unnecessary data (such as advertising posts and spam) and checking the integrity of the data.

[1177] Step 4:

[1178] The server then uses natural language processing techniques to extract keywords, hashtags, and entities from the cleansed data, including techniques such as tokenization, part-of-speech tagging, and entity recognition.

[1179] Step 5:

[1180] The server evaluates the importance of each post based on the extracted keywords and entities, and uses a scoring algorithm to select the most important posts, taking into account engagement data (number of likes, retweets, comments, etc.).

[1181] Step 6:

[1182] The server analyzes the user's emotions using an emotion engine, which uses an algorithm to determine the user's emotions (e.g., joy, surprise, sadness) based on specific posts and past activity data.

[1183] Step 7:

[1184] The server adjusts the importance rating based on the analysis results of the emotion engine. Posts containing keywords that users frequently express the emotion of "joy" are given a higher rating.

[1185] Step 8:

[1186] The server then summarises the ranked posts, using machine learning models and rule-based techniques to provide a short summary of the posts' key points.

[1187] Step 9:

[1188] The server collects links related to the summarized information (such as the original post, additional details, etc.) and adds them to the summary data, allowing users to easily find more information.

[1189] Step 10:

[1190] The server prepares the summary information based on the user's delivery preferences (e.g. email, app notification, dashboard view) and formats the summary data accordingly.

[1191] Step 11:

[1192] The server delivers the summary information to the user in a manner that depends on the user's settings, such as by emailing the summary information via a mail server or by sending a push notification to the app.

[1193] Step 12:

[1194] The device records user operations (such as displaying summary information and clicking links), and this operation data is saved as a log.

[1195] Step 13:

[1196] The server collects and analyzes user operation data sent from the device, and uses this data to improve the summarization algorithm and delivery method.

[1197] Step 14:

[1198] The server will then apply the analysis results to optimize the information gathering, summarizing, and distribution processes from the next time onward, thereby improving the quality of the information provided to users.

[1199] Example 2

[1200] 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."

[1201] Currently, there is a huge amount of information available on social networking services, making it difficult for users to efficiently obtain important information. Furthermore, information provided does not take into account the user's emotional state, so information that meets the user's needs is often not provided. This increases the likelihood that users will miss useful information in this information-overloaded world. Furthermore, there is a need to accurately evaluate the importance and relevance of the information provided and deliver it to users in an appropriate format.

[1202] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1203] In this invention, the server includes means for collecting timeline data from an SNS service, means for cleansing the collected timeline data and removing unnecessary data, means for extracting keywords, hashtags, and entities from the posted content using natural language processing technology, means for evaluating the importance of posts based on the extracted data, means for analyzing user emotion data and reflecting the results in the importance evaluation, means for automatically summarizing the evaluated important posts, means for providing links related to the summarized information, means for formatting the summarized information based on the user's distribution settings, means for providing the distributed information to the user, means for recording user operations, and means for analyzing the recorded operation data and improving the summarization algorithm and distribution method. This allows users to efficiently obtain important information from vast amounts of information and further enables the provision of appropriate information according to the user's emotional state.

[1204] "SNS service" refers to a social networking service, an online platform for people to communicate over the Internet.

[1205] "Timeline data" refers to data that shows the content posted by users on social networking services and the order in which they were posted.

[1206] "Cleansing" is the process of removing unnecessary information from collected timeline data and extracting important information.

[1207] "Natural language processing technology" is a technology that allows computers to analyze and understand human language.

[1208] "Keywords" are important words or phrases in your post.

[1209] A "hashtag" is a tag preceded by the " " symbol that is added to a post to indicate a particular topic or theme.

[1210] An "entity" is a proper noun such as a person's name, place name, or organization name contained in the posted content.

[1211] "Importance evaluation" is the process of measuring the value and importance of a post based on certain criteria and assigning a score.

[1212] "Emotional data" refers to information that indicates the emotional state of a user.

[1213] "Summarizing" refers to the process of briefly summarizing the main points of the posted content.

[1214] "Link" means a URL or hyperlink that provides a connection to related sources of information or further information.

[1215] "Delivery Preferences" refers to options that allow users to set how they wish to receive information.

[1216] "Operational Data" means records of actions and events performed by users on the system.

[1217] A "summarization algorithm" is a formula or method used to efficiently summarize a post's content.

[1218] "Delivery method" refers to the means or process used to provide information to users.

[1219] The present invention is configured by combining a system that collects timeline data from SNS services and efficiently provides important information to users with an emotion engine.

[1220] server

[1221] The server is responsible for collecting timeline data from SNS services. Specifically, the server accesses the API of each SNS service (e.g., social networking platform) and obtains timeline data using an authentication token. This data is then stored in the server's database.

[1222] The collected data goes through a cleansing process to remove unnecessary data. This process improves the accuracy of the data and makes subsequent processing more efficient. The server uses natural language processing techniques (e.g., natural language processing libraries) to extract keywords, hashtags, and entities from the posts, thereby identifying important information.

[1223] Next, the server evaluates the importance of posts based on the extracted data. The server considers engagement data (e.g., number of likes, retweets, and comments) and reflects this in the importance evaluation. Furthermore, it uses an emotion engine to analyze user emotion data and reflects this in the importance evaluation of the summary information.

[1224] The server uses machine learning models (e.g., generative AI models) to automatically summarize important posts that have been rated, and also includes relevant links to help users find more information.

[1225] The server formats the summary information based on the user's delivery settings and prepares it for delivery. For example, if the user selects email notification, the server formats the summary information in HTML format and prepares it for email transmission. Finally, the server uses a delivery method such as sending the summary information via email via a mail server.

[1226] The server also records and analyzes user actions (viewing summary information, clicking links), and the resulting data is used to improve the summary algorithm and delivery method.

[1227] Terminal

[1228] The terminal is a device (e.g., smartphone, tablet, or PC) that users use to access the system. The user can use the terminal to receive and check the summary information delivered to them. The terminal also records the user's actions and sends them to the server. This data is passed to the server as feedback and used to improve the system.

[1229] User

[1230] A user is an individual or a corporation who wants to efficiently obtain important information from an SNS service. A user can use this service by registering their SNS account information in the system and providing the necessary information.

[1231] Users can use their devices to check summary information delivered from the server and click on related links to view detailed information. Users can also customize their delivery settings to receive information in a way that suits their needs (e.g., email notifications, app notifications).

[1232] Specific examples

[1233] For example, suppose User B has registered an account for a social networking service (e.g., a social networking platform) in the system. The server accesses the APIs of these social networking services to collect User B's timeline data. The server then cleanses the collected data and uses natural language processing technology to extract important keywords and hashtags.

[1234] The server uses an emotion engine to analyze emotions from User B's timeline data and past operation data, and reflects that emotion data in the importance rating of the summary information. For example, User B rates posts containing keywords that frequently indicate the emotion of "joy" with a high importance rating. Next, the server summarizes the important posts using a generative AI model and provides them to User B in the form of an email or app notification. The summary also includes a link related to the original post, allowing User B to check the details.

[1235] The emotion engine also collects emotion data from User B, which will be used to optimize the system in the future. Specific examples of prompt sentences are as follows:

[1236] "Extract important keywords from User B's social networking platform timeline data, analyze the user's sentiment using a sentiment engine, and summarize the important information. Include relevant links in the summary and provide it in the form of an email notification."

[1237] In this way, the present invention is a system that efficiently extracts important information from SNS services and provides information optimized to the user's emotions, thereby solving the problem of information overload and improving user convenience.

[1238] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1239] Step 1:

[1240] The server calls the API of the SNS service to obtain timeline data. Specifically, it sends an API request using the API key and authentication token of each SNS service to obtain timeline data in JSON format. In this process, it uses the authentication token and API endpoint of each SNS service as input and saves the obtained timeline data as output in a database.

[1241] Step 2:

[1242] The server cleanses the acquired timeline data. Specifically, it removes unnecessary fields from the JSON data and extracts only important fields (e.g., post content, timestamp, and user information). It removes noise and duplicate data to generate a clean dataset. In this process, it uses the acquired timeline data as input and generates cleansed data as output.

[1243] Step 3:

[1244] The server uses natural language processing techniques to extract keywords, hashtags, and entities from the cleansed data. Specifically, it uses natural language processing libraries (e.g., spaCy, NLTK) to parse the text of posts and extract important words and phrases. This process uses the cleansed data as input and produces a list of extracted keywords, hashtags, and entities as output.

[1245] Step 4:

[1246] The server evaluates the importance of posts based on the extracted data. Specifically, it calculates a score taking into account engagement data (e.g., number of likes, retweets, and comments) and selects posts with high importance. In this process, it uses the extracted data and engagement data as input and generates an importance evaluation result as output.

[1247] Step 5:

[1248] The server uses an emotion engine to analyze the user's emotional data and reflects the results in the importance rating. Specifically, the emotion engine analyzes the user's emotional state from the post content and operation data and modifies the importance rating. In this process, the post content and operation data are used as input, and a modified importance rating result is generated as output.

[1249] Step 6:

[1250] The server automatically summarizes posts based on the importance assessment results. Specifically, it uses a generative AI model (e.g., GPT-3) to generate a summary by briefly summarizing the main points of each post. In this process, it uses the importance assessment results as input and generates summarized text as output.

[1251] Step 7:

[1252] The server collects and provides links related to the summarized information, specifically, links to the original post and additional details in the summary data. This process uses the summary text as input and generates the linked summary data as output.

[1253] Step 8:

[1254] The server formats the summary information based on the user's delivery settings. Specifically, it formats the summary information into a format such as email or app notification according to the delivery method selected by the user. In this process, the server uses the linked summary data and delivery setting information as input and generates formatted delivery data as output.

[1255] Step 9:

[1256] The server provides the formatted delivery data to the user, specifically by sending summary information to the user via a mail server or push notification system, using the formatted delivery data as input and generating the notification sent to the user as output.

[1257] Step 10:

[1258] The server records user actions and analyzes the recorded data. Specifically, it records user actions such as displaying summary information and clicking links, and analyzes the data to improve the system. In this process, it uses user action data as input and generates analysis results as output.

[1259] (Application example 2)

[1260] 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."

[1261] In recent years, with the spread of social networking services, users are surrounded by a vast amount of information. This makes it difficult for them to find the information they truly need. Furthermore, there is a need for systems that can provide information that responds to users' emotions, rather than simply collecting and summarizing information. Furthermore, there is a need for systems that can improve the shopping experience in virtual stores by analyzing users' emotions and suggesting products based on those emotions.

[1262] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1263] In this invention, the server includes means for collecting timeline data from an SNS service, means for cleansing the collected timeline data and removing unnecessary data, means for extracting keywords, hashtags, and entities from the posted content using natural language processing technology, means for evaluating the importance of posts based on the extracted data, means for automatically summarizing the evaluated important posts, means for delivering the summarized information to users, means for providing links related to the delivered information, means for recording user operations, means for analyzing the recorded operation data and improving the summarization algorithm and delivery method, means for analyzing emotions from the recorded operation data, and means for suggesting products based on the analyzed emotion data. This makes it possible to efficiently extract important information from an SNS service and provide information and product suggestions optimized to match the user's emotions.

[1264] "SNS service" is an abbreviation for social networking service, a platform that allows users to communicate with other users online.

[1265] "Timeline data" is data that displays the content posted by users on social media services and the actions (likes, retweets, etc.) taken by other users in chronological order.

[1266] "Cleansing" is a process of removing unnecessary information and noise from collected data, and is a preprocessing step to improve the quality of the data.

[1267] "Automatic summarization" refers to the process of shortening long posts and extracting only the main points in a concise manner.

[1268] "Natural language processing technology" is a technology that enables computers to understand, interpret, and process human language, specifically extracting keywords and entities, and analyzing sentiment.

[1269] "Emotional data" refers to data related to emotions such as joy, sadness, and surprise that are derived from users' posts and actions.

[1270] "Suggesting products" means selecting and presenting products that are highly relevant to the user based on analyzed emotional data and the user's past operation data.

[1271] A "summarization algorithm" is a method or formula for summarizing the content of a post in a concise manner, and includes machine learning models and rule-based methods.

[1272] "Delivery method" refers to the means by which summary information and product suggestions are provided to users, including email, app notifications, dashboard displays, etc.

[1273] The following describes in detail an embodiment of the present invention. The present invention is a system that collects timeline data from social networking services and efficiently provides important information to users. This system also incorporates a function to analyze users' emotions and make product recommendations based on those emotions.

[1274] The server first collects timeline data through the API of the social media service. At this time, it authenticates the user using an authentication token. The collected data undergoes a cleansing process to remove unnecessary information. Next, it uses natural language processing technology to extract keywords, hashtags, and entities from the post content.

[1275] Based on the extracted data, the server rates the posts' importance, taking into account engagement data (number of likes, retweets, comments, etc.). The ranked important posts are automatically summarized to generate a summary, which includes links to the original post and additional details.

[1276] The summarized information is formatted appropriately based on the user's delivery settings and delivered to the user via email, app notifications, etc. User actions (viewing the summary information, clicking links, etc.) are recorded and sent to a server. Analysis of this recorded data allows for improvements to the summarization algorithm and delivery method.

[1277] Furthermore, an emotion engine is used to analyze emotions from user posts and operation data. Emotional data extracted from the recorded operation data is reflected in the evaluation of the importance of information and product suggestions. Based on the emotional data, the most suitable products are selected from a product catalog and suggested to the user.

[1278] In this embodiment, a smartphone, smart glasses, or a head-mounted display can be used as hardware, and the Requests library, a natural language processing library (e.g., NLTK or spaCy), and a sentiment analysis library (e.g., VADER) are used as software.

[1279] For example, if a user posts on social media that they want a new smartphone, the server collects the post, cleansing it, and extracts keywords. The emotion engine then determines that the post is a "joy" message, generates summary information, and suggests suitable smartphones and accessories. This information is then sent via email or notification based on the user's settings.

[1280] Example prompt sentence:

[1281] Build a system program that analyzes emotions such as joy and sadness based on the content users post on social media and suggests the best products for them.

[1282] As described above, this system can improve user convenience by efficiently extracting important information from SNS services and providing information and product suggestions that match the user's emotions.

[1283] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1284] Step 1:

[1285] The server accesses the API of the SNS service and collects timeline data using the authentication token.

[1286] Input: SNS service API URL, authentication token

[1287] Output: A list of timeline data

[1288] Specific operation: The server sends an HTTP request to the API of each SNS service and retrieves the user's timeline data using the authentication token. The retrieved data is saved in list format.

[1289] Step 2:

[1290] The server cleanses the collected timeline data and removes unnecessary data.

[1291] Input: List of timeline data

[1292] Output: Cleansed timeline data

[1293] How it works: The server analyzes the collected timeline data and removes unnecessary information such as spam, advertisements, and duplicate data. The cleansed data is then passed on to the next processing step.

[1294] Step 3:

[1295] The server uses natural language processing technology to extract keywords, hashtags, and entities from the post content.

[1296] Input: Cleansed timeline data

[1297] Output: A list of extracted keywords, hashtags, and entities

[1298] How it works: The server uses a natural language processing library (such as NLTK or spaCy) to analyze the text data and extract important keywords and entities. The extracted information is saved in a list format.

[1299] Step 4:

[1300] The server evaluates the importance of the post based on the extracted data.

[1301] Input: List of keywords, hashtags, entities

[1302] Output: A list of posts with their importance ratings

[1303] Specific operation: The server calculates an importance score based on the extracted keywords and engagement data (number of likes, retweets, and comments) and evaluates the importance of each post. Posts with high importance are passed on to the next step.

[1304] Step 5:

[1305] The server automatically summarizes the most important posts that have been rated.

[1306] Input: A list of posts with importance ratings

[1307] Output: List of summary information

[1308] How it works: The server uses machine learning models and rule-based methods to extract and shorten the main points that summarize the post content. The generated summary information is saved in a list format.

[1309] Step 6:

[1310] The server collects links related to the summarized information and appends them to the summary data.

[1311] Input: List of summary information

[1312] Output: A list of summary data with link information added

[1313] What happens: The server collects links to the original post and additional details and adds them to the summary information. The linked data is passed on to the next step.

[1314] Step 7:

[1315] The server prepares the summary information based on the user's delivery preferences.

[1316] Input: User's delivery settings, list of summary data with link information

[1317] Output: Summary data formatted for delivery

[1318] Specific behavior: The server takes into account the user's delivery preferences (email, app notifications, dashboard display) and formats the summary data appropriately.

[1319] Step 8:

[1320] The server delivers the summary information to the user in a manner that depends on the settings.

[1321] Input: Summary data formatted for delivery

[1322] Output: Notifications and emails delivered to users

[1323] Specific operation: The server uses the mail server or push notification to send summary information to the user, who then receives the information on their device.

[1324] Step 9:

[1325] The device records user actions (displaying summary information, clicking links, etc.) and sends them to the server.

[1326] Input: User operation data

[1327] Output: Operation data sent to the server

[1328] Specific operation: When a user views summary information on their device and clicks on a link, the operation data is recorded and sent to the server.

[1329] Step 10:

[1330] The server analyzes the recorded operation data and improves the summarization algorithm and delivery method.

[1331] Input: User operation data

[1332] Output: Improved summarization algorithms and delivery methods

[1333] Specific operation: The server analyzes user operation data, evaluates the performance of the summarization algorithm and delivery method, and makes necessary adjustments and improvements to reflect them in future deliveries.

[1334] Step 11:

[1335] The server analyzes emotions from the recorded operation data.

[1336] Input: User operation data

[1337] Output: Emotion data

[1338] Specific operation: The server uses a sentiment analysis library (e.g., VADER) to calculate the user's sentiment score from the operation data. The calculated sentiment data is reflected in the information importance rating and product recommendations.

[1339] Step 12:

[1340] The server suggests products based on the analyzed emotion data.

[1341] Input: Emotion data, product catalog

[1342] Output: A list of suggested products for the user

[1343] Specific operation: The server selects the most suitable products from the product catalog based on the emotion data and proposes them to the user. The selected product list is then provided to the user along with summary information.

[1344] 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.

[1345] 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.

[1346] 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.

[1347] [Fourth embodiment]

[1348] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1349] 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.

[1350] 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).

[1351] 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.

[1352] 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.

[1353] 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).

[1354] 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.

[1355] 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.

[1356] 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.

[1357] 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.

[1358] 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.

[1359] 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.

[1360] 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."

[1361] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes embodiments of the present invention, which are merely illustrative and do not limit the present invention.

[1362] This invention is a system that collects timeline data from SNS services and efficiently provides important information to users. This system consists of three main components: a server, a terminal, and a user.

[1363] server

[1364] The server is responsible for collecting timeline data from SNS services. Specifically, it accesses the API of each SNS service and retrieves the timeline data using an authentication token. The collected data is stored in a database on the server.

[1365] The server cleanses the stored timeline data and removes unnecessary data, which improves data accuracy and makes subsequent processing more efficient.

[1366] The server uses natural language processing techniques to extract keywords, hashtags, and entities from posts, thereby identifying important information from the collected data.

[1367] The server evaluates the importance of posts based on the extracted data and selects the most important posts, taking into account engagement data (number of likes, retweets, comments, etc.).

[1368] The server automatically summarizes the selected important posts and generates summary data that is delivered to users in a format that is easy for users to understand.

[1369] The server provides links associated with the summarized information, allowing the user to view more detailed information.

[1370] The server records and analyzes user actions (clicks on summary information, links, etc.), which allows for continuous improvement of the summary algorithm and delivery method.

[1371] Terminal

[1372] A terminal is a device (such as a smartphone, tablet, or PC) that a user uses to access the system. The user can use the terminal to receive the collected summary information.

[1373] The device records the user's actions and sends them to the server, which provides feedback to the server and uses it to improve the system.

[1374] User

[1375] A user is an individual or a corporation who wants to efficiently obtain important information from an SNS service. A user can use the service by registering their SNS account information in the system and providing the necessary information.

[1376] The user receives and checks the summary information delivered from the server using a terminal, and can also refer to detailed information by clicking on related links.

[1377] Users can customize their own notification settings, such as the frequency of notifications and how they want to receive them (email notifications, app notifications, etc.).

[1378] Specific examples

[1379] For example, suppose User A has registered accounts for social networking services (e.g., Twitter and Facebook) in the system. The server accesses the APIs of these social networking services to collect User A's timeline data. The server then cleanses the collected data and extracts important keywords and hashtags using natural language processing technology. The server then evaluates the importance of posts based on the extracted data and selects particularly important posts. The server then summarizes the selected posts and provides them to User A in the form of emails or app notifications. The summaries also include links related to the original posts, allowing User A to view the details. Furthermore, any actions User A takes on notifications are recorded by the device and sent to the server. This feedback data is used to improve the system's summarization algorithm and delivery method.

[1380] As described above, the system of the present invention can efficiently extract important information from SNS services and provide it to users, thereby solving the problem of information overload and improving user convenience.

[1381] The processing flow will be explained below.

[1382] Step 1:

[1383] The server accesses the API of the SNS service registered by the user and requests timeline data using the authentication token. Specifically, it sends an API request to obtain the user's timeline data (post content, number of likes, number of retweets, etc.).

[1384] Step 2:

[1385] The server receives the timeline data returned from the API and stores it in an internal database, along with metadata such as timestamps and user IDs.

[1386] Step 3:

[1387] The server cleanses the stored timeline data, removing duplicates and unnecessary data (such as advertising posts and spam) and checking the integrity of the data.

[1388] Step 4:

[1389] The server then uses natural language processing techniques to extract keywords, hashtags, and entities from the cleansed data, including techniques such as tokenization, part-of-speech tagging, and entity recognition.

[1390] Step 5:

[1391] The server evaluates the importance of each post based on the extracted keywords and entities, and uses a scoring algorithm to select the most important posts, taking into account engagement data (number of likes, retweets, comments, etc.).

[1392] Step 6:

[1393] The server then summarises the ranked posts, using machine learning models and rule-based techniques to provide a short summary of the posts' key points.

[1394] Step 7:

[1395] The server collects links related to the summarized information (such as the original post, additional details, etc.) and adds them to the summary data, allowing users to easily check for more information.

[1396] Step 8:

[1397] The server prepares the summary information based on the user's delivery preferences (e.g. email, app notification, dashboard view) and formats the summary data accordingly.

[1398] Step 9:

[1399] The server delivers the summary information to the user in a manner that depends on the user's settings, such as by emailing the summary information via a mail server or by sending a push notification to the app.

[1400] Step 10:

[1401] The device records user operations (such as displaying summary information and clicking links), and this operation data is saved as a log.

[1402] Step 11:

[1403] The server collects and analyzes user operation data sent from the device, and uses this data to improve the summarization algorithm and delivery method.

[1404] Step 12:

[1405] The server reflects the analysis results and optimizes the information gathering, summarizing, and distribution process from the next time onwards, thereby improving the quality of information provided to users.

[1406] Example 1

[1407] 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."

[1408] Modern social networking services provide a vast amount of information, but it is difficult to efficiently extract and provide important information to users. In particular, because they contain a lot of unnecessary data and spam, it takes a lot of time and effort for users to find the information they truly need. In addition, there is a lack of a mechanism for continuously improving the system based on user operation history and delivering information that is more appropriate for users.

[1409] 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.

[1410] In this invention, the server includes means for collecting timeline data from social networking services, means for cleansing the collected timeline data and removing unnecessary data, and means for extracting keywords, hashtags, and entities from posted content using natural language processing technology. This improves information accuracy and removes unnecessary data, allowing only important information to be efficiently extracted and provided to users. Furthermore, adding a means for users to customize delivery frequency and notification method enables information delivery tailored to individual user needs. Furthermore, by recording user operations and analyzing the operation data, the system can continuously improve the summarization algorithm and delivery method, thereby improving the overall convenience of the system.

[1411] "SNS service" is an abbreviation for social networking service, which is an online platform that enables users to communicate and share information with other users via the Internet.

[1412] "Timeline data" refers to a series of messages and updates posted on a social networking service that relate to a specific user.

[1413] "Cleansing" is the process of removing unnecessary data and noise from collected data and making it usable.

[1414] "Unnecessary data" refers to information collected by the system that is not suitable for analysis or use, such as spam and advertisements.

[1415] "Natural language processing technology" is a technology that allows computers to analyze and understand human language, and it analyzes the meaning of documents using language models and algorithms.

[1416] A "keyword" refers to a word that is considered particularly important in text data and is used as a target for search and analysis.

[1417] A "hashtag" is a tag used on social media services to indicate a specific topic or theme, and usually refers to a word or phrase preceded by the " " symbol.

[1418] An "entity" is a word or phrase that has a specific meaning in natural language processing, and refers to a proper noun or a specific concept.

[1419] "Assessing importance" is the process of identifying particularly valuable information from the collected data and determining its priority.

[1420] A "summary" is a conversion of the entire original information into a short, concise, and simplified representation that includes the main points.

[1421] A "link" is a reference, in the form of a URL, to a web page or other Internet resource that can be clicked to access related information.

[1422] "Recording operations" means saving the actions (clicks, taps, etc.) that a user takes on the system as data.

[1423] "Analysis" is the process of examining recorded data in detail to understand its meaning and patterns.

[1424] "Customization" refers to adjusting system settings and features to suit the user's preferences and needs.

[1425] The present invention provides a system that collects timeline data from SNS services and efficiently provides important information to users. The following embodiment is an example and is not intended to limit the present invention.

[1426] server

[1427] Collection Steps

[1428] The server is responsible for collecting timeline data from social networking services. Specifically, it accesses the API of each social networking service and retrieves the timeline data using an authentication token. For example, it collects data using the Twitter API or Facebook API. The collected data is stored in a database on the server.

[1429] Cleansing Step

[1430] The server cleanses the stored timeline data and removes unnecessary data, using spam, advertisement, and other filtering methods, which improves the accuracy of the data and makes subsequent processing more efficient.

[1431] Natural Language Processing Step

[1432] The server uses natural language processing techniques to extract keywords, hashtags, and entities from posts, such as text analysis using natural language processing libraries NLTK and spaCy, to identify important information from the collected data.

[1433] Importance evaluation step

[1434] The server evaluates the importance of posts based on the extracted data and selects important posts. This process also takes into account engagement data (number of likes, retweets, comments, etc.). For example, a post with 100 retweets and 500 likes will be evaluated as having high importance.

[1435] Summary generation step

[1436] The server automatically summarizes selected important posts and generates summary data to be delivered to users using algorithms such as the BERT summarizer. The summaries are provided in a format that is easy for users to understand.

[1437] Related link provision steps

[1438] The server provides links related to the summarized information, for example adding a "Learn more" link at the end of the summary, allowing the user to view more detailed information.

[1439] Operation record and analysis steps

[1440] The server records and analyzes user actions (clicks on summary information, links, etc.), which allows for continuous improvement of the summary algorithm and delivery method.

[1441] Terminal

[1442] Access and Display Steps

[1443] The terminal is a device (smartphone, tablet, PC, etc.) through which the user accesses the system and can receive the collected summary information. For example, a message saying "New summary information has arrived" will be displayed in the notification bar of the smartphone.

[1444] Operation Record Steps

[1445] The device records the user's actions and sends them to the server, which provides feedback to the server and uses it to improve the system.

[1446] User

[1447] Account registration steps

[1448] A user is an individual or corporation who wants to efficiently obtain important information from a social networking service. A user can use the service by registering their social networking account information in the system and providing the necessary information. For example, they can provide "Twitter API token: xxxxxxxx."

[1449] Information Receipt and Confirmation Steps

[1450] The user receives the summary information delivered from the server using the terminal and checks it. For example, the user can click a details link in the notified summary information to check the details.

[1451] Delivery settings customization steps

[1452] Users can customize their own notification settings, such as the frequency of notifications and how they want to receive them (email notifications, app notifications, etc.).

[1453] Specific examples

[1454] For example, suppose User A has registered accounts for social networking services (e.g., Twitter and Facebook) in the system. The server accesses the APIs of these social networking services to collect User A's timeline data. The server then cleanses the collected data and extracts important keywords and hashtags using natural language processing technology. The server then evaluates the importance of posts based on the extracted data and selects particularly important posts. The server then summarizes the selected posts and provides them to User A in the form of emails or app notifications. The summaries also include links related to the original posts, allowing User A to view the details. Furthermore, any actions User A takes on notifications are recorded by the device and sent to the server. This feedback data is used to improve the system's summarization algorithm and delivery method.

[1455] Example prompt:

[1456] "Generate a program that cleanses timeline data collected from Twitter and Facebook, extracts important information, and summarizes it. Include relevant links in the summary and record user actions to use as feedback data."

[1457] As described above, the system of the present invention can efficiently extract important information from SNS services and provide it to users, thereby solving the problem of information overload and improving user convenience.

[1458] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1459] Step 1:

[1460] Initial settings (server, user)

[1461] The server starts and reads the SNS API key and database connection information from the configuration file. This is done as part of the server initialization process.

[1462] Input: config file

[1463] Output: Initialization completion status

[1464] Users register their social media account information through a web interface or app. For example, by registering "Twitter API token: xxxxxxxx", social media data collection is ready.

[1465] Input: User-entered social media account information

[1466] Output: Registration completion status

[1467] Step 2:

[1468] Data collection (server)

[1469] The server accesses the API of the SNS service using the authentication token and acquires the user's timeline data, for example, the latest tweets using the Twitter API.

[1470] Input: User's authentication token

[1471] Output: Social media timeline data

[1472] The server stores the acquired timeline data in a database.

[1473] Input: Social media timeline data

[1474] Output: Data stored in the database

[1475] Step 3:

[1476] Data cleansing (server)

[1477] The server reads the timeline data stored in the database and removes unnecessary data (spam, advertisements, etc.) using keyword matching and regular expressions as filtering methods.

[1478] Input: Timeline data stored in a database

[1479] Output: Cleansed data

[1480] Specifically, the server filters out posts containing keywords such as "spam" and "advertising."

[1481] Step 4:

[1482] Natural language processing (server)

[1483] The server parses the cleansed timeline data and extracts keywords, hashtags, and entities from posts using natural language processing libraries (NLTK and spaCy).

[1484] Input: Cleansed data

[1485] Output: Extracted keywords, hashtags, and entities

[1486] For example, extract "AI" and "future" from a tweet saying "AI will change the future."

[1487] Step 5:

[1488] Importance rating (server)

[1489] The server evaluates the importance of each post based on the extracted keywords and entities, and also uses engagement data (number of likes, retweets, comments, etc.) to determine the score.

[1490] Input: Extracted keywords, hashtags, entities, and engagement data

[1491] Output: Importance score

[1492] Specifically, the server evaluates posts with 100 retweets and 500 likes as having high importance.

[1493] Step 6:

[1494] Summary generation (server)

[1495] The server automatically summarizes posts that are rated as highly important using a summary generation algorithm (BERT summarizer).

[1496] Input: Posts with high importance scores

[1497] Output: Summary data

[1498] Specifically, it converts "Original post: A new AI technology has been announced. Learn more here." into "Summary: A new AI technology has been announced."

[1499] Step 7:

[1500] Related link provided (server)

[1501] The server provides links related to the summarized posts.

[1502] Input: Summary data

[1503] Output: Summary data with associated links

[1504] Specifically, a "Learn more" link will be added to the end of the summary.

[1505] Step 8:

[1506] Information distribution (server, terminal)

[1507] The server delivers the summary information and related links to the user's device via email, push notification, or other methods depending on the user's delivery settings.

[1508] Input: Summary data with related links, user distribution settings

[1509] Output: Summary information delivered

[1510] The device displays the received summary information to the user. For example, a message saying "New summary information has arrived" is displayed in the notification bar of the smartphone.

[1511] Input: Delivered summary information

[1512] Output: Summary information displayed on the user's screen

[1513] Step 9:

[1514] Operation record and analysis (terminal, server)

[1515] When a user clicks on summary information or related links, the action is recorded in real time on the device.

[1516] Input: User actions

[1517] Output: Operation record data

[1518] The terminal transmits the recorded operation data to the server.

[1519] Input: Operation record data

[1520] Output: Operation data sent to the server

[1521] The server analyzes the received operation data and uses it to improve the summarization algorithm and delivery method.

[1522] Input: Operation data sent to the server

[1523] Output: Analysis results, system improvement information

[1524] Step 10:

[1525] Customizing delivery settings (user)

[1526] Users can adjust the frequency of delivery and notification method to suit their preferences.

[1527] Input: User settings information

[1528] Output: Updated distribution settings

[1529] For example, set the delivery frequency to once a day and the notification method to email notification.

[1530] The above are the specific processing steps of this system.

[1531] (Application example 1)

[1532] 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."

[1533] In modern society, the amount of information disseminated on the Internet is enormous, and there is a high risk of missing important security-related information. This poses a challenge, making it difficult for individuals and companies to quickly implement security measures. There is also a need for a method to efficiently collect information scattered across social networking sites and extract and provide only the necessary information. A method is needed to solve this information overload problem and provide important security information quickly and efficiently.

[1534] 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.

[1535] In this invention, the server includes means for collecting timeline data from SNS services, means for cleansing the collected timeline data and removing unnecessary data, means for extracting keywords, hashtags, and entities from post content using natural language processing technology, means for evaluating the importance of posts based on the extracted data, means for automatically summarizing the evaluated important posts, means for delivering the summarized information to users, means for providing links related to the delivered information, means for recording user operations, means for analyzing the recorded operation data and improving the summarization algorithm and delivery method, and means for collecting data from security-related SNS accounts and providing notifications in real time. This makes it possible to efficiently collect important security-related information and quickly notify users.

[1536] "SNS service" is an abbreviation for social networking service, an online platform that makes it easy for users to share information over the Internet.

[1537] "Timeline data" is a continuous record of information posted by users and related accounts on social media services, and is data displayed in chronological order.

[1538] "Cleansing" is the process of removing unnecessary information and noise from collected data and organizing it to include only the necessary information.

[1539] "Natural language processing technology" refers to all technologies that allow computers to interpret, analyze, and process human language.

[1540] "Keywords" are words or phrases that are particularly important in text or data, and are used for search and analysis.

[1541] A "hashtag" is a short phrase used on social media to express a specific keyword or topic, and begins with the symbol "."

[1542] An "entity" is information that indicates an independent existence, such as a specific name or title, and refers to a specific item such as a store name, a person's name, or a place name.

[1543] "Importance" is a measure of the value and urgency of information in collected data or posts based on specific criteria.

[1544] A "summary" is a short, concise expression of long information that extracts and provides the essential content.

[1545] A "link" is a string of characters or a button that allows you to connect to a specific location or information on the Internet, and is a means of accessing other web pages or resources.

[1546] "Operation data" is a record of a series of actions a user performs while using a system, including actions such as clicking, scrolling, and typing.

[1547] An "authentication token" is a temporary string of characters that proves a user has been authenticated to a system and is used to ensure secure access.

[1548] "Delivery settings" are settings that allow users to customize how and how often they receive information.

[1549] "Real-time" refers to the instant display and reflection of current situations and actions, and refers to a state in which information is provided without delay.

[1550] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes embodiments of the present invention, which are merely illustrative and do not limit the present invention.

[1551] In this system, to obtain timeline data from a social networking service, the server first accesses the social networking service's API and collects the data using an authentication token. For example, the server uses the authentication token to obtain security-related timeline data from the Twitter or Facebook API.

[1552] The collected data is stored in a database on the server, where it undergoes a data cleansing process. This cleansing process removes unnecessary data and noise, leaving only the important security data. Next, natural language processing techniques are used to extract keywords, hashtags, and entities from the posts. For example, natural language processing libraries (e.g., NLTK, SpaCy) are used to extract important keywords such as "phishing attack" and "virus" from the posts.

[1553] The server then evaluates the importance of posts based on the extracted data. Specifically, it uses engagement data (e.g., the number of likes, retweets, and comments) to quantify the importance of each post. It also automatically selects particularly important posts based on these values ​​and generates summaries. For example, it might determine that "this post has received many likes and retweets, so it is highly important."

[1554] After selecting important posts, the server summarizes them and delivers them to users. This can be delivered via email or push notifications. The summaries also include links related to the original posts, allowing users to easily view more detailed information. The server also records the actions users take on the information they receive as notifications (e.g., clicks and scrolls) and sends the data to the server. This action data is analyzed and used to improve the summarization algorithm and delivery method.

[1555] Additionally, the system specifically collects data from security-related social media accounts and provides real-time notifications to users, who can view these notifications using their smartphones, tablets, PCs, or other devices.

[1556] As a concrete example, consider the case where a security officer uses this system. The officer registers his / her social media account in the system and configures it to collect security-related information in real time. The following prompt sentence is input to the generative AI model:

[1557] Username: @cybersecuritynews

[1558] Post content: Sharing important information about the latest phishing attacks. Click here for detailed countermeasures. [Link]

[1559] Engagement data: Likes 50, Retweets 20, Comments 10

[1560] Based on this prompt, the generative AI model summarizes important information and notifies the security personnel. The security personnel can then click on a link to view more detailed information if necessary. This process allows security personnel to take prompt action without missing any important information.

[1561] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1562] Step 1:

[1563] The server accesses the API of the SNS service and collects timeline data using the authentication token. The input is the API endpoint of the SNS service and the authentication token, and the output is the collected timeline data. Specifically, the server sends an HTTP request to retrieve authenticated user data.

[1564] Step 2:

[1565] The server cleanses the collected timeline data. The input is the timeline data collected in step 1, and the output is the cleansed data. Specifically, a filtering process is performed to remove noise and unnecessary information from the timeline data stored in the database.

[1566] Step 3:

[1567] The server uses natural language processing technology to extract keywords, hashtags, and entities from the post content. The input is the cleansed data from step 2, and the output is the extracted keywords, hashtags, and entities. Specifically, it uses a natural language processing library to perform text analysis and extract important words and phrases.

[1568] Step 4:

[1569] The server evaluates the importance of posts based on the extracted data. The input is the keywords, hashtags, entities, and engagement data extracted in step 3, and the output is an importance score for each post. Specifically, the server applies a scoring algorithm based on the number of likes, retweets, comments, etc. to calculate the importance.

[1570] Step 5:

[1571] The server automatically summarizes the rated important posts. The input is the posts with high importance scores obtained in step 4, and the output is the summarized information. Specifically, it uses a generative AI model to convert the post content into a summary sentence.

[1572] Step 6:

[1573] The server delivers the summarized information to the user. The input is the summarized information from step 5, and the output is a notification message to the user. Specifically, the information is delivered via email notification or the app's push notification function.

[1574] Step 7:

[1575] The server provides links related to the distributed information. The input is the summarized information from step 5, and the output is links related to the summarized information. Specifically, the server extracts links from the original post and adds them to the summary.

[1576] Step 8:

[1577] The device records user operations. The input is the user's operations on the device (clicks, scrolls, etc.), and the output is a record of those operations. Specifically, it sets up an event listener and records each operation event in a log.

[1578] Step 9:

[1579] The server analyzes the recorded operation data and improves the summarization algorithm and delivery method. The input is the operation data recorded in step 8, and the output is an improved summarization algorithm and delivery method. Specifically, the operation data is statistically analyzed and the algorithm is adjusted through a feedback loop.

[1580] Step 10:

[1581] The server collects data from security-related social media accounts and provides notifications in real time. The input is data from security-related social media accounts, and the output is security information notifications delivered in real time. Specifically, it prioritizes data posted from specific security-related accounts and immediately notifies users.

[1582] 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.

[1583] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following embodiments are illustrative and do not limit the present invention.

[1584] This invention combines a system that collects timeline data from SNS services and efficiently provides important information to users with an emotion engine. This system consists of four main components: a server, a device, a user, and an emotion engine.

[1585] server

[1586] The server is responsible for collecting timeline data from SNS services. Specifically, it accesses the API of each SNS service and retrieves the timeline data using an authentication token. The collected data is stored in a database on the server.

[1587] The server cleanses the stored timeline data and removes unnecessary data, which improves data accuracy and makes subsequent processing more efficient.

[1588] The server uses natural language processing techniques to extract keywords, hashtags, and entities from posts, thereby identifying important information from the collected data.

[1589] The server evaluates the importance of posts based on the extracted data and selects the most important posts, taking into account engagement data (number of likes, retweets, comments, etc.).

[1590] The server uses an emotion engine to analyze the user's emotions from the collected timeline data and the user's past operation data, and reflects the emotion data in the importance evaluation of the summary information.

[1591] The server then summarises the selected important posts, using machine learning models and rule-based techniques to create short summaries of the posts' key points.

[1592] The server collects links related to the summarized information (such as the original post, additional details, etc.) and adds them to the summary data, allowing users to easily find more information.

[1593] The server prepares the summary information based on the user's delivery preferences (e.g. email, app notification, dashboard view) and formats the summary data accordingly.

[1594] The server delivers the summary information to the user in a manner that depends on the user's settings, for example, by emailing the summary information via a mail server or by sending a push notification to the app.

[1595] The server records and analyzes user actions (viewing summary information, clicking links, etc.) to continually improve the summary algorithm and delivery method.

[1596] Terminal

[1597] A terminal is a device (such as a smartphone, tablet, or PC) that a user uses to access the system. The user can use the terminal to receive the collected summary information.

[1598] The device records the user's actions and sends them to the server, which provides feedback to the server and uses it to improve the system.

[1599] User

[1600] A user is an individual or a corporation who wants to efficiently obtain important information from an SNS service. A user can use the service by registering their SNS account information in the system and providing the necessary information.

[1601] The user receives and checks the summary information delivered from the server using a terminal, and can also refer to detailed information by clicking on related links.

[1602] Users can customize their own notification settings, such as the frequency of notifications and how they want to receive them (email notifications, app notifications, etc.).

[1603] Emotion Engine

[1604] The emotion engine is a component for recognizing user emotions, which allows us to analyze user emotions from collected timeline data and user operation data.

[1605] The emotion engine has an algorithm that determines the user's emotions (happiness, surprise, sadness, etc.) from the content of posts and operation data. The emotion data is sent to the server and used to evaluate the importance of summary information and improve delivery methods.

[1606] The sentiment engine analyzes how users feel about specific keywords or entities and reflects this in selecting and summarizing important information.

[1607] Specific examples

[1608] For example, suppose User B has registered accounts for social networking services (e.g., Twitter and Instagram) in the system. The server accesses the APIs of these social networking services to collect User B's timeline data. It then cleanses the collected data and extracts important keywords and hashtags using natural language processing technology. The server uses an emotion engine to analyze emotions from User B's timeline data and past operation data, and reflects the emotion data in the importance rating of the summary information. For example, User B may rate posts containing keywords that frequently indicate the emotion "joy" as highly important. The server then summarizes the important posts and provides them to User B in the form of emails or app notifications. The summaries also include links related to the original posts, allowing User B to view the details. The emotion engine also collects User B's emotion data, which is used for future system optimization.

[1609] As described above, the system of the present invention can efficiently extract important information from SNS services and provide information optimized to suit the user's emotions, thereby solving the problem of information overload and improving user convenience.

[1610] The processing flow will be explained below.

[1611] Step 1:

[1612] The server accesses the API of the SNS service registered by the user and requests timeline data using the authentication token. Specifically, it sends an API request to obtain the user's timeline data (post content, number of likes, number of retweets, etc.).

[1613] Step 2:

[1614] The server receives the timeline data returned from the API and stores it in an internal database, along with metadata such as timestamps and user IDs.

[1615] Step 3:

[1616] The server cleanses the stored timeline data, removing duplicates and unnecessary data (such as advertising posts and spam) and checking the integrity of the data.

[1617] Step 4:

[1618] The server then uses natural language processing techniques to extract keywords, hashtags, and entities from the cleansed data, including techniques such as tokenization, part-of-speech tagging, and entity recognition.

[1619] Step 5:

[1620] The server evaluates the importance of each post based on the extracted keywords and entities, and uses a scoring algorithm to select the most important posts, taking into account engagement data (number of likes, retweets, comments, etc.).

[1621] Step 6:

[1622] The server analyzes the user's emotions using an emotion engine, which uses an algorithm to determine the user's emotions (e.g., joy, surprise, sadness) based on specific posts and past activity data.

[1623] Step 7:

[1624] The server adjusts the importance rating based on the analysis results of the emotion engine. Posts containing keywords that users frequently express the emotion of "joy" are given a higher rating.

[1625] Step 8:

[1626] The server then summarises the ranked posts, using machine learning models and rule-based techniques to provide a short summary of the posts' key points.

[1627] Step 9:

[1628] The server collects links related to the summarized information (such as the original post, additional details, etc.) and adds them to the summary data, allowing users to easily find more information.

[1629] Step 10:

[1630] The server prepares the summary information based on the user's delivery preferences (e.g. email, app notification, dashboard view) and formats the summary data accordingly.

[1631] Step 11:

[1632] The server delivers the summary information to the user in a manner that depends on the user's settings, such as by emailing the summary information via a mail server or by sending a push notification to the app.

[1633] Step 12:

[1634] The device records user operations (such as displaying summary information and clicking links), and this operation data is saved as a log.

[1635] Step 13:

[1636] The server collects and analyzes user operation data sent from the device, and uses this data to improve the summarization algorithm and delivery method.

[1637] Step 14:

[1638] The server will then apply the analysis results to optimize the information gathering, summarizing, and distribution processes from the next time onward, thereby improving the quality of the information provided to users.

[1639] Example 2

[1640] 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."

[1641] Currently, there is a huge amount of information available on social networking services, making it difficult for users to efficiently obtain important information. Furthermore, information provided does not take into account the user's emotional state, so information that meets the user's needs is often not provided. This increases the likelihood that users will miss useful information in this information-overloaded world. Furthermore, there is a need to accurately evaluate the importance and relevance of the information provided and deliver it to users in an appropriate format.

[1642] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1643] In this invention, the server includes means for collecting timeline data from an SNS service, means for cleansing the collected timeline data and removing unnecessary data, means for extracting keywords, hashtags, and entities from the posted content using natural language processing technology, means for evaluating the importance of posts based on the extracted data, means for analyzing user emotion data and reflecting the results in the importance evaluation, means for automatically summarizing the evaluated important posts, means for providing links related to the summarized information, means for formatting the summarized information based on the user's distribution settings, means for providing the distributed information to the user, means for recording user operations, and means for analyzing the recorded operation data and improving the summarization algorithm and distribution method. This allows users to efficiently obtain important information from vast amounts of information and further enables the provision of appropriate information according to the user's emotional state.

[1644] "SNS service" refers to a social networking service, an online platform for people to communicate over the Internet.

[1645] "Timeline data" refers to data that shows the content posted by users on social networking services and the order in which they were posted.

[1646] "Cleansing" is the process of removing unnecessary information from collected timeline data and extracting important information.

[1647] "Natural language processing technology" is a technology that allows computers to analyze and understand human language.

[1648] "Keywords" are important words or phrases in your post.

[1649] A "hashtag" is a tag preceded by the " " symbol that is added to a post to indicate a particular topic or theme.

[1650] An "entity" is a proper noun such as a person's name, place name, or organization name contained in the posted content.

[1651] "Importance evaluation" is the process of measuring the value and importance of a post based on certain criteria and assigning a score.

[1652] "Emotional data" refers to information that indicates the emotional state of a user.

[1653] "Summarizing" refers to the process of briefly summarizing the main points of the posted content.

[1654] "Link" means a URL or hyperlink that provides a connection to related sources of information or further information.

[1655] "Delivery Preferences" refers to options that allow users to set how they wish to receive information.

[1656] "Operational Data" means records of actions and events performed by users on the system.

[1657] A "summarization algorithm" is a formula or method used to efficiently summarize a post's content.

[1658] "Delivery method" refers to the means or process used to provide information to users.

[1659] The present invention is configured by combining a system that collects timeline data from SNS services and efficiently provides important information to users with an emotion engine.

[1660] server

[1661] The server is responsible for collecting timeline data from SNS services. Specifically, the server accesses the API of each SNS service (e.g., social networking platform) and obtains timeline data using an authentication token. This data is then stored in the server's database.

[1662] The collected data goes through a cleansing process to remove unnecessary data. This process improves the accuracy of the data and makes subsequent processing more efficient. The server uses natural language processing techniques (e.g., natural language processing libraries) to extract keywords, hashtags, and entities from the posts, thereby identifying important information.

[1663] Next, the server evaluates the importance of posts based on the extracted data. The server considers engagement data (e.g., number of likes, retweets, and comments) and reflects this in the importance evaluation. Furthermore, it uses an emotion engine to analyze user emotion data and reflects this in the importance evaluation of the summary information.

[1664] The server uses machine learning models (e.g., generative AI models) to automatically summarize important posts that have been rated, and also includes relevant links to help users find more information.

[1665] The server formats the summary information based on the user's delivery settings and prepares it for delivery. For example, if the user selects email notification, the server formats the summary information in HTML format and prepares it for email transmission. Finally, the server uses a delivery method such as sending the summary information via email via a mail server.

[1666] The server also records and analyzes user actions (viewing summary information, clicking links), and the resulting data is used to improve the summary algorithm and delivery method.

[1667] Terminal

[1668] The terminal is a device (e.g., smartphone, tablet, or PC) that users use to access the system. The user can use the terminal to receive and check the summary information delivered to them. The terminal also records the user's actions and sends them to the server. This data is passed to the server as feedback and used to improve the system.

[1669] User

[1670] A user is an individual or a corporation who wants to efficiently obtain important information from an SNS service. A user can use this service by registering their SNS account information in the system and providing the necessary information.

[1671] Users can use their devices to check summary information delivered from the server and click on related links to view detailed information. Users can also customize their delivery settings to receive information in a way that suits their needs (e.g., email notifications, app notifications).

[1672] Specific examples

[1673] For example, suppose User B has registered an account for a social networking service (e.g., a social networking platform) in the system. The server accesses the APIs of these social networking services to collect User B's timeline data. The server then cleanses the collected data and uses natural language processing technology to extract important keywords and hashtags.

[1674] The server uses an emotion engine to analyze emotions from User B's timeline data and past operation data, and reflects that emotion data in the importance rating of the summary information. For example, User B rates posts containing keywords that frequently indicate the emotion of "joy" with a high importance rating. Next, the server summarizes the important posts using a generative AI model and provides them to User B in the form of an email or app notification. The summary also includes a link related to the original post, allowing User B to check the details.

[1675] The emotion engine also collects emotion data from User B, which will be used to optimize the system in the future. Specific examples of prompt sentences are as follows:

[1676] "Extract important keywords from User B's social networking platform timeline data, analyze the user's sentiment using a sentiment engine, and summarize the important information. Include relevant links in the summary and provide it in the form of an email notification."

[1677] In this way, the present invention is a system that efficiently extracts important information from SNS services and provides information optimized to the user's emotions, thereby solving the problem of information overload and improving user convenience.

[1678] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1679] Step 1:

[1680] The server calls the API of the SNS service to obtain timeline data. Specifically, it sends an API request using the API key and authentication token of each SNS service to obtain timeline data in JSON format. In this process, it uses the authentication token and API endpoint of each SNS service as input and saves the obtained timeline data as output in a database.

[1681] Step 2:

[1682] The server cleanses the acquired timeline data. Specifically, it removes unnecessary fields from the JSON data and extracts only important fields (e.g., post content, timestamp, and user information). It removes noise and duplicate data to generate a clean dataset. In this process, it uses the acquired timeline data as input and generates cleansed data as output.

[1683] Step 3:

[1684] The server uses natural language processing techniques to extract keywords, hashtags, and entities from the cleansed data. Specifically, it uses natural language processing libraries (e.g., spaCy, NLTK) to parse the text of posts and extract important words and phrases. This process uses the cleansed data as input and produces a list of extracted keywords, hashtags, and entities as output.

[1685] Step 4:

[1686] The server evaluates the importance of posts based on the extracted data. Specifically, it calculates a score taking into account engagement data (e.g., number of likes, retweets, and comments) and selects posts with high importance. In this process, it uses the extracted data and engagement data as input and generates an importance evaluation result as output.

[1687] Step 5:

[1688] The server uses an emotion engine to analyze the user's emotional data and reflects the results in the importance rating. Specifically, the emotion engine analyzes the user's emotional state from the post content and operation data and modifies the importance rating. In this process, the post content and operation data are used as input, and a modified importance rating result is generated as output.

[1689] Step 6:

[1690] The server automatically summarizes posts based on the importance assessment results. Specifically, it uses a generative AI model (e.g., GPT-3) to generate a summary by briefly summarizing the main points of each post. In this process, it uses the importance assessment results as input and generates summarized text as output.

[1691] Step 7:

[1692] The server collects and provides links related to the summarized information, specifically, links to the original post and additional details in the summary data. This process uses the summary text as input and generates the linked summary data as output.

[1693] Step 8:

[1694] The server formats the summary information based on the user's delivery settings. Specifically, it formats the summary information into a format such as email or app notification according to the delivery method selected by the user. In this process, the server uses the linked summary data and delivery setting information as input and generates formatted delivery data as output.

[1695] Step 9:

[1696] The server provides the formatted delivery data to the user, specifically by sending summary information to the user via a mail server or push notification system, using the formatted delivery data as input and generating the notification sent to the user as output.

[1697] Step 10:

[1698] The server records user actions and analyzes the recorded data. Specifically, it records user actions such as displaying summary information and clicking links, and analyzes the data to improve the system. In this process, it uses user action data as input and generates analysis results as output.

[1699] (Application example 2)

[1700] 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."

[1701] In recent years, with the spread of social networking services, users are surrounded by a vast amount of information. This makes it difficult for them to find the information they truly need. Furthermore, there is a need for systems that can provide information that responds to users' emotions, rather than simply collecting and summarizing information. Furthermore, there is a need for systems that can improve the shopping experience in virtual stores by analyzing users' emotions and suggesting products based on those emotions.

[1702] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1703] In this invention, the server includes means for collecting timeline data from an SNS service, means for cleansing the collected timeline data and removing unnecessary data, means for extracting keywords, hashtags, and entities from the posted content using natural language processing technology, means for evaluating the importance of posts based on the extracted data, means for automatically summarizing the evaluated important posts, means for delivering the summarized information to users, means for providing links related to the delivered information, means for recording user operations, means for analyzing the recorded operation data and improving the summarization algorithm and delivery method, means for analyzing emotions from the recorded operation data, and means for suggesting products based on the analyzed emotion data. This makes it possible to efficiently extract important information from an SNS service and provide information and product suggestions optimized to match the user's emotions.

[1704] "SNS service" is an abbreviation for social networking service, a platform that allows users to communicate with other users online.

[1705] "Timeline data" is data that displays the content posted by users on social media services and the actions (likes, retweets, etc.) taken by other users in chronological order.

[1706] "Cleansing" is a process of removing unnecessary information and noise from collected data, and is a preprocessing step to improve the quality of the data.

[1707] "Automatic summarization" refers to the process of shortening long posts and extracting only the main points in a concise manner.

[1708] "Natural language processing technology" is a technology that enables computers to understand, interpret, and process human language, specifically extracting keywords and entities, and analyzing sentiment.

[1709] "Emotional data" refers to data related to emotions such as joy, sadness, and surprise that are derived from users' posts and actions.

[1710] "Suggesting products" means selecting and presenting products that are highly relevant to the user based on analyzed emotional data and the user's past operation data.

[1711] A "summarization algorithm" is a method or formula for summarizing the content of a post in a concise manner, and includes machine learning models and rule-based methods.

[1712] "Delivery method" refers to the means by which summary information and product suggestions are provided to users, including email, app notifications, dashboard displays, etc.

[1713] The following describes in detail an embodiment of the present invention. The present invention is a system that collects timeline data from social networking services and efficiently provides important information to users. This system also incorporates a function to analyze users' emotions and make product recommendations based on those emotions.

[1714] The server first collects timeline data through the API of the social media service. At this time, it authenticates the user using an authentication token. The collected data undergoes a cleansing process to remove unnecessary information. Next, it uses natural language processing technology to extract keywords, hashtags, and entities from the post content.

[1715] Based on the extracted data, the server rates the posts' importance, taking into account engagement data (number of likes, retweets, comments, etc.). The ranked important posts are automatically summarized to generate a summary, which includes links to the original post and additional details.

[1716] The summarized information is formatted appropriately based on the user's delivery settings and delivered to the user via email, app notifications, etc. User actions (viewing the summary information, clicking links, etc.) are recorded and sent to a server. Analysis of this recorded data allows for improvements to the summarization algorithm and delivery method.

[1717] Furthermore, an emotion engine is used to analyze emotions from user posts and operation data. Emotional data extracted from the recorded operation data is reflected in the evaluation of the importance of information and product suggestions. Based on the emotional data, the most suitable products are selected from a product catalog and suggested to the user.

[1718] In this embodiment, a smartphone, smart glasses, or a head-mounted display can be used as hardware, and the Requests library, a natural language processing library (e.g., NLTK or spaCy), and a sentiment analysis library (e.g., VADER) are used as software.

[1719] For example, if a user posts on social media that they want a new smartphone, the server collects the post, cleansing it, and extracts keywords. The emotion engine then determines that the post is a "joy" message, generates summary information, and suggests suitable smartphones and accessories. This information is then sent via email or notification based on the user's settings.

[1720] Example prompt sentence:

[1721] Build a system program that analyzes emotions such as joy and sadness based on the content users post on social media and suggests the best products for them.

[1722] As described above, this system can improve user convenience by efficiently extracting important information from SNS services and providing information and product suggestions that match the user's emotions.

[1723] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1724] Step 1:

[1725] The server accesses the API of the SNS service and collects timeline data using the authentication token.

[1726] Input: SNS service API URL, authentication token

[1727] Output: A list of timeline data

[1728] Specific operation: The server sends an HTTP request to the API of each SNS service and retrieves the user's timeline data using the authentication token. The retrieved data is saved in list format.

[1729] Step 2:

[1730] The server cleanses the collected timeline data and removes unnecessary data.

[1731] Input: List of timeline data

[1732] Output: Cleansed timeline data

[1733] How it works: The server analyzes the collected timeline data and removes unnecessary information such as spam, advertisements, and duplicate data. The cleansed data is then passed on to the next processing step.

[1734] Step 3:

[1735] The server uses natural language processing technology to extract keywords, hashtags, and entities from the post content.

[1736] Input: Cleansed timeline data

[1737] Output: A list of extracted keywords, hashtags, and entities

[1738] How it works: The server uses a natural language processing library (such as NLTK or spaCy) to analyze the text data and extract important keywords and entities. The extracted information is saved in a list format.

[1739] Step 4:

[1740] The server evaluates the importance of the post based on the extracted data.

[1741] Input: List of keywords, hashtags, entities

[1742] Output: A list of posts with their importance ratings

[1743] Specific operation: The server calculates an importance score based on the extracted keywords and engagement data (number of likes, retweets, and comments) and evaluates the importance of each post. Posts with high importance are passed on to the next step.

[1744] Step 5:

[1745] The server automatically summarizes the most important posts that have been rated.

[1746] Input: A list of posts with importance ratings

[1747] Output: List of summary information

[1748] How it works: The server uses machine learning models and rule-based methods to extract and shorten the main points that summarize the post content. The generated summary information is saved in a list format.

[1749] Step 6:

[1750] The server collects links related to the summarized information and appends them to the summary data.

[1751] Input: List of summary information

[1752] Output: A list of summary data with link information added

[1753] What happens: The server collects links to the original post and additional details and adds them to the summary information. The linked data is passed on to the next step.

[1754] Step 7:

[1755] The server prepares the summary information based on the user's delivery preferences.

[1756] Input: User's delivery settings, list of summary data with link information

[1757] Output: Summary data formatted for delivery

[1758] Specific behavior: The server takes into account the user's delivery preferences (email, app notifications, dashboard display) and formats the summary data appropriately.

[1759] Step 8:

[1760] The server delivers the summary information to the user in a manner that depends on the settings.

[1761] Input: Summary data formatted for delivery

[1762] Output: Notifications and emails delivered to users

[1763] Specific operation: The server uses the mail server or push notification to send summary information to the user, who then receives the information on their device.

[1764] Step 9:

[1765] The device records user actions (displaying summary information, clicking links, etc.) and sends them to the server.

[1766] Input: User operation data

[1767] Output: Operation data sent to the server

[1768] Specific operation: When a user views summary information on their device and clicks on a link, the operation data is recorded and sent to the server.

[1769] Step 10:

[1770] The server analyzes the recorded operation data and improves the summarization algorithm and delivery method.

[1771] Input: User operation data

[1772] Output: Improved summarization algorithms and delivery methods

[1773] Specific operation: The server analyzes user operation data, evaluates the performance of the summarization algorithm and delivery method, and makes necessary adjustments and improvements to reflect them in future deliveries.

[1774] Step 11:

[1775] The server analyzes emotions from the recorded operation data.

[1776] Input: User operation data

[1777] Output: Emotion data

[1778] Specific operation: The server uses a sentiment analysis library (e.g., VADER) to calculate the user's sentiment score from the operation data. The calculated sentiment data is reflected in the information importance rating and product recommendations.

[1779] Step 12:

[1780] The server suggests products based on the analyzed emotion data.

[1781] Input: Emotion data, product catalog

[1782] Output: A list of suggested products for the user

[1783] Specific operation: The server selects the most suitable products from the product catalog based on the emotion data and proposes them to the user. The selected product list is then provided to the user along with summary information.

[1784] 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.

[1785] 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.

[1786] 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.

[1787] 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.

[1788] 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.

[1789] These emotions are distributed in the 3 o'c...

Claims

1. A means for collecting timeline data from SNS services; a means for cleansing the collected timeline data and removing unnecessary data; A means of extracting keywords, hashtags, and entities from the content of posts using natural language processing technology; A means for assessing the importance of posts based on the extracted data; A means of automatically summarizing important rated posts; a means for delivering the summarized information to the user; means for providing links related to the distributed information; a means for recording user actions; A means of analyzing the recorded operational data to improve summarization algorithms and delivery methods; A system including:

2. The system of claim 1 , wherein the system uses an authentication token to collect timeline data from a social networking service.

3. 2. The system according to claim 1, further comprising means for delivering summary information in accordance with a delivery setting of a user.

Images