System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting information about an election from a plurality of sources on the Internet; means for categorizing and filtering the collected information; means for evaluating the credibility of the collected information using a credibility evaluation algorithm and calculating a credibility score; means for automatically displaying the information based on the credibility score and generating a summary site; and means for periodically updating the summary site to reflect the latest information.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 elections, there is a problem that it is difficult for voters to gather information about candidates and make appropriate decisions. In particular, because information is scattered across various sources, it is difficult to efficiently gather reliable information, resulting in situations where voters are unable to cast their votes based on sufficient information. To solve this problem, a system is needed that can centrally collect a wide range of information, evaluate its reliability, and present it in an easy-to-understand manner. [Means for solving the problem]

[0005] This invention provides a system for appropriately collecting, classifying, evaluating, and presenting election-related information. Specifically, the system includes a means for collecting election-related information from multiple sources on the Internet, a means for categorizing and filtering the collected information, a means for evaluating the credibility of the collected information using a reliability evaluation algorithm and calculating a reliability score, a means for automatically displaying information based on the reliability score and generating a website aggregation, and a means for periodically updating the website aggregation to reflect the latest information. This system enables voters to efficiently collect reliable information and make appropriate decisions.

[0006] "Election information" refers to all information related to candidates and election activities, including political ideas, policy proposals, election campaign details, gossip, etc.

[0007] "Multiple sources on the internet" refers to various information providers and platforms accessible via the internet, such as news websites, blogs, and social media.

[0008] "Means of collection" include methods of automatically obtaining election information from designated sources using crawling technology or APIs.

[0009] "Classification and filtering methods" refers to methods for sorting collected information into specific categories (such as political ideology, election campaign content, gossip, etc.) and removing unnecessary or redundant information.

[0010] "Trustworthiness assessment algorithm" refers to an algorithm for assessing the credibility of collected information and calculating a trust score based on the reliability of the information source and its past assessment history.

[0011] A "trust score" is an indicator that numerically represents the credibility of information based on the reliability of the source of information and its past evaluation history.

[0012] The "means for generating an aggregate site" refers to a method for automatically generating a website that displays collected and classified information in a unified manner.

[0013] "Means of regular updates to reflect the latest information" refers to a method of incorporating new information according to a set schedule and keeping the content of the aggregation site up to date.

[0014] "Users" refer to election voters who collect and use the latest information on candidates.

[0015] "Notification Preferences" means the user's ability to receive notifications via their chosen means (e.g., email) when new information about a particular candidate is added. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0024] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0037] This invention is a system that efficiently collects, classifies, and evaluates election-related information and provides it to voters in an easy-to-understand manner. The program processing of this system is explained below in natural language.

[0038] Information Collection Module

[0039] The server collects election-related information from news websites, blogs, social media, and other sources on the Internet at specific times each day. It pre-sets the websites and hashtags it monitors and crawls them all. For example, the server crawls news sites based on a pre-set URL list at 1:00 AM and 1:00 PM to collect election-related articles. It also collects social media posts using specific hashtags (e.g., "election 2023").

[0040] Data Reduction Module

[0041] The server analyzes the collected information and classifies it by category (political ideology, election campaign content, gossip, etc.). It uses natural language processing (NLP) technology to extract keywords and content from each piece of information and automatically classify it. It also filters out duplication and noise, leaving only useful information. For example, if the same news is collected from multiple sources, the server will only retain the most reliable source.

[0042] Authenticity Assessment Module

[0043] The server calculates a trust score based on the reliability of the source and its past evaluation history to assess the credibility of the collected information. Using AI algorithms, the server checks the reliability and consistency of a specific source and assigns a trust score. For example, the server evaluates the trust score of a news website and the credibility of an article based on that, and filters out information with low credibility.

[0044] Aggregation site generation module

[0045] The server generates a website based on the information that has been organized and credibility-evaluated. This website has a profile page for each candidate, and the latest information is displayed in categories such as election campaign details, policy proposals, and gossip. For example, the server creates a section on Candidate A's page that displays the latest policy proposals and information on election campaign events.

[0046] Auto Update Module

[0047] The server periodically retrieves new information and automatically updates the aggregation site. This ensures that the information on the site is always up to date. For example, after crawling twice a day, the server updates the aggregation site with new information and automatically archives old information.

[0048] User Access Module

[0049] Users can access the aggregation site from their devices (smartphones or PCs) and view the latest information on each candidate and category. They can also set up email notifications for updates on specific candidates. For example, a user can check the latest developments of candidate A on their smartphone and set up notifications to be sent by email when new information is added.

[0050] By combining the above modules, this invention can realize a system that properly collects, classifies, and evaluates information related to elections, and provides voters with reliable information.

[0051] The processing flow will be explained below.

[0052] Step 1: Gather information

[0053] The server loads a list of websites, news sources, and social media hashtags to monitor.

[0054] The server crawls monitored sites at designated times (for example, 1:00 AM and 1:00 PM) to collect new articles and posts related to the election.

[0055] The server temporarily stores the collected data in storage.

[0056] Step 2: Data Classification

[0057] The server analyzes the collected information and uses natural language processing (NLP) technology to extract keywords and content from each piece of information.

[0058] Based on the extracted keywords, the server classifies the information into categories (political ideology, election campaign content, gossip, etc.).

[0059] The server filters out redundant information and noise, leaving only the useful information.

[0060] Step 3: Credibility assessment

[0061] The server uses a credibility assessment algorithm to assess the authenticity of the collected information.

[0062] The server calculates a trust score based on the reliability of the source and its past rating history.

[0063] The server filters out information with a reliability score below a certain level, and only information with a high reliability score proceeds to the next step.

[0064] Step 4: Generate a website

[0065] The server generates a summary site based on the information that has been organized and evaluated for credibility.

[0066] The server creates a profile page for each candidate, displaying the latest information in categories such as political ideology, election activities, policy proposals, and gossip.

[0067] The server optimizes the site design for user accessibility.

[0068] Step 5: Automatic Updates

[0069] The server retrieves new information on a specified schedule and periodically updates the content of the aggregation site.

[0070] The server automatically archives old information and reflects the latest information.

[0071] The server crawls twice a day and updates the site with new information in real time.

[0072] Step 6: User Access and Notification

[0073] Users access the aggregation site from their device (smartphone or PC) and view information on candidates and categories that interest them.

[0074] Users can set up update notifications for specific candidates.

[0075] The server will send email notifications based on the user's settings when new information is added.

[0076] Through these processing steps, the system can efficiently collect, classify, and evaluate election-related information, providing voters with reliable information.

[0077] Example 1

[0078] 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."

[0079] Election-related information is diverse and collected from a variety of sources. This information is not necessarily reliable, and there is a lot of duplication and noise, making it difficult for voters to obtain accurate and reliable information about elections. Furthermore, because the information is scattered, there is a lack of efficient ways to obtain the latest information about specific candidates. Furthermore, there is the problem that it is difficult to always obtain the latest information during election periods, when information is frequently updated.

[0080] 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.

[0081] In this invention, the server includes: means for collecting election-related information from multiple sources on the Internet; means for categorizing and filtering the collected information using natural language processing technology; means for evaluating the credibility of the collected information using a reliability evaluation algorithm that calculates a reliability score based on the reliability of the information source and its past evaluation history; means for automatically displaying the information based on the reliability score and generating a summary site including a profile page for each candidate; and means for periodically updating the summary site to reflect the latest information. This allows voters to efficiently obtain the latest, reliable election information on a single site.

[0082] "Multiple sources on the internet" refers to online platforms such as websites, blogs and social media platforms that are used to provide data about the election.

[0083] "Means of collection" refers to programs and algorithms for automatically obtaining information on the Internet, and is a system for crawling based on specific keywords or URL lists.

[0084] "Natural language processing technology" refers to the general technology for analyzing text data to understand its meaning and process information written in human language, extracting, classifying, and filtering content.

[0085] "Categorizing and filtering" refers to the process of separating collected information based on specific themes or topics, and removing redundancies and noise to retain only the useful information.

[0086] "Source credibility" is an assessment of how accurate and reliable the source of information has been in the past, and serves as a criterion for judging the credibility of information.

[0087] "Past evaluation history" refers to a record of evaluations of the reliability and source of previously collected information, and is data used to determine the reliability of current information.

[0088] A "trust score" is a numerical representation of the credibility of collected information or information sources, with a higher score indicating higher reliability.

[0089] A "trustworthiness evaluation algorithm" refers to a calculation method or program for calculating the reliability of information based on the reliability of the information source and past evaluation history.

[0090] An "aggregator site" is a website that displays collected and classified information in a centralized manner, and is a platform that provides each candidate with a profile page and the latest information.

[0091] "Regular updating means" means a mechanism for automatically updating the contents of a database or website to collect new information at set intervals and keep existing data up to date.

[0092] "Means for enabling access via a web browser" refers to a mechanism that allows a user to access the aggregation site via a web browser using a terminal connected to the Internet.

[0093] "Means for setting up update notifications" refers to an interface that allows users to set up notifications, such as by email, when new information is added about a specific candidate or category.

[0094] The present invention relates to a system that efficiently collects, classifies, and evaluates election-related information and provides it to voters in an easy-to-understand manner. This system consists of three main components: a server, a terminal, and a user. The hardware and software required to implement the present invention are described in detail below.

[0095] The server is an internet-connected computer that runs a program using the Python programming language and related libraries (BeautifulSoup, SpaCy, etc.). The server first collects election-related information from news websites, blogs, social media, etc. on the internet. For example, the server crawls news sites based on a set list of URLs at 1:00 AM and 1:00 PM, and also collects social media posts using a specific hashtag (e.g., "Election 2023").

[0096] The server then analyzes the collected information using natural language processing (NLP) technology and classifies it by category (political ideology, election campaign details, gossip, etc.). Specifically, it uses the SpaCy library to extract text features and then uses machine learning algorithms such as SVM (Support Vector Machine) to classify the information. It also filters out duplicate and noisy information, leaving only the useful information. For example, if the same news is collected from multiple sources, the server will only retain the most reliable source.

[0097] The server then evaluates the credibility of the collected information by referencing past evaluation history and external credibility score databases (e.g., Media Bias / Fact Check) to assess the trustworthiness of sources and articles, and then calculating a credibility score using an AI model. Information with low credibility is filtered out, and only information with high credibility is retained.

[0098] After sorting and evaluating the credibility of the information, the server generates an aggregate website. This website has a profile page for each candidate, with the latest information displayed in categories such as election activities, policy proposals, and gossip. For example, the server creates a section on Candidate A's page that displays the latest policy proposals and information on election campaign events. The aggregate website is built using the Django framework.

[0099] In addition, the server periodically retrieves new information and automatically updates the aggregation site, ensuring that the information on the site is always up to date. After crawling twice a day, the server updates the aggregation site with new information and automatically archives old information.

[0100] Users can access the website through a web browser on their device (smartphone or PC) and view the latest information about each candidate and category. They can also set up email notifications for updates about specific candidates. For example, a user can check the latest information about candidate A on their smartphone and set up notifications to be sent by email when new information is added.

[0101] Below are some example prompts to input to a generative AI model:

[0102] (Example of a prompt)

[0103] "Collect news articles about specific candidates, including their latest policy proposals and campaign events, and organize them by category. Also, rate the credibility of the information you collect and display only the most credible information."

[0104] As described above, the present invention realizes a system for providing information about elections efficiently and reliably.

[0105] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0106] Step 1: Gather information

[0107] The server will crawl election information from news websites, blogs and social media across the internet at 1:00 AM and 1:00 PM.

[0108] Input: A pre-defined list of URLs or a specific hashtag (e.g., Election 2023).

[0109] What it does: The server uses Python's BeautifulSoup library to parse HTML and extract news articles and social media posts, and it also uses the Twitter API to collect tweets containing specific hashtags.

[0110] Output: A text data list of news articles and social media posts about the election.

[0111] Step 2: Data analysis and classification

[0112] The server analyzes the collected information using natural language processing (NLP) technology and classifies it into categories.

[0113] Input: The text data list collected in step 1.

[0114] What it does: The server uses the SpaCy library to extract text features, and then uses SVM (Support Vector Machine) and other classification algorithms to classify the data into categories such as political ideology, campaign content, gossip, etc. It also filters out duplicates and noise.

[0115] Output: A list of text data sorted by category.

[0116] Step 3: Credibility assessment

[0117] The server calculates a trust score based on the reliability of the source and past evaluation history to evaluate the credibility of the collected information.

[0118] Input: The text data list classified in step 2.

[0119] Specific operation: The server refers to each source's domain name, past rating history, and an external trust score database, and calculates a trust score using an AI model (e.g., random forest or neural network).

[0120] Output: A list of text data with a confidence score for each piece of information.

[0121] Step 4: Generate a website

[0122] The server generates a summary site based on the information that has been organized and evaluated for credibility.

[0123] Input: A list of text data with confidence scores assigned in Step 3.

[0124] What it does: The server adds data to a website built using the Django framework, updates each candidate's profile page, and dynamically generates HTML templates to display the information.

[0125] Output: A website that aggregates the latest election information.

[0126] Step 5: Automatic Updates

[0127] The server periodically retrieves new information and automatically updates the aggregation site.

[0128] Input: Historical database and newly collected information.

[0129] What it does: The server sets up a Cron job to run the crawl twice a day, updating the database so that new information is added and old information is archived.

[0130] Output: A website that aggregates information and keeps it up to date.

[0131] Step 6: User Access

[0132] Users can access the aggregation site from their devices (smartphones or PCs) and view the latest information on each candidate and category.

[0133] Input: The user's access request.

[0134] What happens: A user accesses the site through a web browser and views a specific candidate or category page. The user also configures email notifications in their account settings page to receive notifications when new information is added.

[0135] Output: Latest election information available to the user, along with email notification settings.

[0136] (Application example 1)

[0137] 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."

[0138] There is a wide range of information related to elections, and the challenge is to centrally organize it while evaluating its credibility and reliability and provide it to voters. Furthermore, in order to immediately reflect the collected information in actual election activities and choices, it is necessary to provide the latest information in near real time. Furthermore, there are insufficient means of providing interactive election-related information in brick-and-mortar stores, and a system that allows users to easily access it is needed.

[0139] 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.

[0140] In this invention, the server includes: means for collecting election-related information from multiple sources on the Internet, including news websites, blogs, and social networking sites; means for categorizing and filtering the collected information; means for evaluating the credibility of the collected information using a reliability evaluation algorithm and calculating a reliability score; means for automatically displaying the information and generating a website aggregation based on the reliability score; means for periodically updating the website aggregation to reflect the latest information; and means for providing an interface that makes the information available via smartphones, tablets, and interactive display devices. This makes it possible to centrally manage collected election-related information in a reliable manner and provide it interactively in physical stores.

[0141] "Election information" refers to general information such as election campaigns, political ideas, candidate profiles, policy proposals, and related news and events.

[0142] "Multiple sources on the Internet" refers to multiple online platforms, including news websites, blogs, and social media, and has a mechanism for collecting information from these.

[0143] "Classification by category" is a process of organizing collected information by theme, such as political ideology, election campaign details, or gossip, making it easier for users to understand the information.

[0144] "Filtering" is the process of removing redundancy and noise from collected information and selecting only useful information.

[0145] A "trustworthiness evaluation algorithm" is a method for calculating the reliability of collected information based on the reliability of the information source and past evaluation history.

[0146] A "trust score" is a numerical representation of the reliability of a source of information and the content of the information, with a higher score indicating more trustworthy information.

[0147] An "Omatome Site" is a website that displays and provides organized, categorized, and evaluated election information in a centralized manner.

[0148] "Periodic updating" refers to a process of incorporating new information at regular intervals to keep the information up-to-date.

[0149] "Interface provision means" refers to mechanisms that make it easier for users to access information through smartphones, tablets, and interactive display devices.

[0150] To implement this invention, the following system is constructed. A server collects election-related information from news websites, blogs, social networking sites, etc. on the Internet at a specific time each day. Specifically, the server uses a crawling tool to collect information based on a pre-set URL list and hashtags.

[0151] Information Collection Module

[0152] The server uses the requests library and BeautifulSoup to collect information from news websites and blogs. Information from social media sites is collected using the corresponding APIs. For example, news sites are crawled at 1:00 AM and 1:00 PM every day to collect election-related articles and posts. This also includes social media posts with specific hashtags such as "Election 2023."

[0153] Data Reduction Module

[0154] The server analyzes the collected information and classifies it by category (political ideology, election campaign details, gossip, etc.). It uses NLP (natural language processing) technology to automatically categorize information by analyzing keywords and context. Specifically, it uses spaCy and BERT models to extract key keywords from documents and categorize them based on those keywords. Additionally, if the same news is collected from multiple sources, it eliminates duplicates and retains only the most reliable source.

[0155] Authenticity Assessment Module

[0156] The server evaluates the credibility of the collected information by calculating a trust score based on the reliability of the source and past evaluation history. It uses AI algorithms to check the reliability and consistency of a specific source and assign a trust score. The evaluation uses machine learning libraries such as Scikit-learn and TensorFlow.

[0157] Aggregation site generation module

[0158] The server then generates a website based on the information that has been organized and credibility-assessed. This website has a profile page for each candidate, with the latest information displayed in categories such as election activities, policy proposals, and gossip.

[0159] Auto Update Module

[0160] The server periodically retrieves new information and automatically updates the aggregation site. This ensures that the information on the site is always up to date. For example, after crawling twice a day, new information is updated on the aggregation site, and old information is automatically archived.

[0161] User Access Module

[0162] Users can access the website from their smartphones, tablets, and interactive display devices to view the latest information on each candidate and category. They can also opt to receive email updates about specific candidates, providing real-time access to the election information they need.

[0163] Specific examples

[0164] A specific example is the prompt "Aggregate, categorize, and rate the credibility of the latest news about Japan's 2023 elections."

[0165] Example prompt:

[0166] "Please compile the latest news about the 2023 Japanese election and categorize it into the following categories: 'Political ideology,' 'Election campaign content,' and 'Gossip.' Also, please rate the trustworthiness of each news source."

[0167] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0168] Step 1:

[0169] The server collects election-related information from news websites, blogs, social media, and other sources on the Internet at designated times.

[0170] Input: a specific time, a set list of URLs, a specific hashtag (e.g., election 2023).

[0171] How it works: The server uses the requests library and BeautifulSoup to crawl each URL and retrieve election-related articles and posts. It also collects information from social media sites using their corresponding APIs.

[0172] Output: Collected election-related information (articles, posts).

[0173] Step 2:

[0174] The server analyzes the information collected in step 1, classifies it by category (political ideology, election campaign content, gossip, etc.), and filters it.

[0175] Input: Collected election-related information.

[0176] How it works: The server uses NLP techniques such as spaCy and BERT models to extract keywords and key content from documents and automatically classify them into predefined categories, filtering out redundant and noisy information.

[0177] Output: Useful information sorted by category.

[0178] Step 3:

[0179] The server evaluates the credibility of the information classified in step 2 and calculates a trust score.

[0180] Input: Useful information sorted by category.

[0181] How it works: The server uses machine learning libraries such as Scikit-learn or TensorFlow to calculate a trust score based on the reliability of the source and its past rating history.

[0182] Output: Information with a confidence score.

[0183] Step 4:

[0184] The server generates an aggregate site based on the information that was assigned a trust score in step 3.

[0185] Input: Information with a confidence score.

[0186] How it works: The server generates profile pages for each candidate, creating pages that display the latest information by category, such as campaign activities, policy proposals, and gossip.

[0187] Output: Aggregate site (web page).

[0188] Step 5:

[0189] The server periodically retrieves new information and automatically updates the aggregation site.

[0190] Input: Newly collected election information (reprocessed from step 1).

[0191] What happens: The server re-runs steps 1 through 4 with the new information to keep the site up to date.

[0192] Output: A summary site that reflects the latest information.

[0193] Step 6:

[0194] Users access the aggregation site from their smartphones, tablets, and interactive display devices to view the latest information about each candidate and category.

[0195] Input: URL of the aggregation site.

[0196] How it works: A device (smartphone, tablet, etc.) connects to the website through a browser, allowing users to interactively view the latest election information. Users can also opt to receive email updates about specific candidates.

[0197] Output: Interactive election updates and email notification options.

[0198] 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.

[0199] This invention is a system that efficiently collects, classifies, and evaluates election-related information, provides it to voters in an easy-to-understand manner, and recognizes the user's emotions and dynamically adjusts the way the information is presented. Below, we will explain the program processing of this system in natural language.

[0200] Information Collection Module

[0201] The server pre-configures websites and social media hashtags to monitor, crawls them at designated times (e.g., 1:00 AM and 1:00 PM) to collect new election-related information, and temporarily stores the collected data. For example, the server collects articles and posts related to "Election 2023" from designated news portals and social media.

[0202] Data Classification Module

[0203] The server analyzes the collected information and uses natural language processing (NLP) technology to extract keywords and content from each piece of information. This allows the information to be automatically categorized into categories such as political ideology, election campaign content, and gossip. It also filters out duplication and noise, retaining only useful information. For example, if similar news is obtained from multiple sources, the server selects the most reliable source and deletes the rest.

[0204] Authenticity Assessment Module

[0205] The server evaluates the credibility of the collected information using a credibility evaluation algorithm. The algorithm calculates a credibility score based on the reliability of the source and its past evaluation history. Information with a credibility score below a certain level is filtered out, and only highly credible information is advanced to the next step. For example, the server evaluates the credibility score of news sites and eliminates articles with low credibility.

[0206] Aggregation site generation module

[0207] The server generates a website based on the information that has been organized and credibility-evaluated. This website has a profile page for each candidate, displaying the latest information by category, such as political ideology, election campaign details, policy proposals, and gossip. For example, the server creates a section on Candidate A's page that displays the latest policy proposals and election campaign event information.

[0208] Auto Update Module

[0209] The server retrieves new information according to a specified schedule and periodically updates the contents of the aggregation site. This ensures that the information on the site is always up to date. For example, the server updates the new information after crawling twice a day, and automatically archives old information.

[0210] User Access and Notification Module

[0211] Users access the aggregation site from their devices (smartphones or PCs) and view the latest information on candidates and categories of interest. They can also set up update notifications for specific candidates. This allows users to receive email notifications when new information is added. For example, a user can check the latest developments of candidate A on their smartphone and set up email notifications when new information is added.

[0212] Emotion Engine Module

[0213] The server is equipped with an emotion engine to recognize the user's emotions. This engine analyzes the user's emotions based on the information the user is viewing and their interaction patterns. For example, the server analyzes the user's click history and browsing time to estimate their emotional state, such as their interests and stress level.

[0214] Dynamic Display Adjustment Module

[0215] The server dynamically adjusts the display format of information based on the emotional data obtained from the emotion engine. For example, if the user is feeling stressed, the displayed information is simplified. It also prioritizes the display of information about specific candidates based on the results of emotion analysis. For example, if the server determines that the user is interested in candidate B, it prioritizes displaying information about candidate B on the top page.

[0216] By combining the above modules, the present invention can realize a system that not only provides information but also dynamically presents information taking into account the emotional state of the user.

[0217] The processing flow will be explained below.

[0218] Step 1: Gather information

[0219] The server loads a list of websites, news sources, and social media hashtags to monitor.

[0220] The server crawls these sources at designated times (e.g., 1:00 AM and 1:00 PM) to collect election-related information.

[0221] The server temporarily stores the collected information in storage.

[0222] Step 2: Data Classification

[0223] The server analyzes the collected information and extracts keywords and content using natural language processing (NLP) technology.

[0224] Based on the extracted keywords, the server classifies the information into categories (political ideology, election campaign content, gossip, etc.).

[0225] The server filters out redundant information and noise, and keeps only the useful information.

[0226] Step 3: Credibility assessment

[0227] The server uses a credibility assessment algorithm to assess the authenticity of the collected information.

[0228] The server calculates a trust score based on the reliability of the source and its past rating history.

[0229] The server filters out information with a reliability score below a certain level, and only information with a high reliability score proceeds to the next step.

[0230] Step 4: Generate a website

[0231] The server generates a summary site based on the information that has been organized and evaluated for credibility.

[0232] The server creates a profile page for each candidate, displaying the latest information by category, such as political ideology, election campaign details, policy proposals, and gossip.

[0233] The server optimizes the site design for user accessibility.

[0234] Step 5: Automatic Updates

[0235] The server retrieves new information on a specified schedule and periodically updates the content of the aggregation site.

[0236] The server automatically archives old information and reflects the latest information.

[0237] The server crawls twice a day and updates the site with new information in real time.

[0238] Step 6: User Access and Notification

[0239] Users access the aggregation site from their device (smartphone or PC) and view information on candidates and categories that interest them.

[0240] Users can set up update notifications for specific candidates.

[0241] The server will send email notifications when new information is added based on the user's notification settings.

[0242] Step 7: Emotion Recognition

[0243] The server provides an emotion engine for recognizing the user's emotions.

[0244] The server collects user interaction patterns such as click history, viewing time, and mouse movements.

[0245] The server analyzes interaction patterns and estimates the user's emotional state (interests, concerns, stress, etc.).

[0246] Step 8: Dynamic display adjustment

[0247] The server dynamically adjusts the presentation of information based on data from the emotion engine.

[0248] The server simplifies the information displayed when the user is stressed.

[0249] Based on the results of the sentiment analysis, the server prioritizes displaying information about specific candidates.

[0250] For example, if the user shows a strong interest in candidate A, the server places information about candidate A in a prominent position on the top page.

[0251] Through these steps, the system can efficiently collect information about elections, evaluate its reliability, and present information according to the user's emotional state.

[0252] Example 2

[0253] 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."

[0254] Conventional election information systems have problems with the quality of information provided to users due to inefficient collection, classification, and reliability evaluation of information. Furthermore, they lack the ability to dynamically adjust information display according to user emotions, resulting in a suboptimal user experience.

[0255] 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.

[0256] In this invention, the server includes means for collecting election-related information from multiple sources on the Internet, means for categorizing and filtering the collected information using natural language processing technology, means for evaluating the credibility of the collected information using a reliability evaluation algorithm and calculating a reliability score, means for automatically displaying information and generating an aggregator site based on the reliability score, means for periodically updating the aggregator site to reflect the latest information, and means for analyzing user sentiment and dynamically adjusting the display format of the information based on the data, thereby improving the quality of the collected information and optimizing the user experience.

[0257] The "Internet" is a collection of globally connected computer networks that enable the exchange of data and the viewing of information.

[0258] "Sources" refer to media such as websites and social media that provide specific information.

[0259] "Natural language processing technology" refers to the technology used to process and analyze human language using a computer, and is used for text analysis and document classification.

[0260] A "category" is a unit of classification for grouping similar things together, and is a criterion for dividing information into specific groups.

[0261] "Filtering" refers to the process of selecting and removing information based on specific criteria.

[0262] A "trustworthiness assessment algorithm" refers to a set of methods and formulas for calculating and assessing the reliability of information sources or the information itself.

[0263] A "trust score" is a number calculated as part of an evaluation and is an indicator of the reliability of the information or source.

[0264] An "aggregator site" is a website that aggregates a large amount of information in one place and provides it in a format that is easy for users to view.

[0265] "Update" is the process of rewriting existing data or information to the latest version.

[0266] "Emotion analysis" is a technology for estimating and evaluating a user's emotional state, and is primarily based on behavioral and interaction data.

[0267] "Dynamic adjustment" refers to changing the display format or content of information in real time or according to the situation at hand.

[0268] This invention is a system that efficiently collects, classifies, and evaluates election-related information, provides it to voters in an easy-to-understand manner, and recognizes the user's emotions and dynamically adjusts the way the information is presented.

[0269] First, the server collects election-related information from multiple sources on the Internet. To do this, it uses Python scraping modules (e.g., BeautifulSoup or Scrapy) to extract text and metadata from specified URLs and social media hashtags. The collected data is temporarily stored in a database (e.g., MySQL).

[0270] The server then analyzes the collected information using natural language processing techniques (e.g., NLTK or spaCy). The text data is tokenized, and the keywords and content of each piece of information are extracted. This allows the information to be automatically classified into categories such as political ideology, election campaign content, and gossip. It also filters out redundancies and noise, and only useful information is retained.

[0271] The server then uses a credibility assessment algorithm to evaluate the credibility of the collected information. The algorithm refers to the past evaluation history of the data source and calculates a credibility score for the source. Information with a credibility score below a certain level is filtered out, and only information with a high credibility score is advanced to the next step.

[0272] After sorting and evaluating the credibility of the information, the server generates a website. This website is built using a web framework (e.g., Django or Flask) and dynamically generates a profile page for each candidate. The profile page displays the latest information by category, such as political ideology, election campaign details, policy proposals, and gossip.

[0273] In addition, the server periodically re-runs the crawling process to retrieve new information, which is then added to the database, and old information is automatically archived, ensuring that the aggregation site always reflects the latest information.

[0274] Users can access the aggregation site using a web browser on their smartphone or PC to view the latest information on candidates and categories they are interested in. They can also set up update notifications to receive email notifications when new information is added.

[0275] The server also runs an emotion engine to recognize the user's emotions. This engine analyzes the user's click history and browsing time, and uses an emotion analysis algorithm (e.g., Sentiment Analysis API) to estimate the user's emotional state. Based on this, the server dynamically adjusts the information display format. For example, if the user is feeling stressed, the server can simplify the displayed information.

[0276] For example, the server collects information related to "Election 2023" at 1:00 AM and 1:00 PM. It retrieves the latest news about candidates from news portals and collects posts using the hashtag "Election 2023" from social media. It then uses NLP technology to analyze the data and classify it into categories.

[0277] An example of a prompt for a generative AI model is shown below.

[0278] "Describe a system that collects election updates, rates and categorizes them for credibility, and generates an aggregator. It uses sentiment analysis to dynamically adjust the presentation of information based on the information the user is viewing."

[0279] By inputting this prompt sentence into a generative AI model, the processing content of the above system can be automatically written down.

[0280] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0281] Step 1:

[0282] Information gathering

[0283] The server is configured in advance with the websites and social media hashtags to be monitored. At the specified times (e.g., 1:00 AM and 1:00 PM), it uses Python to call a scraping module (e.g., BeautifulSoup or Scrapy) to extract text and metadata from the specified URLs and hashtags. The collected data is temporarily stored in a MySQL database. The input is the URLs and hashtags to be monitored, and the output is the collected text data and metadata.

[0284] Step 2:

[0285] Data Classification

[0286] The server analyzes the collected information using natural language processing technology (e.g., NLTK or spaCy). Specifically, it tokenizes the text data and extracts the keywords and content of each piece of information. This automatically classifies the information into categories such as political ideology, election campaign content, and gossip. It also filters out duplication and noise. The input is the collected text data and metadata, and the output is data classified by category.

[0287] Step 3:

[0288] Credibility assessment

[0289] The server uses a reliability evaluation algorithm to evaluate the credibility of the collected information. It refers to the evaluation history of past data sources and calculates the reliability score of the information source. As a result, information with a reliability score below a certain level is filtered out, and only information with a high reliability is advanced to the next step. The input is data classified by category, and the output is data with a reliability score.

[0290] Step 4:

[0291] Aggregate site generation

[0292] The server generates an aggregator site based on the information that has been organized and credibility-evaluated. Using a web framework (e.g., Django or Flask), it dynamically generates a profile page for each candidate. The page displays the latest information by category, such as political ideology, election campaign details, policy proposals, and gossip. The input is data with a credibility score, and the output is the aggregator site HTML page.

[0293] Step 5:

[0294] automatic update

[0295] The server periodically retrieves new information according to a specified schedule and updates the site content. It re-runs the crawling process at regular intervals to retrieve new information and add it to the database. Old information is automatically archived. The input is the latest collected information, and the output is the updated aggregated site.

[0296] Step 6:

[0297] User Access and Notifications

[0298] Users can access the aggregation site using a browser on their device (smartphone or PC) and view the latest information on candidates and categories they are interested in. They can also set up update notifications and receive email notifications when new information is added. The input is the user's access request and notification settings, and the output is the latest information displayed and the notification email.

[0299] Step 7:

[0300] Emotion Analysis

[0301] The server runs an emotion engine to recognize user emotions. It analyzes click history and browsing time, and uses emotion analysis algorithms (e.g., Sentiment Analysis API) to estimate the user's emotional state. The input is the user's operation log and interaction data, and the output is emotion data.

[0302] Step 8:

[0303] Dynamic display adjustment

[0304] The server dynamically adjusts the display format of information based on data obtained from the emotion engine. For example, if the user is feeling stressed, the information can be reorganized to be simpler. It is also possible to prioritize the display of information about specific candidates based on their level of interest. The input is emotion data and data with confidence scores, and the output is information in an adjusted display format.

[0305] (Application example 2)

[0306] 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."

[0307] In addition to efficiently collecting, classifying, and evaluating election information and providing it to voters in an easy-to-understand manner, there is a need to provide more appropriate information to real-world customers and improve their experience by recognizing user emotions and dynamically adjusting the way information is presented. In particular, there is a lack of technology that enables store staff to respond to customers quickly and accurately. Therefore, it is necessary to develop a new system based on election information collection systems that can provide information according to the customer's emotional state.

[0308] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting election-related information from multiple information sources on the Internet; means for categorizing and filtering the collected information; means for evaluating the credibility of the collected information using a reliability evaluation algorithm and calculating a reliability score; means for automatically displaying information and generating a summary website based on the reliability score; means for periodically updating the summary website to reflect the latest information; means for recognizing user emotions and dynamically adjusting the display format of information; and means for displaying information about real-world customers on staff terminals and providing information based on the customer's emotional state. This not only enables efficient collection and provision of election information, but also enables provision of appropriate information tailored to the situation to real-world customers, thereby improving the customer experience.

[0309] "Election information" is information about election campaigns, candidates, election results, policy proposals, campaign promises, and news and rumors related to elections.

[0310] "Multiple sources on the Internet" refers to various types of information sources published on the Internet, such as news sites, social media, blogs, forums, and portal sites.

[0311] "Means of collection" refers to technology that automatically collects information on the Internet using web crawlers and APIs.

[0312] "Means of categorizing and filtering" refers to technology that uses natural language processing and keyword extraction algorithms to classify collected information into categories such as political ideology, election campaign details, and gossip information, and eliminates unnecessary data.

[0313] A "trustworthiness evaluation algorithm" is an algorithm that calculates the reliability of collected information based on evaluation indicators such as the reliability of the information source and past evaluation history.

[0314] The "means for evaluating credibility and calculating a trust score" is a technology that uses a trust evaluation algorithm to calculate a trust score for each piece of collected information and evaluate its credibility.

[0315] An "omatome site" is a website that organizes collected election information and integrates it for easy access by users.

[0316] The "means for generating an aggregate site" is a technology for constructing a website that can be viewed by users based on information that has undergone an evaluation of its reliability.

[0317] "Means of periodic updating to reflect the latest information" refers to technology that recollects information at specified intervals to keep the content of the website up to date.

[0318] "Means for recognizing user emotions and dynamically adjusting the display format of information" is a technology that estimates the user's emotional state from their interactions and facial expressions, and changes the way information is presented based on the results.

[0319] "Information about real-world customers" refers to information about customers' purchasing history, interests, and behavior when visiting a physical store.

[0320] "Means of displaying information on staff devices and providing information based on the emotional state of the customer" refers to technology that allows staff to refer to customer information in real time using, for example, smart glasses or a head-mounted display, and present appropriate information using emotion recognition technology.

[0321] The system program required to implement this invention includes the steps of data collection, classification, evaluation, and display. Each module of this system and its function will be described below.

[0322] Information Collection Module

[0323] The server automatically collects election-related information from multiple sources on the Internet. This process involves using web crawlers and APIs to retrieve information from specific news sites and social media sites. For example, it collects the latest news articles and social media posts related to the "2023 Election."

[0324] Data Classification Module

[0325] The server analyzes the collected information using natural language processing technology and categorizes it based on keywords and content. The collected data is classified into categories such as political ideology, election campaign details, and gossip information. It also filters out duplicate and noisy information, retaining only the more useful information. For example, if the same news is obtained from multiple sources, the data from the most reliable source is used.

[0326] Reliability Evaluation Module

[0327] The server evaluates the credibility of the collected information using a credibility evaluation algorithm. This algorithm calculates a credibility score based on the source's credibility and past evaluation history. Information with a credibility score below a certain level is filtered out, and only highly credible information is advanced to the next step. For example, if a particular news site has provided credible information in the past, information from that site will be given a high credibility score.

[0328] Aggregation site generation module

[0329] The server generates a website based on the information after the reliability evaluation. This website has a profile page for each candidate, displaying the latest information by category, such as political ideology, election campaign details, policy proposals, and gossip. For example, Candidate A's page will have a section displaying recent policy proposals and information about election campaign events.

[0330] Auto Update Module

[0331] The server automatically retrieves new information according to a specified schedule and periodically updates the content of the aggregation site. This ensures that the information on the site is always up to date. For example, the server updates the site with new information after crawling twice a day, and automatically archives old information.

[0332] User Access and Notification Module

[0333] Users access the aggregation site from their devices (smartphones or PCs) to view the latest information on candidates and categories of interest. They can also set up update notifications for specific candidates. This allows users to receive email notifications when new information is added. For example, a user can check the latest developments of candidate A on their smartphone and set up email notifications when new information is added.

[0334] Emotion Engine Module

[0335] The server is equipped with an emotion engine to recognize the user's emotions. This engine analyzes the user's emotions based on the information the user is viewing and their interaction patterns. For example, the server analyzes the user's click history and browsing time to estimate their emotional state, such as their interests and stress level.

[0336] Dynamic Display Adjustment Module

[0337] The server dynamically adjusts the display format of information based on the emotional data obtained from the emotion engine. For example, if the user is feeling stressed, the displayed information is simplified. It also prioritizes the display of information about specific candidates based on the results of emotion analysis. For example, if the server determines that the user is interested in candidate B, it prioritizes displaying information about candidate B on the top page.

[0338] Improving real-world customer experiences

[0339] In addition to the above modules, the system also uses smart glasses and head-mounted displays to provide effective information to customers in the real world. Staff use these devices to provide appropriate information in real time based on the customer's emotional state. For example, store staff can wear smart glasses to suggest products based on a customer's purchasing history and interests, or provide simple information when a customer is feeling stressed.

[0340] Prompt Sentence Examples

[0341] "Imagine an AI support system that provides the latest campaign information and dynamically displays information based on the customer's emotions. For example, if the customer is stressed, it might only display simple information."

[0342] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0343] Step 1:

[0344] The server collects election-related information from multiple sources on the Internet. As input, it receives a list of specified news sites and social media hashtags. The server uses a web crawler or API to crawl these sources, collects election-related information, and temporarily stores it in storage. The output is the collected raw data.

[0345] Step 2:

[0346] The server analyzes the collected information and uses a data classification module to classify and filter it by category. It receives the collected raw data as input. It uses natural language processing technology to extract keywords and content from the information and classify it into categories such as political ideology, election campaign details, and gossip information. It then filters out duplicate information and noise data, organizing only useful information. The output is organized data categorized by category.

[0347] Step 3:

[0348] The server uses a trust evaluation module to evaluate the credibility of the collected information. It receives the organized data as input. The trust evaluation algorithm calculates a trust score based on the reliability of the source and its past evaluation history. Information with a trust score below a certain level is filtered out, and only highly reliable information is advanced to the next step. The output is data with a trust score.

[0349] Step 4:

[0350] The server uses an aggregator module to generate an aggregator site based on the information that has undergone the reliability evaluation. It receives the data with the reliability scores as input. This creates a profile page for each candidate, displaying the latest information by category, such as political ideology, election campaign details, policy proposals, and gossip information. The output is the aggregator site's HTML / CSS files.

[0351] Step 5:

[0352] The server uses an automatic update module to periodically retrieve new information on a specified schedule and update the content of the aggregation site. It receives new collected data as input, ensuring that the information on the site is always up-to-date. Old information is archived. The output is the updated aggregation site content.

[0353] Step 6:

[0354] Users access the aggregation site from their devices (smartphones or PCs) and browse the latest information about candidates and categories of interest. The system receives the user's access request as input. The user can also set up update notifications for specific candidates. This way, users can receive email notifications when new information is added. The system outputs the user's browsing history and notification settings data.

[0355] Step 7:

[0356] The server uses an emotion engine module to recognize the user's emotions. It receives the user's interaction data (click history, browsing time, etc.) as input. The emotion engine analyzes this data and estimates the user's emotional state (interests, stress level, etc.). The output is the user's emotional state data.

[0357] Step 8:

[0358] The server uses a dynamic display adjustment module to dynamically adjust the display format of information based on the emotional data obtained from the emotion engine. It receives the user's emotional state data as input. For example, if the user is feeling stressed, the displayed information is simplified. If it is determined that the user is interested in a particular candidate, information about that candidate is displayed preferentially. The output is the adjusted display content.

[0359] Step 9:

[0360] Information about real-world customers is displayed on staff devices (smart glasses or head-mounted displays), and information is provided based on the customer's emotional state. The input is real-time customer data received by the device worn by the staff, such as purchase history and interests. The server analyzes this data and displays the most appropriate information on the device. For example, if a customer is feeling emotionally stressed, the information displayed can be simplified to increase their desire to purchase. The output is customer response information displayed on the staff device.

[0361] 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.

[0362] 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.

[0363] 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.

[0364] [Second embodiment]

[0365] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0366] 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.

[0367] 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).

[0368] 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.

[0369] 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.

[0370] 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).

[0371] 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.

[0372] 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.

[0373] 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.

[0374] 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.

[0375] 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.

[0376] 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."

[0377] This invention is a system that efficiently collects, classifies, and evaluates election-related information and provides it to voters in an easy-to-understand manner. The program processing of this system is explained below in natural language.

[0378] Information Collection Module

[0379] The server collects election-related information from news websites, blogs, social media, and other sources on the Internet at specific times each day. It pre-sets the websites and hashtags it monitors and crawls them all. For example, the server crawls news sites based on a pre-set URL list at 1:00 AM and 1:00 PM to collect election-related articles. It also collects social media posts using specific hashtags (e.g., "election 2023").

[0380] Data Reduction Module

[0381] The server analyzes the collected information and classifies it by category (political ideology, election campaign content, gossip, etc.). It uses natural language processing (NLP) technology to extract keywords and content from each piece of information and automatically classify it. It also filters out duplication and noise, leaving only useful information. For example, if the same news is collected from multiple sources, the server will only retain the most reliable source.

[0382] Authenticity Assessment Module

[0383] The server calculates a trust score based on the reliability of the source and its past evaluation history to assess the credibility of the collected information. Using AI algorithms, the server checks the reliability and consistency of a specific source and assigns a trust score. For example, the server evaluates the trust score of a news website and the credibility of an article based on that, and filters out information with low credibility.

[0384] Aggregation site generation module

[0385] The server generates a website based on the information that has been organized and credibility-evaluated. This website has a profile page for each candidate, and the latest information is displayed in categories such as election campaign details, policy proposals, and gossip. For example, the server creates a section on Candidate A's page that displays the latest policy proposals and information on election campaign events.

[0386] Auto Update Module

[0387] The server periodically retrieves new information and automatically updates the aggregation site. This ensures that the information on the site is always up to date. For example, after crawling twice a day, the server updates the aggregation site with new information and automatically archives old information.

[0388] User Access Module

[0389] Users can access the aggregation site from their devices (smartphones or PCs) and view the latest information on each candidate and category. They can also set up email notifications for updates on specific candidates. For example, a user can check the latest developments of candidate A on their smartphone and set up notifications to be sent by email when new information is added.

[0390] By combining the above modules, this invention can realize a system that properly collects, classifies, and evaluates information related to elections, and provides voters with reliable information.

[0391] The processing flow will be explained below.

[0392] Step 1: Gather information

[0393] The server loads a list of websites, news sources, and social media hashtags to monitor.

[0394] The server crawls monitored sites at designated times (for example, 1:00 AM and 1:00 PM) to collect new articles and posts related to the election.

[0395] The server temporarily stores the collected data in storage.

[0396] Step 2: Data Classification

[0397] The server analyzes the collected information and uses natural language processing (NLP) technology to extract keywords and content from each piece of information.

[0398] Based on the extracted keywords, the server classifies the information into categories (political ideology, election campaign content, gossip, etc.).

[0399] The server filters out redundant information and noise, leaving only the useful information.

[0400] Step 3: Credibility assessment

[0401] The server uses a credibility assessment algorithm to assess the authenticity of the collected information.

[0402] The server calculates a trust score based on the reliability of the source and its past rating history.

[0403] The server filters out information with a reliability score below a certain level, and only information with a high reliability score proceeds to the next step.

[0404] Step 4: Generate a website

[0405] The server generates a summary site based on the information that has been organized and evaluated for credibility.

[0406] The server creates a profile page for each candidate, displaying the latest information in categories such as political ideology, election activities, policy proposals, and gossip.

[0407] The server optimizes the site design for user accessibility.

[0408] Step 5: Automatic Updates

[0409] The server retrieves new information on a specified schedule and periodically updates the content of the aggregation site.

[0410] The server automatically archives old information and reflects the latest information.

[0411] The server crawls twice a day and updates the site with new information in real time.

[0412] Step 6: User Access and Notification

[0413] Users access the aggregation site from their device (smartphone or PC) and view information on candidates and categories that interest them.

[0414] Users can set up update notifications for specific candidates.

[0415] The server will send email notifications based on the user's settings when new information is added.

[0416] Through these processing steps, the system can efficiently collect, classify, and evaluate election-related information, providing voters with reliable information.

[0417] Example 1

[0418] 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."

[0419] Election-related information is diverse and collected from a variety of sources. This information is not necessarily reliable, and there is a lot of duplication and noise, making it difficult for voters to obtain accurate and reliable information about elections. Furthermore, because the information is scattered, there is a lack of efficient ways to obtain the latest information about specific candidates. Furthermore, there is the problem that it is difficult to always obtain the latest information during election periods, when information is frequently updated.

[0420] 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.

[0421] In this invention, the server includes: means for collecting election-related information from multiple sources on the Internet; means for categorizing and filtering the collected information using natural language processing technology; means for evaluating the credibility of the collected information using a reliability evaluation algorithm that calculates a reliability score based on the reliability of the information source and its past evaluation history; means for automatically displaying the information based on the reliability score and generating a summary site including a profile page for each candidate; and means for periodically updating the summary site to reflect the latest information. This allows voters to efficiently obtain the latest, reliable election information on a single site.

[0422] "Multiple sources on the internet" refers to online platforms such as websites, blogs and social media platforms that are used to provide data about the election.

[0423] "Means of collection" refers to programs and algorithms for automatically obtaining information on the Internet, and is a system for crawling based on specific keywords or URL lists.

[0424] "Natural language processing technology" refers to the general technology for analyzing text data to understand its meaning and process information written in human language, extracting, classifying, and filtering content.

[0425] "Categorizing and filtering" refers to the process of separating collected information based on specific themes or topics, and removing redundancies and noise to retain only the useful information.

[0426] "Source credibility" is an assessment of how accurate and reliable the source of information has been in the past, and serves as a criterion for judging the credibility of information.

[0427] "Past evaluation history" refers to a record of evaluations of the reliability and source of previously collected information, and is data used to determine the reliability of current information.

[0428] A "trust score" is a numerical representation of the credibility of collected information or information sources, with a higher score indicating higher reliability.

[0429] A "trustworthiness evaluation algorithm" refers to a calculation method or program for calculating the reliability of information based on the reliability of the information source and past evaluation history.

[0430] An "aggregator site" is a website that displays collected and classified information in a centralized manner, and is a platform that provides each candidate with a profile page and the latest information.

[0431] "Regular updating means" means a mechanism for automatically updating the contents of a database or website to collect new information at set intervals and keep existing data up to date.

[0432] "Means for enabling access via a web browser" refers to a mechanism that allows a user to access the aggregation site via a web browser using a terminal connected to the Internet.

[0433] "Means for setting up update notifications" refers to an interface that allows users to set up notifications, such as by email, when new information is added about a specific candidate or category.

[0434] The present invention relates to a system that efficiently collects, classifies, and evaluates election-related information and provides it to voters in an easy-to-understand manner. This system consists of three main components: a server, a terminal, and a user. The hardware and software required to implement the present invention are described in detail below.

[0435] The server is an internet-connected computer that runs a program using the Python programming language and related libraries (BeautifulSoup, SpaCy, etc.). The server first collects election-related information from news websites, blogs, social media, etc. on the internet. For example, the server crawls news sites based on a set list of URLs at 1:00 AM and 1:00 PM, and also collects social media posts using a specific hashtag (e.g., "Election 2023").

[0436] The server then analyzes the collected information using natural language processing (NLP) technology and classifies it by category (political ideology, election campaign details, gossip, etc.). Specifically, it uses the SpaCy library to extract text features and then uses machine learning algorithms such as SVM (Support Vector Machine) to classify the information. It also filters out duplicate and noisy information, leaving only the useful information. For example, if the same news is collected from multiple sources, the server will only retain the most reliable source.

[0437] The server then evaluates the credibility of the collected information by referencing past evaluation history and external credibility score databases (e.g., Media Bias / Fact Check) to assess the trustworthiness of sources and articles, and then calculating a credibility score using an AI model. Information with low credibility is filtered out, and only information with high credibility is retained.

[0438] After sorting and evaluating the credibility of the information, the server generates an aggregate website. This website has a profile page for each candidate, with the latest information displayed in categories such as election activities, policy proposals, and gossip. For example, the server creates a section on Candidate A's page that displays the latest policy proposals and information on election campaign events. The aggregate website is built using the Django framework.

[0439] In addition, the server periodically retrieves new information and automatically updates the aggregation site, ensuring that the information on the site is always up to date. After crawling twice a day, the server updates the aggregation site with new information and automatically archives old information.

[0440] Users can access the website through a web browser on their device (smartphone or PC) and view the latest information about each candidate and category. They can also set up email notifications for updates about specific candidates. For example, a user can check the latest information about candidate A on their smartphone and set up notifications to be sent by email when new information is added.

[0441] Below are some example prompts to input to a generative AI model:

[0442] (Example of a prompt)

[0443] "Collect news articles about specific candidates, including their latest policy proposals and campaign events, and organize them by category. Also, rate the credibility of the information you collect and display only the most credible information."

[0444] As described above, the present invention realizes a system for providing information about elections efficiently and reliably.

[0445] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0446] Step 1: Gather information

[0447] The server will crawl election information from news websites, blogs and social media across the internet at 1:00 AM and 1:00 PM.

[0448] Input: A pre-defined list of URLs or a specific hashtag (e.g., Election 2023).

[0449] What it does: The server uses Python's BeautifulSoup library to parse HTML and extract news articles and social media posts, and it also uses the Twitter API to collect tweets containing specific hashtags.

[0450] Output: A text data list of news articles and social media posts about the election.

[0451] Step 2: Data analysis and classification

[0452] The server analyzes the collected information using natural language processing (NLP) technology and classifies it into categories.

[0453] Input: The text data list collected in step 1.

[0454] What it does: The server uses the SpaCy library to extract text features, and then uses SVM (Support Vector Machine) and other classification algorithms to classify the data into categories such as political ideology, campaign content, gossip, etc. It also filters out duplicates and noise.

[0455] Output: A list of text data sorted by category.

[0456] Step 3: Credibility assessment

[0457] The server calculates a trust score based on the reliability of the source and past evaluation history to evaluate the credibility of the collected information.

[0458] Input: The text data list classified in step 2.

[0459] Specific operation: The server refers to each source's domain name, past rating history, and an external trust score database, and calculates a trust score using an AI model (e.g., random forest or neural network).

[0460] Output: A list of text data with a confidence score for each piece of information.

[0461] Step 4: Generate a website

[0462] The server generates a summary site based on the information that has been organized and evaluated for credibility.

[0463] Input: A list of text data with confidence scores assigned in Step 3.

[0464] What it does: The server adds data to a website built using the Django framework, updates each candidate's profile page, and dynamically generates HTML templates to display the information.

[0465] Output: A website that aggregates the latest election information.

[0466] Step 5: Automatic Updates

[0467] The server periodically retrieves new information and automatically updates the aggregation site.

[0468] Input: Historical database and newly collected information.

[0469] What it does: The server sets up a Cron job to run the crawl twice a day, updating the database so that new information is added and old information is archived.

[0470] Output: A website that aggregates information and keeps it up to date.

[0471] Step 6: User Access

[0472] Users can access the aggregation site from their devices (smartphones or PCs) and view the latest information on each candidate and category.

[0473] Input: The user's access request.

[0474] What happens: A user accesses the site through a web browser and views a specific candidate or category page. The user also configures email notifications in their account settings page to receive notifications when new information is added.

[0475] Output: Latest election information available to the user, along with email notification settings.

[0476] (Application example 1)

[0477] 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."

[0478] There is a wide range of information related to elections, and the challenge is to centrally organize it while evaluating its credibility and reliability and provide it to voters. Furthermore, in order to immediately reflect the collected information in actual election activities and choices, it is necessary to provide the latest information in near real time. Furthermore, there are insufficient means of providing interactive election-related information in brick-and-mortar stores, and a system that allows users to easily access it is needed.

[0479] 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.

[0480] In this invention, the server includes: means for collecting election-related information from multiple sources on the Internet, including news websites, blogs, and social networking sites; means for categorizing and filtering the collected information; means for evaluating the credibility of the collected information using a reliability evaluation algorithm and calculating a reliability score; means for automatically displaying the information and generating a website aggregation based on the reliability score; means for periodically updating the website aggregation to reflect the latest information; and means for providing an interface that makes the information available via smartphones, tablets, and interactive display devices. This makes it possible to centrally manage collected election-related information in a reliable manner and provide it interactively in physical stores.

[0481] "Election information" refers to general information such as election campaigns, political ideas, candidate profiles, policy proposals, and related news and events.

[0482] "Multiple sources on the Internet" refers to multiple online platforms, including news websites, blogs, and social media, and has a mechanism for collecting information from these.

[0483] "Classification by category" is a process of organizing collected information by theme, such as political ideology, election campaign details, or gossip, making it easier for users to understand the information.

[0484] "Filtering" is the process of removing redundancy and noise from collected information and selecting only useful information.

[0485] A "trustworthiness evaluation algorithm" is a method for calculating the reliability of collected information based on the reliability of the information source and past evaluation history.

[0486] A "trust score" is a numerical representation of the reliability of a source of information and the content of the information, with a higher score indicating more trustworthy information.

[0487] An "Omatome Site" is a website that displays and provides organized, categorized, and evaluated election information in a centralized manner.

[0488] "Periodic updating" refers to a process of incorporating new information at regular intervals to keep the information up-to-date.

[0489] "Interface provision means" refers to mechanisms that make it easier for users to access information through smartphones, tablets, and interactive display devices.

[0490] To implement this invention, the following system is constructed. A server collects election-related information from news websites, blogs, social networking sites, etc. on the Internet at a specific time each day. Specifically, the server uses a crawling tool to collect information based on a pre-set URL list and hashtags.

[0491] Information Collection Module

[0492] The server uses the requests library and BeautifulSoup to collect information from news websites and blogs. Information from social media sites is collected using the corresponding APIs. For example, news sites are crawled at 1:00 AM and 1:00 PM every day to collect election-related articles and posts. This also includes social media posts with specific hashtags such as "Election 2023."

[0493] Data Reduction Module

[0494] The server analyzes the collected information and classifies it by category (political ideology, election campaign details, gossip, etc.). It uses NLP (natural language processing) technology to automatically categorize information by analyzing keywords and context. Specifically, it uses spaCy and BERT models to extract key keywords from documents and categorize them based on those keywords. Additionally, if the same news is collected from multiple sources, it eliminates duplicates and retains only the most reliable source.

[0495] Authenticity Assessment Module

[0496] The server evaluates the credibility of the collected information by calculating a trust score based on the reliability of the source and past evaluation history. It uses AI algorithms to check the reliability and consistency of a specific source and assign a trust score. The evaluation uses machine learning libraries such as Scikit-learn and TensorFlow.

[0497] Aggregation site generation module

[0498] The server then generates a website based on the information that has been organized and credibility-assessed. This website has a profile page for each candidate, with the latest information displayed in categories such as election activities, policy proposals, and gossip.

[0499] Auto Update Module

[0500] The server periodically retrieves new information and automatically updates the aggregation site. This ensures that the information on the site is always up to date. For example, after crawling twice a day, new information is updated on the aggregation site, and old information is automatically archived.

[0501] User Access Module

[0502] Users can access the website from their smartphones, tablets, and interactive display devices to view the latest information on each candidate and category. They can also opt to receive email updates about specific candidates, providing real-time access to the election information they need.

[0503] Specific examples

[0504] A specific example is the prompt "Aggregate, categorize, and rate the credibility of the latest news about Japan's 2023 elections."

[0505] Example prompt:

[0506] "Please compile the latest news about the 2023 Japanese election and categorize it into the following categories: 'Political ideology,' 'Election campaign content,' and 'Gossip.' Also, please rate the trustworthiness of each news source."

[0507] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0508] Step 1:

[0509] The server collects election-related information from news websites, blogs, social media, and other sources on the Internet at designated times.

[0510] Input: a specific time, a set list of URLs, a specific hashtag (e.g., election 2023).

[0511] How it works: The server uses the requests library and BeautifulSoup to crawl each URL and retrieve election-related articles and posts. It also collects information from social media sites using their corresponding APIs.

[0512] Output: Collected election-related information (articles, posts).

[0513] Step 2:

[0514] The server analyzes the information collected in step 1, classifies it by category (political ideology, election campaign content, gossip, etc.), and filters it.

[0515] Input: Collected election-related information.

[0516] How it works: The server uses NLP techniques such as spaCy and BERT models to extract keywords and key content from documents and automatically classify them into predefined categories, filtering out redundant and noisy information.

[0517] Output: Useful information sorted by category.

[0518] Step 3:

[0519] The server evaluates the credibility of the information classified in step 2 and calculates a trust score.

[0520] Input: Useful information sorted by category.

[0521] How it works: The server uses machine learning libraries such as Scikit-learn or TensorFlow to calculate a trust score based on the reliability of the source and its past rating history.

[0522] Output: Information with a confidence score.

[0523] Step 4:

[0524] The server generates an aggregate site based on the information that was assigned a trust score in step 3.

[0525] Input: Information with a confidence score.

[0526] How it works: The server generates profile pages for each candidate, creating pages that display the latest information by category, such as campaign activities, policy proposals, and gossip.

[0527] Output: Aggregate site (web page).

[0528] Step 5:

[0529] The server periodically retrieves new information and automatically updates the aggregation site.

[0530] Input: Newly collected election information (reprocessed from step 1).

[0531] What happens: The server re-runs steps 1 through 4 with the new information to keep the site up to date.

[0532] Output: A summary site that reflects the latest information.

[0533] Step 6:

[0534] Users access the aggregation site from their smartphones, tablets, and interactive display devices to view the latest information about each candidate and category.

[0535] Input: URL of the aggregation site.

[0536] How it works: A device (smartphone, tablet, etc.) connects to the website through a browser, allowing users to interactively view the latest election information. Users can also opt to receive email updates about specific candidates.

[0537] Output: Interactive election updates and email notification options.

[0538] 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.

[0539] This invention is a system that efficiently collects, classifies, and evaluates election-related information, provides it to voters in an easy-to-understand manner, and recognizes the user's emotions and dynamically adjusts the way the information is presented. Below, we will explain the program processing of this system in natural language.

[0540] Information Collection Module

[0541] The server pre-configures websites and social media hashtags to monitor, crawls them at designated times (e.g., 1:00 AM and 1:00 PM) to collect new election-related information, and temporarily stores the collected data. For example, the server collects articles and posts related to "Election 2023" from designated news portals and social media.

[0542] Data Classification Module

[0543] The server analyzes the collected information and uses natural language processing (NLP) technology to extract keywords and content from each piece of information. This allows the information to be automatically categorized into categories such as political ideology, election campaign content, and gossip. It also filters out duplication and noise, retaining only useful information. For example, if similar news is obtained from multiple sources, the server selects the most reliable source and deletes the rest.

[0544] Authenticity Assessment Module

[0545] The server evaluates the credibility of the collected information using a credibility evaluation algorithm. The algorithm calculates a credibility score based on the reliability of the source and its past evaluation history. Information with a credibility score below a certain level is filtered out, and only highly credible information is advanced to the next step. For example, the server evaluates the credibility score of news sites and eliminates articles with low credibility.

[0546] Aggregation site generation module

[0547] The server generates a website based on the information that has been organized and credibility-evaluated. This website has a profile page for each candidate, displaying the latest information by category, such as political ideology, election campaign details, policy proposals, and gossip. For example, the server creates a section on Candidate A's page that displays the latest policy proposals and election campaign event information.

[0548] Auto Update Module

[0549] The server retrieves new information according to a specified schedule and periodically updates the contents of the aggregation site. This ensures that the information on the site is always up to date. For example, the server updates the new information after crawling twice a day, and automatically archives old information.

[0550] User Access and Notification Module

[0551] Users access the aggregation site from their devices (smartphones or PCs) and view the latest information on candidates and categories of interest. They can also set up update notifications for specific candidates. This allows users to receive email notifications when new information is added. For example, a user can check the latest developments of candidate A on their smartphone and set up email notifications when new information is added.

[0552] Emotion Engine Module

[0553] The server is equipped with an emotion engine to recognize the user's emotions. This engine analyzes the user's emotions based on the information the user is viewing and their interaction patterns. For example, the server analyzes the user's click history and browsing time to estimate their emotional state, such as their interests and stress level.

[0554] Dynamic Display Adjustment Module

[0555] The server dynamically adjusts the display format of information based on the emotional data obtained from the emotion engine. For example, if the user is feeling stressed, the displayed information is simplified. It also prioritizes the display of information about specific candidates based on the results of emotion analysis. For example, if the server determines that the user is interested in candidate B, it prioritizes displaying information about candidate B on the top page.

[0556] By combining the above modules, the present invention can realize a system that not only provides information but also dynamically presents information taking into account the emotional state of the user.

[0557] The processing flow will be explained below.

[0558] Step 1: Gather information

[0559] The server loads a list of websites, news sources, and social media hashtags to monitor.

[0560] The server crawls these sources at designated times (e.g., 1:00 AM and 1:00 PM) to collect election-related information.

[0561] The server temporarily stores the collected information in storage.

[0562] Step 2: Data Classification

[0563] The server analyzes the collected information and extracts keywords and content using natural language processing (NLP) technology.

[0564] Based on the extracted keywords, the server classifies the information into categories (political ideology, election campaign content, gossip, etc.).

[0565] The server filters out redundant information and noise, and keeps only the useful information.

[0566] Step 3: Credibility assessment

[0567] The server uses a credibility assessment algorithm to assess the authenticity of the collected information.

[0568] The server calculates a trust score based on the reliability of the source and its past rating history.

[0569] The server filters out information with a reliability score below a certain level, and only information with a high reliability score proceeds to the next step.

[0570] Step 4: Generate a website

[0571] The server generates a summary site based on the information that has been organized and evaluated for credibility.

[0572] The server creates a profile page for each candidate, displaying the latest information by category, such as political ideology, election campaign details, policy proposals, and gossip.

[0573] The server optimizes the site design for user accessibility.

[0574] Step 5: Automatic Updates

[0575] The server retrieves new information on a specified schedule and periodically updates the content of the aggregation site.

[0576] The server automatically archives old information and reflects the latest information.

[0577] The server crawls twice a day and updates the site with new information in real time.

[0578] Step 6: User Access and Notification

[0579] Users access the aggregation site from their device (smartphone or PC) and view information on candidates and categories that interest them.

[0580] Users can set up update notifications for specific candidates.

[0581] The server will send email notifications when new information is added based on the user's notification settings.

[0582] Step 7: Emotion Recognition

[0583] The server provides an emotion engine for recognizing the user's emotions.

[0584] The server collects user interaction patterns such as click history, viewing time, and mouse movements.

[0585] The server analyzes interaction patterns and estimates the user's emotional state (interests, concerns, stress, etc.).

[0586] Step 8: Dynamic display adjustment

[0587] The server dynamically adjusts the presentation of information based on data from the emotion engine.

[0588] The server simplifies the information displayed when the user is stressed.

[0589] Based on the results of the sentiment analysis, the server prioritizes displaying information about specific candidates.

[0590] For example, if the user shows a strong interest in candidate A, the server places information about candidate A in a prominent position on the top page.

[0591] Through these steps, the system can efficiently collect information about elections, evaluate its reliability, and present information according to the user's emotional state.

[0592] Example 2

[0593] 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."

[0594] Conventional election information systems have problems with the quality of information provided to users due to inefficient collection, classification, and reliability evaluation of information. Furthermore, they lack the ability to dynamically adjust information display according to user emotions, resulting in a suboptimal user experience.

[0595] 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.

[0596] In this invention, the server includes means for collecting election-related information from multiple sources on the Internet, means for categorizing and filtering the collected information using natural language processing technology, means for evaluating the credibility of the collected information using a reliability evaluation algorithm and calculating a reliability score, means for automatically displaying information and generating an aggregator site based on the reliability score, means for periodically updating the aggregator site to reflect the latest information, and means for analyzing user sentiment and dynamically adjusting the display format of the information based on the data, thereby improving the quality of the collected information and optimizing the user experience.

[0597] The "Internet" is a collection of globally connected computer networks that enable the exchange of data and the viewing of information.

[0598] "Sources" refer to media such as websites and social media that provide specific information.

[0599] "Natural language processing technology" refers to the technology used to process and analyze human language using a computer, and is used for text analysis and document classification.

[0600] A "category" is a unit of classification for grouping similar things together, and is a criterion for dividing information into specific groups.

[0601] "Filtering" refers to the process of selecting and removing information based on specific criteria.

[0602] A "trustworthiness assessment algorithm" refers to a set of methods and formulas for calculating and assessing the reliability of information sources or the information itself.

[0603] A "trust score" is a number calculated as part of an evaluation and is an indicator of the reliability of the information or source.

[0604] An "aggregator site" is a website that aggregates a large amount of information in one place and provides it in a format that is easy for users to view.

[0605] "Update" is the process of rewriting existing data or information to the latest version.

[0606] "Emotion analysis" is a technology for estimating and evaluating a user's emotional state, and is primarily based on behavioral and interaction data.

[0607] "Dynamic adjustment" refers to changing the display format or content of information in real time or according to the situation at hand.

[0608] This invention is a system that efficiently collects, classifies, and evaluates election-related information, provides it to voters in an easy-to-understand manner, and recognizes the user's emotions and dynamically adjusts the way the information is presented.

[0609] First, the server collects election-related information from multiple sources on the Internet. To do this, it uses Python scraping modules (e.g., BeautifulSoup or Scrapy) to extract text and metadata from specified URLs and social media hashtags. The collected data is temporarily stored in a database (e.g., MySQL).

[0610] The server then analyzes the collected information using natural language processing techniques (e.g., NLTK or spaCy). The text data is tokenized, and the keywords and content of each piece of information are extracted. This allows the information to be automatically classified into categories such as political ideology, election campaign content, and gossip. It also filters out redundancies and noise, and only useful information is retained.

[0611] The server then uses a credibility assessment algorithm to evaluate the credibility of the collected information. The algorithm refers to the past evaluation history of the data source and calculates a credibility score for the source. Information with a credibility score below a certain level is filtered out, and only information with a high credibility score is advanced to the next step.

[0612] After sorting and evaluating the credibility of the information, the server generates a website. This website is built using a web framework (e.g., Django or Flask) and dynamically generates a profile page for each candidate. The profile page displays the latest information by category, such as political ideology, election campaign details, policy proposals, and gossip.

[0613] In addition, the server periodically re-runs the crawling process to retrieve new information, which is then added to the database, and old information is automatically archived, ensuring that the aggregation site always reflects the latest information.

[0614] Users can access the aggregation site using a web browser on their smartphone or PC to view the latest information on candidates and categories they are interested in. They can also set up update notifications to receive email notifications when new information is added.

[0615] The server also runs an emotion engine to recognize the user's emotions. This engine analyzes the user's click history and browsing time, and uses an emotion analysis algorithm (e.g., Sentiment Analysis API) to estimate the user's emotional state. Based on this, the server dynamically adjusts the information display format. For example, if the user is feeling stressed, the server can simplify the displayed information.

[0616] For example, the server collects information related to "Election 2023" at 1:00 AM and 1:00 PM. It retrieves the latest news about candidates from news portals and collects posts using the hashtag "Election 2023" from social media. It then uses NLP technology to analyze the data and classify it into categories.

[0617] An example of a prompt for a generative AI model is shown below.

[0618] "Describe a system that collects election updates, rates and categorizes them for credibility, and generates an aggregator. It uses sentiment analysis to dynamically adjust the presentation of information based on the information the user is viewing."

[0619] By inputting this prompt sentence into a generative AI model, the processing content of the above system can be automatically written down.

[0620] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0621] Step 1:

[0622] Information gathering

[0623] The server is configured in advance with the websites and social media hashtags to be monitored. At the specified times (e.g., 1:00 AM and 1:00 PM), it uses Python to call a scraping module (e.g., BeautifulSoup or Scrapy) to extract text and metadata from the specified URLs and hashtags. The collected data is temporarily stored in a MySQL database. The input is the URLs and hashtags to be monitored, and the output is the collected text data and metadata.

[0624] Step 2:

[0625] Data Classification

[0626] The server analyzes the collected information using natural language processing technology (e.g., NLTK or spaCy). Specifically, it tokenizes the text data and extracts the keywords and content of each piece of information. This automatically classifies the information into categories such as political ideology, election campaign content, and gossip. It also filters out duplication and noise. The input is the collected text data and metadata, and the output is data classified by category.

[0627] Step 3:

[0628] Credibility assessment

[0629] The server uses a reliability evaluation algorithm to evaluate the credibility of the collected information. It refers to the evaluation history of past data sources and calculates the reliability score of the information source. As a result, information with a reliability score below a certain level is filtered out, and only information with a high reliability is advanced to the next step. The input is data classified by category, and the output is data with a reliability score.

[0630] Step 4:

[0631] Aggregate site generation

[0632] The server generates an aggregator site based on the information that has been organized and credibility-evaluated. Using a web framework (e.g., Django or Flask), it dynamically generates a profile page for each candidate. The page displays the latest information by category, such as political ideology, election campaign details, policy proposals, and gossip. The input is data with a credibility score, and the output is the aggregator site HTML page.

[0633] Step 5:

[0634] automatic update

[0635] The server periodically retrieves new information according to a specified schedule and updates the site content. It re-runs the crawling process at regular intervals to retrieve new information and add it to the database. Old information is automatically archived. The input is the latest collected information, and the output is the updated aggregated site.

[0636] Step 6:

[0637] User Access and Notifications

[0638] Users can access the aggregation site using a browser on their device (smartphone or PC) and view the latest information on candidates and categories they are interested in. They can also set up update notifications and receive email notifications when new information is added. The input is the user's access request and notification settings, and the output is the latest information displayed and the notification email.

[0639] Step 7:

[0640] Emotion Analysis

[0641] The server runs an emotion engine to recognize user emotions. It analyzes click history and browsing time, and uses emotion analysis algorithms (e.g., Sentiment Analysis API) to estimate the user's emotional state. The input is the user's operation log and interaction data, and the output is emotion data.

[0642] Step 8:

[0643] Dynamic display adjustment

[0644] The server dynamically adjusts the display format of information based on data obtained from the emotion engine. For example, if the user is feeling stressed, the information can be reorganized to be simpler. It is also possible to prioritize the display of information about specific candidates based on their level of interest. The input is emotion data and data with confidence scores, and the output is information in an adjusted display format.

[0645] (Application example 2)

[0646] 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."

[0647] In addition to efficiently collecting, classifying, and evaluating election information and providing it to voters in an easy-to-understand manner, there is a need to provide more appropriate information to real-world customers and improve their experience by recognizing user emotions and dynamically adjusting the way information is presented. In particular, there is a lack of technology that enables store staff to respond to customers quickly and accurately. Therefore, it is necessary to develop a new system based on election information collection systems that can provide information according to the customer's emotional state.

[0648] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting election-related information from multiple information sources on the Internet; means for categorizing and filtering the collected information; means for evaluating the credibility of the collected information using a reliability evaluation algorithm and calculating a reliability score; means for automatically displaying information and generating a summary website based on the reliability score; means for periodically updating the summary website to reflect the latest information; means for recognizing user emotions and dynamically adjusting the display format of information; and means for displaying information about real-world customers on staff terminals and providing information based on the customer's emotional state. This not only enables efficient collection and provision of election information, but also enables provision of appropriate information tailored to the situation to real-world customers, thereby improving the customer experience.

[0649] "Election information" is information about election campaigns, candidates, election results, policy proposals, campaign promises, and news and rumors related to elections.

[0650] "Multiple sources on the Internet" refers to various types of information sources published on the Internet, such as news sites, social media, blogs, forums, and portal sites.

[0651] "Means of collection" refers to technology that automatically collects information on the Internet using web crawlers and APIs.

[0652] "Means of categorizing and filtering" refers to technology that uses natural language processing and keyword extraction algorithms to classify collected information into categories such as political ideology, election campaign details, and gossip information, and eliminates unnecessary data.

[0653] A "trustworthiness evaluation algorithm" is an algorithm that calculates the reliability of collected information based on evaluation indicators such as the reliability of the information source and past evaluation history.

[0654] The "means for evaluating credibility and calculating a trust score" is a technology that uses a trust evaluation algorithm to calculate a trust score for each piece of collected information and evaluate its credibility.

[0655] An "omatome site" is a website that organizes collected election information and integrates it for easy access by users.

[0656] The "means for generating an aggregate site" is a technology for constructing a website that can be viewed by users based on information that has undergone an evaluation of its reliability.

[0657] "Means of periodic updating to reflect the latest information" refers to technology that recollects information at specified intervals to keep the content of the website up to date.

[0658] "Means for recognizing user emotions and dynamically adjusting the display format of information" is a technology that estimates the user's emotional state from their interactions and facial expressions, and changes the way information is presented based on the results.

[0659] "Information about real-world customers" refers to information about customers' purchasing history, interests, and behavior when visiting a physical store.

[0660] "Means of displaying information on staff devices and providing information based on the emotional state of the customer" refers to technology that allows staff to refer to customer information in real time using, for example, smart glasses or a head-mounted display, and present appropriate information using emotion recognition technology.

[0661] The system program required to implement this invention includes the steps of data collection, classification, evaluation, and display. Each module of this system and its function will be described below.

[0662] Information Collection Module

[0663] The server automatically collects election-related information from multiple sources on the Internet. This process involves using web crawlers and APIs to retrieve information from specific news sites and social media sites. For example, it collects the latest news articles and social media posts related to the "2023 Election."

[0664] Data Classification Module

[0665] The server analyzes the collected information using natural language processing technology and categorizes it based on keywords and content. The collected data is classified into categories such as political ideology, election campaign details, and gossip information. It also filters out duplicate and noisy information, retaining only the more useful information. For example, if the same news is obtained from multiple sources, the data from the most reliable source is used.

[0666] Reliability Evaluation Module

[0667] The server evaluates the credibility of the collected information using a credibility evaluation algorithm. This algorithm calculates a credibility score based on the source's credibility and past evaluation history. Information with a credibility score below a certain level is filtered out, and only highly credible information is advanced to the next step. For example, if a particular news site has provided credible information in the past, information from that site will be given a high credibility score.

[0668] Aggregation site generation module

[0669] The server generates a website based on the information after the reliability evaluation. This website has a profile page for each candidate, displaying the latest information by category, such as political ideology, election campaign details, policy proposals, and gossip. For example, Candidate A's page will have a section displaying recent policy proposals and information about election campaign events.

[0670] Auto Update Module

[0671] The server automatically retrieves new information according to a specified schedule and periodically updates the content of the aggregation site. This ensures that the information on the site is always up to date. For example, the server updates the site with new information after crawling twice a day, and automatically archives old information.

[0672] User Access and Notification Module

[0673] Users access the aggregation site from their devices (smartphones or PCs) to view the latest information on candidates and categories of interest. They can also set up update notifications for specific candidates. This allows users to receive email notifications when new information is added. For example, a user can check the latest developments of candidate A on their smartphone and set up email notifications when new information is added.

[0674] Emotion Engine Module

[0675] The server is equipped with an emotion engine to recognize the user's emotions. This engine analyzes the user's emotions based on the information the user is viewing and their interaction patterns. For example, the server analyzes the user's click history and browsing time to estimate their emotional state, such as their interests and stress level.

[0676] Dynamic Display Adjustment Module

[0677] The server dynamically adjusts the display format of information based on the emotional data obtained from the emotion engine. For example, if the user is feeling stressed, the displayed information is simplified. It also prioritizes the display of information about specific candidates based on the results of emotion analysis. For example, if the server determines that the user is interested in candidate B, it prioritizes displaying information about candidate B on the top page.

[0678] Improving real-world customer experiences

[0679] In addition to the above modules, the system also uses smart glasses and head-mounted displays to provide effective information to customers in the real world. Staff use these devices to provide appropriate information in real time based on the customer's emotional state. For example, store staff can wear smart glasses to suggest products based on a customer's purchasing history and interests, or provide simple information when a customer is feeling stressed.

[0680] Prompt Sentence Examples

[0681] "Imagine an AI support system that provides the latest campaign information and dynamically displays information based on the customer's emotions. For example, if the customer is stressed, it might only display simple information."

[0682] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0683] Step 1:

[0684] The server collects election-related information from multiple sources on the Internet. As input, it receives a list of specified news sites and social media hashtags. The server uses a web crawler or API to crawl these sources, collects election-related information, and temporarily stores it in storage. The output is the collected raw data.

[0685] Step 2:

[0686] The server analyzes the collected information and uses a data classification module to classify and filter it by category. It receives the collected raw data as input. It uses natural language processing technology to extract keywords and content from the information and classify it into categories such as political ideology, election campaign details, and gossip information. It then filters out duplicate information and noise data, organizing only useful information. The output is organized data categorized by category.

[0687] Step 3:

[0688] The server uses a trust evaluation module to evaluate the credibility of the collected information. It receives the organized data as input. The trust evaluation algorithm calculates a trust score based on the reliability of the source and its past evaluation history. Information with a trust score below a certain level is filtered out, and only highly reliable information is advanced to the next step. The output is data with a trust score.

[0689] Step 4:

[0690] The server uses an aggregator module to generate an aggregator site based on the information that has undergone the reliability evaluation. It receives the data with the reliability scores as input. This creates a profile page for each candidate, displaying the latest information by category, such as political ideology, election campaign details, policy proposals, and gossip information. The output is the aggregator site's HTML / CSS files.

[0691] Step 5:

[0692] The server uses an automatic update module to periodically retrieve new information on a specified schedule and update the content of the aggregation site. It receives new collected data as input, ensuring that the information on the site is always up-to-date. Old information is archived. The output is the updated aggregation site content.

[0693] Step 6:

[0694] Users access the aggregation site from their devices (smartphones or PCs) and browse the latest information about candidates and categories of interest. The system receives the user's access request as input. The user can also set up update notifications for specific candidates. This way, users can receive email notifications when new information is added. The system outputs the user's browsing history and notification settings data.

[0695] Step 7:

[0696] The server uses an emotion engine module to recognize the user's emotions. It receives the user's interaction data (click history, browsing time, etc.) as input. The emotion engine analyzes this data and estimates the user's emotional state (interests, stress level, etc.). The output is the user's emotional state data.

[0697] Step 8:

[0698] The server uses a dynamic display adjustment module to dynamically adjust the display format of information based on the emotional data obtained from the emotion engine. It receives the user's emotional state data as input. For example, if the user is feeling stressed, the displayed information is simplified. If it is determined that the user is interested in a particular candidate, information about that candidate is displayed preferentially. The output is the adjusted display content.

[0699] Step 9:

[0700] Information about real-world customers is displayed on staff devices (smart glasses or head-mounted displays), and information is provided based on the customer's emotional state. The input is real-time customer data received by the device worn by the staff, such as purchase history and interests. The server analyzes this data and displays the most appropriate information on the device. For example, if a customer is feeling emotionally stressed, the information displayed can be simplified to increase their desire to purchase. The output is customer response information displayed on the staff device.

[0701] 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.

[0702] 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.

[0703] 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.

[0704] [Third embodiment]

[0705] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0706] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0707] 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).

[0708] 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.

[0709] 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.

[0710] 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).

[0711] 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.

[0712] 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.

[0713] 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.

[0714] 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.

[0715] 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.

[0716] 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."

[0717] This invention is a system that efficiently collects, classifies, and evaluates election-related information and provides it to voters in an easy-to-understand manner. The program processing of this system is explained below in natural language.

[0718] Information Collection Module

[0719] The server collects election-related information from news websites, blogs, social media, and other sources on the Internet at specific times each day. It pre-sets the websites and hashtags it monitors and crawls them all. For example, the server crawls news sites based on a pre-set URL list at 1:00 AM and 1:00 PM to collect election-related articles. It also collects social media posts using specific hashtags (e.g., "election 2023").

[0720] Data Reduction Module

[0721] The server analyzes the collected information and classifies it by category (political ideology, election campaign content, gossip, etc.). It uses natural language processing (NLP) technology to extract keywords and content from each piece of information and automatically classify it. It also filters out duplication and noise, leaving only useful information. For example, if the same news is collected from multiple sources, the server will only retain the most reliable source.

[0722] Authenticity Assessment Module

[0723] The server calculates a trust score based on the reliability of the source and its past evaluation history to assess the credibility of the collected information. Using AI algorithms, the server checks the reliability and consistency of a specific source and assigns a trust score. For example, the server evaluates the trust score of a news website and the credibility of an article based on that, and filters out information with low credibility.

[0724] Aggregation site generation module

[0725] The server generates a website based on the information that has been organized and credibility-evaluated. This website has a profile page for each candidate, and the latest information is displayed in categories such as election campaign details, policy proposals, and gossip. For example, the server creates a section on Candidate A's page that displays the latest policy proposals and information on election campaign events.

[0726] Auto Update Module

[0727] The server periodically retrieves new information and automatically updates the aggregation site. This ensures that the information on the site is always up to date. For example, after crawling twice a day, the server updates the aggregation site with new information and automatically archives old information.

[0728] User Access Module

[0729] Users can access the aggregation site from their devices (smartphones or PCs) and view the latest information on each candidate and category. They can also set up email notifications for updates on specific candidates. For example, a user can check the latest developments of candidate A on their smartphone and set up notifications to be sent by email when new information is added.

[0730] By combining the above modules, this invention can realize a system that properly collects, classifies, and evaluates information related to elections, and provides voters with reliable information.

[0731] The processing flow will be explained below.

[0732] Step 1: Gather information

[0733] The server loads a list of websites, news sources, and social media hashtags to monitor.

[0734] The server crawls monitored sites at designated times (for example, 1:00 AM and 1:00 PM) to collect new articles and posts related to the election.

[0735] The server temporarily stores the collected data in storage.

[0736] Step 2: Data Classification

[0737] The server analyzes the collected information and uses natural language processing (NLP) technology to extract keywords and content from each piece of information.

[0738] Based on the extracted keywords, the server classifies the information into categories (political ideology, election campaign content, gossip, etc.).

[0739] The server filters out redundant information and noise, leaving only the useful information.

[0740] Step 3: Credibility assessment

[0741] The server uses a credibility assessment algorithm to assess the authenticity of the collected information.

[0742] The server calculates a trust score based on the reliability of the source and its past rating history.

[0743] The server filters out information with a reliability score below a certain level, and only information with a high reliability score proceeds to the next step.

[0744] Step 4: Generate a website

[0745] The server generates a summary site based on the information that has been organized and evaluated for credibility.

[0746] The server creates a profile page for each candidate, displaying the latest information in categories such as political ideology, election activities, policy proposals, and gossip.

[0747] The server optimizes the site design for user accessibility.

[0748] Step 5: Automatic Updates

[0749] The server retrieves new information on a specified schedule and periodically updates the content of the aggregation site.

[0750] The server automatically archives old information and reflects the latest information.

[0751] The server crawls twice a day and updates the site with new information in real time.

[0752] Step 6: User Access and Notification

[0753] Users access the aggregation site from their device (smartphone or PC) and view information on candidates and categories that interest them.

[0754] Users can set up update notifications for specific candidates.

[0755] The server will send email notifications based on the user's settings when new information is added.

[0756] Through these processing steps, the system can efficiently collect, classify, and evaluate election-related information, providing voters with reliable information.

[0757] Example 1

[0758] 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."

[0759] Election-related information is diverse and collected from a variety of sources. This information is not necessarily reliable, and there is a lot of duplication and noise, making it difficult for voters to obtain accurate and reliable information about elections. Furthermore, because the information is scattered, there is a lack of efficient ways to obtain the latest information about specific candidates. Furthermore, there is the problem that it is difficult to always obtain the latest information during election periods, when information is frequently updated.

[0760] 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.

[0761] In this invention, the server includes: means for collecting election-related information from multiple sources on the Internet; means for categorizing and filtering the collected information using natural language processing technology; means for evaluating the credibility of the collected information using a reliability evaluation algorithm that calculates a reliability score based on the reliability of the information source and its past evaluation history; means for automatically displaying the information based on the reliability score and generating a summary site including a profile page for each candidate; and means for periodically updating the summary site to reflect the latest information. This allows voters to efficiently obtain the latest, reliable election information on a single site.

[0762] "Multiple sources on the internet" refers to online platforms such as websites, blogs and social media platforms that are used to provide data about the election.

[0763] "Means of collection" refers to programs and algorithms for automatically obtaining information on the Internet, and is a system for crawling based on specific keywords or URL lists.

[0764] "Natural language processing technology" refers to the general technology for analyzing text data to understand its meaning and process information written in human language, extracting, classifying, and filtering content.

[0765] "Categorizing and filtering" refers to the process of separating collected information based on specific themes or topics, and removing redundancies and noise to retain only the useful information.

[0766] "Source credibility" is an assessment of how accurate and reliable the source of information has been in the past, and serves as a criterion for judging the credibility of information.

[0767] "Past evaluation history" refers to a record of evaluations of the reliability and source of previously collected information, and is data used to determine the reliability of current information.

[0768] A "trust score" is a numerical representation of the credibility of collected information or information sources, with a higher score indicating higher reliability.

[0769] A "trustworthiness evaluation algorithm" refers to a calculation method or program for calculating the reliability of information based on the reliability of the information source and past evaluation history.

[0770] An "aggregator site" is a website that displays collected and classified information in a centralized manner, and is a platform that provides each candidate with a profile page and the latest information.

[0771] "Regular updating means" means a mechanism for automatically updating the contents of a database or website to collect new information at set intervals and keep existing data up to date.

[0772] "Means for enabling access via a web browser" refers to a mechanism that allows a user to access the aggregation site via a web browser using a terminal connected to the Internet.

[0773] "Means for setting up update notifications" refers to an interface that allows users to set up notifications, such as by email, when new information is added about a specific candidate or category.

[0774] The present invention relates to a system that efficiently collects, classifies, and evaluates election-related information and provides it to voters in an easy-to-understand manner. This system consists of three main components: a server, a terminal, and a user. The hardware and software required to implement the present invention are described in detail below.

[0775] The server is an internet-connected computer that runs a program using the Python programming language and related libraries (BeautifulSoup, SpaCy, etc.). The server first collects election-related information from news websites, blogs, social media, etc. on the internet. For example, the server crawls news sites based on a set list of URLs at 1:00 AM and 1:00 PM, and also collects social media posts using a specific hashtag (e.g., "Election 2023").

[0776] The server then analyzes the collected information using natural language processing (NLP) technology and classifies it by category (political ideology, election campaign details, gossip, etc.). Specifically, it uses the SpaCy library to extract text features and then uses machine learning algorithms such as SVM (Support Vector Machine) to classify the information. It also filters out duplicate and noisy information, leaving only the useful information. For example, if the same news is collected from multiple sources, the server will only retain the most reliable source.

[0777] The server then evaluates the credibility of the collected information by referencing past evaluation history and external credibility score databases (e.g., Media Bias / Fact Check) to assess the trustworthiness of sources and articles, and then calculating a credibility score using an AI model. Information with low credibility is filtered out, and only information with high credibility is retained.

[0778] After sorting and evaluating the credibility of the information, the server generates an aggregate website. This website has a profile page for each candidate, with the latest information displayed in categories such as election activities, policy proposals, and gossip. For example, the server creates a section on Candidate A's page that displays the latest policy proposals and information on election campaign events. The aggregate website is built using the Django framework.

[0779] In addition, the server periodically retrieves new information and automatically updates the aggregation site, ensuring that the information on the site is always up to date. After crawling twice a day, the server updates the aggregation site with new information and automatically archives old information.

[0780] Users can access the website through a web browser on their device (smartphone or PC) and view the latest information about each candidate and category. They can also set up email notifications for updates about specific candidates. For example, a user can check the latest information about candidate A on their smartphone and set up notifications to be sent by email when new information is added.

[0781] Below are some example prompts to input to a generative AI model:

[0782] (Example of a prompt)

[0783] "Collect news articles about specific candidates, including their latest policy proposals and campaign events, and organize them by category. Also, rate the credibility of the information you collect and display only the most credible information."

[0784] As described above, the present invention realizes a system for providing information about elections efficiently and reliably.

[0785] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0786] Step 1: Gather information

[0787] The server will crawl election information from news websites, blogs and social media across the internet at 1:00 AM and 1:00 PM.

[0788] Input: A pre-defined list of URLs or a specific hashtag (e.g., Election 2023).

[0789] What it does: The server uses Python's BeautifulSoup library to parse HTML and extract news articles and social media posts, and it also uses the Twitter API to collect tweets containing specific hashtags.

[0790] Output: A text data list of news articles and social media posts about the election.

[0791] Step 2: Data analysis and classification

[0792] The server analyzes the collected information using natural language processing (NLP) technology and classifies it into categories.

[0793] Input: The text data list collected in step 1.

[0794] What it does: The server uses the SpaCy library to extract text features, and then uses SVM (Support Vector Machine) and other classification algorithms to classify the data into categories such as political ideology, campaign content, gossip, etc. It also filters out duplicates and noise.

[0795] Output: A list of text data sorted by category.

[0796] Step 3: Credibility assessment

[0797] The server calculates a trust score based on the reliability of the source and past evaluation history to evaluate the credibility of the collected information.

[0798] Input: The text data list classified in step 2.

[0799] Specific operation: The server refers to each source's domain name, past rating history, and an external trust score database, and calculates a trust score using an AI model (e.g., random forest or neural network).

[0800] Output: A list of text data with a confidence score for each piece of information.

[0801] Step 4: Generate a website

[0802] The server generates a summary site based on the information that has been organized and evaluated for credibility.

[0803] Input: A list of text data with confidence scores assigned in Step 3.

[0804] What it does: The server adds data to a website built using the Django framework, updates each candidate's profile page, and dynamically generates HTML templates to display the information.

[0805] Output: A website that aggregates the latest election information.

[0806] Step 5: Automatic Updates

[0807] The server periodically retrieves new information and automatically updates the aggregation site.

[0808] Input: Historical database and newly collected information.

[0809] What it does: The server sets up a Cron job to run the crawl twice a day, updating the database so that new information is added and old information is archived.

[0810] Output: A website that aggregates information and keeps it up to date.

[0811] Step 6: User Access

[0812] Users can access the aggregation site from their devices (smartphones or PCs) and view the latest information on each candidate and category.

[0813] Input: The user's access request.

[0814] What happens: A user accesses the site through a web browser and views a specific candidate or category page. The user also configures email notifications in their account settings page to receive notifications when new information is added.

[0815] Output: Latest election information available to the user, along with email notification settings.

[0816] (Application example 1)

[0817] 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."

[0818] There is a wide range of information related to elections, and the challenge is to centrally organize it while evaluating its credibility and reliability and provide it to voters. Furthermore, in order to immediately reflect the collected information in actual election activities and choices, it is necessary to provide the latest information in near real time. Furthermore, there are insufficient means of providing interactive election-related information in brick-and-mortar stores, and a system that allows users to easily access it is needed.

[0819] 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.

[0820] In this invention, the server includes: means for collecting election-related information from multiple sources on the Internet, including news websites, blogs, and social networking sites; means for categorizing and filtering the collected information; means for evaluating the credibility of the collected information using a reliability evaluation algorithm and calculating a reliability score; means for automatically displaying the information and generating a website aggregation based on the reliability score; means for periodically updating the website aggregation to reflect the latest information; and means for providing an interface that makes the information available via smartphones, tablets, and interactive display devices. This makes it possible to centrally manage collected election-related information in a reliable manner and provide it interactively in physical stores.

[0821] "Election information" refers to general information such as election campaigns, political ideas, candidate profiles, policy proposals, and related news and events.

[0822] "Multiple sources on the Internet" refers to multiple online platforms, including news websites, blogs, and social media, and has a mechanism for collecting information from these.

[0823] "Classification by category" is a process of organizing collected information by theme, such as political ideology, election campaign details, or gossip, making it easier for users to understand the information.

[0824] "Filtering" is the process of removing redundancy and noise from collected information and selecting only useful information.

[0825] A "trustworthiness evaluation algorithm" is a method for calculating the reliability of collected information based on the reliability of the information source and past evaluation history.

[0826] A "trust score" is a numerical representation of the reliability of a source of information and the content of the information, with a higher score indicating more trustworthy information.

[0827] An "Omatome Site" is a website that displays and provides organized, categorized, and evaluated election information in a centralized manner.

[0828] "Periodic updating" refers to a process of incorporating new information at regular intervals to keep the information up-to-date.

[0829] "Interface provision means" refers to mechanisms that make it easier for users to access information through smartphones, tablets, and interactive display devices.

[0830] To implement this invention, the following system is constructed. A server collects election-related information from news websites, blogs, social networking sites, etc. on the Internet at a specific time each day. Specifically, the server uses a crawling tool to collect information based on a pre-set URL list and hashtags.

[0831] Information Collection Module

[0832] The server uses the requests library and BeautifulSoup to collect information from news websites and blogs. Information from social media sites is collected using the corresponding APIs. For example, news sites are crawled at 1:00 AM and 1:00 PM every day to collect election-related articles and posts. This also includes social media posts with specific hashtags such as "Election 2023."

[0833] Data Reduction Module

[0834] The server analyzes the collected information and classifies it by category (political ideology, election campaign details, gossip, etc.). It uses NLP (natural language processing) technology to automatically categorize information by analyzing keywords and context. Specifically, it uses spaCy and BERT models to extract key keywords from documents and categorize them based on those keywords. Additionally, if the same news is collected from multiple sources, it eliminates duplicates and retains only the most reliable source.

[0835] Authenticity Assessment Module

[0836] The server evaluates the credibility of the collected information by calculating a trust score based on the reliability of the source and past evaluation history. It uses AI algorithms to check the reliability and consistency of a specific source and assign a trust score. The evaluation uses machine learning libraries such as Scikit-learn and TensorFlow.

[0837] Aggregation site generation module

[0838] The server then generates a website based on the information that has been organized and credibility-assessed. This website has a profile page for each candidate, with the latest information displayed in categories such as election activities, policy proposals, and gossip.

[0839] Auto Update Module

[0840] The server periodically retrieves new information and automatically updates the aggregation site. This ensures that the information on the site is always up to date. For example, after crawling twice a day, new information is updated on the aggregation site, and old information is automatically archived.

[0841] User Access Module

[0842] Users can access the website from their smartphones, tablets, and interactive display devices to view the latest information on each candidate and category. They can also opt to receive email updates about specific candidates, providing real-time access to the election information they need.

[0843] Specific examples

[0844] A specific example is the prompt "Aggregate, categorize, and rate the credibility of the latest news about Japan's 2023 elections."

[0845] Example prompt:

[0846] "Please compile the latest news about the 2023 Japanese election and categorize it into the following categories: 'Political ideology,' 'Election campaign content,' and 'Gossip.' Also, please rate the trustworthiness of each news source."

[0847] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0848] Step 1:

[0849] The server collects election-related information from news websites, blogs, social media, and other sources on the Internet at designated times.

[0850] Input: a specific time, a set list of URLs, a specific hashtag (e.g., election 2023).

[0851] How it works: The server uses the requests library and BeautifulSoup to crawl each URL and retrieve election-related articles and posts. It also collects information from social media sites using their corresponding APIs.

[0852] Output: Collected election-related information (articles, posts).

[0853] Step 2:

[0854] The server analyzes the information collected in step 1, classifies it by category (political ideology, election campaign content, gossip, etc.), and filters it.

[0855] Input: Collected election-related information.

[0856] How it works: The server uses NLP techniques such as spaCy and BERT models to extract keywords and key content from documents and automatically classify them into predefined categories, filtering out redundant and noisy information.

[0857] Output: Useful information sorted by category.

[0858] Step 3:

[0859] The server evaluates the credibility of the information classified in step 2 and calculates a trust score.

[0860] Input: Useful information sorted by category.

[0861] How it works: The server uses machine learning libraries such as Scikit-learn or TensorFlow to calculate a trust score based on the reliability of the source and its past rating history.

[0862] Output: Information with a confidence score.

[0863] Step 4:

[0864] The server generates an aggregate site based on the information that was assigned a trust score in step 3.

[0865] Input: Information with a confidence score.

[0866] How it works: The server generates profile pages for each candidate, creating pages that display the latest information by category, such as campaign activities, policy proposals, and gossip.

[0867] Output: Aggregate site (web page).

[0868] Step 5:

[0869] The server periodically retrieves new information and automatically updates the aggregation site.

[0870] Input: Newly collected election information (reprocessed from step 1).

[0871] What happens: The server re-runs steps 1 through 4 with the new information to keep the site up to date.

[0872] Output: A summary site that reflects the latest information.

[0873] Step 6:

[0874] Users access the aggregation site from their smartphones, tablets, and interactive display devices to view the latest information about each candidate and category.

[0875] Input: URL of the aggregation site.

[0876] How it works: A device (smartphone, tablet, etc.) connects to the website through a browser, allowing users to interactively view the latest election information. Users can also opt to receive email updates about specific candidates.

[0877] Output: Interactive election updates and email notification options.

[0878] 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.

[0879] This invention is a system that efficiently collects, classifies, and evaluates election-related information, provides it to voters in an easy-to-understand manner, and recognizes the user's emotions and dynamically adjusts the way the information is presented. Below, we will explain the program processing of this system in natural language.

[0880] Information Collection Module

[0881] The server pre-configures websites and social media hashtags to monitor, crawls them at designated times (e.g., 1:00 AM and 1:00 PM) to collect new election-related information, and temporarily stores the collected data. For example, the server collects articles and posts related to "Election 2023" from designated news portals and social media.

[0882] Data Classification Module

[0883] The server analyzes the collected information and uses natural language processing (NLP) technology to extract keywords and content from each piece of information. This allows the information to be automatically categorized into categories such as political ideology, election campaign content, and gossip. It also filters out duplication and noise, retaining only useful information. For example, if similar news is obtained from multiple sources, the server selects the most reliable source and deletes the rest.

[0884] Authenticity Assessment Module

[0885] The server evaluates the credibility of the collected information using a credibility evaluation algorithm. The algorithm calculates a credibility score based on the reliability of the source and its past evaluation history. Information with a credibility score below a certain level is filtered out, and only highly credible information is advanced to the next step. For example, the server evaluates the credibility score of news sites and eliminates articles with low credibility.

[0886] Aggregation site generation module

[0887] The server generates a website based on the information that has been organized and credibility-evaluated. This website has a profile page for each candidate, displaying the latest information by category, such as political ideology, election campaign details, policy proposals, and gossip. For example, the server creates a section on Candidate A's page that displays the latest policy proposals and election campaign event information.

[0888] Auto Update Module

[0889] The server retrieves new information according to a specified schedule and periodically updates the contents of the aggregation site. This ensures that the information on the site is always up to date. For example, the server updates the new information after crawling twice a day, and automatically archives old information.

[0890] User Access and Notification Module

[0891] Users access the aggregation site from their devices (smartphones or PCs) and view the latest information on candidates and categories of interest. They can also set up update notifications for specific candidates. This allows users to receive email notifications when new information is added. For example, a user can check the latest developments of candidate A on their smartphone and set up email notifications when new information is added.

[0892] Emotion Engine Module

[0893] The server is equipped with an emotion engine to recognize the user's emotions. This engine analyzes the user's emotions based on the information the user is viewing and their interaction patterns. For example, the server analyzes the user's click history and browsing time to estimate their emotional state, such as their interests and stress level.

[0894] Dynamic Display Adjustment Module

[0895] The server dynamically adjusts the display format of information based on the emotional data obtained from the emotion engine. For example, if the user is feeling stressed, the displayed information is simplified. It also prioritizes the display of information about specific candidates based on the results of emotion analysis. For example, if the server determines that the user is interested in candidate B, it prioritizes displaying information about candidate B on the top page.

[0896] By combining the above modules, the present invention can realize a system that not only provides information but also dynamically presents information taking into account the emotional state of the user.

[0897] The processing flow will be explained below.

[0898] Step 1: Gather information

[0899] The server loads a list of websites, news sources, and social media hashtags to monitor.

[0900] The server crawls these sources at designated times (e.g., 1:00 AM and 1:00 PM) to collect election-related information.

[0901] The server temporarily stores the collected information in storage.

[0902] Step 2: Data Classification

[0903] The server analyzes the collected information and extracts keywords and content using natural language processing (NLP) technology.

[0904] Based on the extracted keywords, the server classifies the information into categories (political ideology, election campaign content, gossip, etc.).

[0905] The server filters out redundant information and noise, and keeps only the useful information.

[0906] Step 3: Credibility assessment

[0907] The server uses a credibility assessment algorithm to assess the authenticity of the collected information.

[0908] The server calculates a trust score based on the reliability of the source and its past rating history.

[0909] The server filters out information with a reliability score below a certain level, and only information with a high reliability score proceeds to the next step.

[0910] Step 4: Generate a website

[0911] The server generates a summary site based on the information that has been organized and evaluated for credibility.

[0912] The server creates a profile page for each candidate, displaying the latest information by category, such as political ideology, election campaign details, policy proposals, and gossip.

[0913] The server optimizes the site design for user accessibility.

[0914] Step 5: Automatic Updates

[0915] The server retrieves new information on a specified schedule and periodically updates the content of the aggregation site.

[0916] The server automatically archives old information and reflects the latest information.

[0917] The server crawls twice a day and updates the site with new information in real time.

[0918] Step 6: User Access and Notification

[0919] Users access the aggregation site from their device (smartphone or PC) and view information on candidates and categories that interest them.

[0920] Users can set up update notifications for specific candidates.

[0921] The server will send email notifications when new information is added based on the user's notification settings.

[0922] Step 7: Emotion Recognition

[0923] The server provides an emotion engine for recognizing the user's emotions.

[0924] The server collects user interaction patterns such as click history, viewing time, and mouse movements.

[0925] The server analyzes interaction patterns and estimates the user's emotional state (interests, concerns, stress, etc.).

[0926] Step 8: Dynamic display adjustment

[0927] The server dynamically adjusts the presentation of information based on data from the emotion engine.

[0928] The server simplifies the information displayed when the user is stressed.

[0929] Based on the results of the sentiment analysis, the server prioritizes displaying information about specific candidates.

[0930] For example, if the user shows a strong interest in candidate A, the server places information about candidate A in a prominent position on the top page.

[0931] Through these steps, the system can efficiently collect information about elections, evaluate its reliability, and present information according to the user's emotional state.

[0932] Example 2

[0933] 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."

[0934] Conventional election information systems have problems with the quality of information provided to users due to inefficient collection, classification, and reliability evaluation of information. Furthermore, they lack the ability to dynamically adjust information display according to user emotions, resulting in a suboptimal user experience.

[0935] 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.

[0936] In this invention, the server includes means for collecting election-related information from multiple sources on the Internet, means for categorizing and filtering the collected information using natural language processing technology, means for evaluating the credibility of the collected information using a reliability evaluation algorithm and calculating a reliability score, means for automatically displaying information and generating an aggregator site based on the reliability score, means for periodically updating the aggregator site to reflect the latest information, and means for analyzing user sentiment and dynamically adjusting the display format of the information based on the data, thereby improving the quality of the collected information and optimizing the user experience.

[0937] The "Internet" is a collection of globally connected computer networks that enable the exchange of data and the viewing of information.

[0938] "Sources" refer to media such as websites and social media that provide specific information.

[0939] "Natural language processing technology" refers to the technology used to process and analyze human language using a computer, and is used for text analysis and document classification.

[0940] A "category" is a unit of classification for grouping similar things together, and is a criterion for dividing information into specific groups.

[0941] "Filtering" refers to the process of selecting and removing information based on specific criteria.

[0942] A "trustworthiness assessment algorithm" refers to a set of methods and formulas for calculating and assessing the reliability of information sources or the information itself.

[0943] A "trust score" is a number calculated as part of an evaluation and is an indicator of the reliability of the information or source.

[0944] An "aggregator site" is a website that aggregates a large amount of information in one place and provides it in a format that is easy for users to view.

[0945] "Update" is the process of rewriting existing data or information to the latest version.

[0946] "Emotion analysis" is a technology for estimating and evaluating a user's emotional state, and is primarily based on behavioral and interaction data.

[0947] "Dynamic adjustment" refers to changing the display format or content of information in real time or according to the situation at hand.

[0948] This invention is a system that efficiently collects, classifies, and evaluates election-related information, provides it to voters in an easy-to-understand manner, and recognizes the user's emotions and dynamically adjusts the way the information is presented.

[0949] First, the server collects election-related information from multiple sources on the Internet. To do this, it uses Python scraping modules (e.g., BeautifulSoup or Scrapy) to extract text and metadata from specified URLs and social media hashtags. The collected data is temporarily stored in a database (e.g., MySQL).

[0950] The server then analyzes the collected information using natural language processing techniques (e.g., NLTK or spaCy). The text data is tokenized, and the keywords and content of each piece of information are extracted. This allows the information to be automatically classified into categories such as political ideology, election campaign content, and gossip. It also filters out redundancies and noise, and only useful information is retained.

[0951] The server then uses a credibility assessment algorithm to evaluate the credibility of the collected information. The algorithm refers to the past evaluation history of the data source and calculates a credibility score for the source. Information with a credibility score below a certain level is filtered out, and only information with a high credibility score is advanced to the next step.

[0952] After sorting and evaluating the credibility of the information, the server generates a website. This website is built using a web framework (e.g., Django or Flask) and dynamically generates a profile page for each candidate. The profile page displays the latest information by category, such as political ideology, election campaign details, policy proposals, and gossip.

[0953] In addition, the server periodically re-runs the crawling process to retrieve new information, which is then added to the database, and old information is automatically archived, ensuring that the aggregation site always reflects the latest information.

[0954] Users can access the aggregation site using a web browser on their smartphone or PC to view the latest information on candidates and categories they are interested in. They can also set up update notifications to receive email notifications when new information is added.

[0955] The server also runs an emotion engine to recognize the user's emotions. This engine analyzes the user's click history and browsing time, and uses an emotion analysis algorithm (e.g., Sentiment Analysis API) to estimate the user's emotional state. Based on this, the server dynamically adjusts the information display format. For example, if the user is feeling stressed, the server can simplify the displayed information.

[0956] For example, the server collects information related to "Election 2023" at 1:00 AM and 1:00 PM. It retrieves the latest news about candidates from news portals and collects posts using the hashtag "Election 2023" from social media. It then uses NLP technology to analyze the data and classify it into categories.

[0957] An example of a prompt for a generative AI model is shown below.

[0958] "Describe a system that collects election updates, rates and categorizes them for credibility, and generates an aggregator. It uses sentiment analysis to dynamically adjust the presentation of information based on the information the user is viewing."

[0959] By inputting this prompt sentence into a generative AI model, the processing content of the above system can be automatically written down.

[0960] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0961] Step 1:

[0962] Information gathering

[0963] The server is configured in advance with the websites and social media hashtags to be monitored. At the specified times (e.g., 1:00 AM and 1:00 PM), it uses Python to call a scraping module (e.g., BeautifulSoup or Scrapy) to extract text and metadata from the specified URLs and hashtags. The collected data is temporarily stored in a MySQL database. The input is the URLs and hashtags to be monitored, and the output is the collected text data and metadata.

[0964] Step 2:

[0965] Data Classification

[0966] The server analyzes the collected information using natural language processing technology (e.g., NLTK or spaCy). Specifically, it tokenizes the text data and extracts the keywords and content of each piece of information. This automatically classifies the information into categories such as political ideology, election campaign content, and gossip. It also filters out duplication and noise. The input is the collected text data and metadata, and the output is data classified by category.

[0967] Step 3:

[0968] Credibility assessment

[0969] The server uses a reliability evaluation algorithm to evaluate the credibility of the collected information. It refers to the evaluation history of past data sources and calculates the reliability score of the information source. As a result, information with a reliability score below a certain level is filtered out, and only information with a high reliability is advanced to the next step. The input is data classified by category, and the output is data with a reliability score.

[0970] Step 4:

[0971] Aggregate site generation

[0972] The server generates an aggregator site based on the information that has been organized and credibility-evaluated. Using a web framework (e.g., Django or Flask), it dynamically generates a profile page for each candidate. The page displays the latest information by category, such as political ideology, election campaign details, policy proposals, and gossip. The input is data with a credibility score, and the output is the aggregator site HTML page.

[0973] Step 5:

[0974] automatic update

[0975] The server periodically retrieves new information according to a specified schedule and updates the site content. It re-runs the crawling process at regular intervals to retrieve new information and add it to the database. Old information is automatically archived. The input is the latest collected information, and the output is the updated aggregated site.

[0976] Step 6:

[0977] User Access and Notifications

[0978] Users can access the aggregation site using a browser on their device (smartphone or PC) and view the latest information on candidates and categories they are interested in. They can also set up update notifications and receive email notifications when new information is added. The input is the user's access request and notification settings, and the output is the latest information displayed and the notification email.

[0979] Step 7:

[0980] Emotion Analysis

[0981] The server runs an emotion engine to recognize user emotions. It analyzes click history and browsing time, and uses emotion analysis algorithms (e.g., Sentiment Analysis API) to estimate the user's emotional state. The input is the user's operation log and interaction data, and the output is emotion data.

[0982] Step 8:

[0983] Dynamic display adjustment

[0984] The server dynamically adjusts the display format of information based on data obtained from the emotion engine. For example, if the user is feeling stressed, the information can be reorganized to be simpler. It is also possible to prioritize the display of information about specific candidates based on their level of interest. The input is emotion data and data with confidence scores, and the output is information in an adjusted display format.

[0985] (Application example 2)

[0986] 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."

[0987] In addition to efficiently collecting, classifying, and evaluating election information and providing it to voters in an easy-to-understand manner, there is a need to provide more appropriate information to real-world customers and improve their experience by recognizing user emotions and dynamically adjusting the way information is presented. In particular, there is a lack of technology that enables store staff to respond to customers quickly and accurately. Therefore, it is necessary to develop a new system based on election information collection systems that can provide information according to the customer's emotional state.

[0988] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting election-related information from multiple information sources on the Internet; means for categorizing and filtering the collected information; means for evaluating the credibility of the collected information using a reliability evaluation algorithm and calculating a reliability score; means for automatically displaying information and generating a summary website based on the reliability score; means for periodically updating the summary website to reflect the latest information; means for recognizing user emotions and dynamically adjusting the display format of information; and means for displaying information about real-world customers on staff terminals and providing information based on the customer's emotional state. This not only enables efficient collection and provision of election information, but also enables provision of appropriate information tailored to the situation to real-world customers, thereby improving the customer experience.

[0989] "Election information" is information about election campaigns, candidates, election results, policy proposals, campaign promises, and news and rumors related to elections.

[0990] "Multiple sources on the Internet" refers to various types of information sources published on the Internet, such as news sites, social media, blogs, forums, and portal sites.

[0991] "Means of collection" refers to technology that automatically collects information on the Internet using web crawlers and APIs.

[0992] "Means of categorizing and filtering" refers to technology that uses natural language processing and keyword extraction algorithms to classify collected information into categories such as political ideology, election campaign details, and gossip information, and eliminates unnecessary data.

[0993] A "trustworthiness evaluation algorithm" is an algorithm that calculates the reliability of collected information based on evaluation indicators such as the reliability of the information source and past evaluation history.

[0994] The "means for evaluating credibility and calculating a trust score" is a technology that uses a trust evaluation algorithm to calculate a trust score for each piece of collected information and evaluate its credibility.

[0995] An "omatome site" is a website that organizes collected election information and integrates it for easy access by users.

[0996] The "means for generating an aggregate site" is a technology for constructing a website that can be viewed by users based on information that has undergone an evaluation of its reliability.

[0997] "Means of periodic updating to reflect the latest information" refers to technology that recollects information at specified intervals to keep the content of the website up to date.

[0998] "Means for recognizing user emotions and dynamically adjusting the display format of information" is a technology that estimates the user's emotional state from their interactions and facial expressions, and changes the way information is presented based on the results.

[0999] "Information about real-world customers" refers to information about customers' purchasing history, interests, and behavior when visiting a physical store.

[1000] "Means of displaying information on staff devices and providing information based on the emotional state of the customer" refers to technology that allows staff to refer to customer information in real time using, for example, smart glasses or a head-mounted display, and present appropriate information using emotion recognition technology.

[1001] The system program required to implement this invention includes the steps of data collection, classification, evaluation, and display. Each module of this system and its function will be described below.

[1002] Information Collection Module

[1003] The server automatically collects election-related information from multiple sources on the Internet. This process involves using web crawlers and APIs to retrieve information from specific news sites and social media sites. For example, it collects the latest news articles and social media posts related to the "2023 Election."

[1004] Data Classification Module

[1005] The server analyzes the collected information using natural language processing technology and categorizes it based on keywords and content. The collected data is classified into categories such as political ideology, election campaign details, and gossip information. It also filters out duplicate and noisy information, retaining only the more useful information. For example, if the same news is obtained from multiple sources, the data from the most reliable source is used.

[1006] Reliability Evaluation Module

[1007] The server evaluates the credibility of the collected information using a credibility evaluation algorithm. This algorithm calculates a credibility score based on the source's credibility and past evaluation history. Information with a credibility score below a certain level is filtered out, and only highly credible information is advanced to the next step. For example, if a particular news site has provided credible information in the past, information from that site will be given a high credibility score.

[1008] Aggregation site generation module

[1009] The server generates a website based on the information after the reliability evaluation. This website has a profile page for each candidate, displaying the latest information by category, such as political ideology, election campaign details, policy proposals, and gossip. For example, Candidate A's page will have a section displaying recent policy proposals and information about election campaign events.

[1010] Auto Update Module

[1011] The server automatically retrieves new information according to a specified schedule and periodically updates the content of the aggregation site. This ensures that the information on the site is always up to date. For example, the server updates the site with new information after crawling twice a day, and automatically archives old information.

[1012] User Access and Notification Module

[1013] Users access the aggregation site from their devices (smartphones or PCs) to view the latest information on candidates and categories of interest. They can also set up update notifications for specific candidates. This allows users to receive email notifications when new information is added. For example, a user can check the latest developments of candidate A on their smartphone and set up email notifications when new information is added.

[1014] Emotion Engine Module

[1015] The server is equipped with an emotion engine to recognize the user's emotions. This engine analyzes the user's emotions based on the information the user is viewing and their interaction patterns. For example, the server analyzes the user's click history and browsing time to estimate their emotional state, such as their interests and stress level.

[1016] Dynamic Display Adjustment Module

[1017] The server dynamically adjusts the display format of information based on the emotional data obtained from the emotion engine. For example, if the user is feeling stressed, the displayed information is simplified. It also prioritizes the display of information about specific candidates based on the results of emotion analysis. For example, if the server determines that the user is interested in candidate B, it prioritizes displaying information about candidate B on the top page.

[1018] Improving real-world customer experiences

[1019] In addition to the above modules, the system also uses smart glasses and head-mounted displays to provide effective information to customers in the real world. Staff use these devices to provide appropriate information in real time based on the customer's emotional state. For example, store staff can wear smart glasses to suggest products based on a customer's purchasing history and interests, or provide simple information when a customer is feeling stressed.

[1020] Prompt Sentence Examples

[1021] "Imagine an AI support system that provides the latest campaign information and dynamically displays information based on the customer's emotions. For example, if the customer is stressed, it might only display simple information."

[1022] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1023] Step 1:

[1024] The server collects election-related information from multiple sources on the Internet. As input, it receives a list of specified news sites and social media hashtags. The server uses a web crawler or API to crawl these sources, collects election-related information, and temporarily stores it in storage. The output is the collected raw data.

[1025] Step 2:

[1026] The server analyzes the collected information and uses a data classification module to classify and filter it by category. It receives the collected raw data as input. It uses natural language processing technology to extract keywords and content from the information and classify it into categories such as political ideology, election campaign details, and gossip information. It then filters out duplicate information and noise data, organizing only useful information. The output is organized data categorized by category.

[1027] Step 3:

[1028] The server uses a trust evaluation module to evaluate the credibility of the collected information. It receives the organized data as input. The trust evaluation algorithm calculates a trust score based on the reliability of the source and its past evaluation history. Information with a trust score below a certain level is filtered out, and only highly reliable information is advanced to the next step. The output is data with a trust score.

[1029] Step 4:

[1030] The server uses an aggregator module to generate an aggregator site based on the information that has undergone the reliability evaluation. It receives the data with the reliability scores as input. This creates a profile page for each candidate, displaying the latest information by category, such as political ideology, election campaign details, policy proposals, and gossip information. The output is the aggregator site's HTML / CSS files.

[1031] Step 5:

[1032] The server uses an automatic update module to periodically retrieve new information on a specified schedule and update the content of the aggregation site. It receives new collected data as input, ensuring that the information on the site is always up-to-date. Old information is archived. The output is the updated aggregation site content.

[1033] Step 6:

[1034] Users access the aggregation site from their devices (smartphones or PCs) and browse the latest information about candidates and categories of interest. The system receives the user's access request as input. The user can also set up update notifications for specific candidates. This way, users can receive email notifications when new information is added. The system outputs the user's browsing history and notification settings data.

[1035] Step 7:

[1036] The server uses an emotion engine module to recognize the user's emotions. It receives the user's interaction data (click history, browsing time, etc.) as input. The emotion engine analyzes this data and estimates the user's emotional state (interests, stress level, etc.). The output is the user's emotional state data.

[1037] Step 8:

[1038] The server uses a dynamic display adjustment module to dynamically adjust the display format of information based on the emotional data obtained from the emotion engine. It receives the user's emotional state data as input. For example, if the user is feeling stressed, the displayed information is simplified. If it is determined that the user is interested in a particular candidate, information about that candidate is displayed preferentially. The output is the adjusted display content.

[1039] Step 9:

[1040] Information about real-world customers is displayed on staff devices (smart glasses or head-mounted displays), and information is provided based on the customer's emotional state. The input is real-time customer data received by the device worn by the staff, such as purchase history and interests. The server analyzes this data and displays the most appropriate information on the device. For example, if a customer is feeling emotionally stressed, the information displayed can be simplified to increase their desire to purchase. The output is customer response information displayed on the staff device.

[1041] 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.

[1042] 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.

[1043] 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.

[1044] [Fourth embodiment]

[1045] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1046] 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.

[1047] 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).

[1048] 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.

[1049] 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.

[1050] 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).

[1051] 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.

[1052] 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.

[1053] 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.

[1054] 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.

[1055] 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.

[1056] 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.

[1057] 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."

[1058] This invention is a system that efficiently collects, classifies, and evaluates election-related information and provides it to voters in an easy-to-understand manner. The program processing of this system is explained below in natural language.

[1059] Information Collection Module

[1060] The server collects election-related information from news websites, blogs, social media, and other sources on the Internet at specific times each day. It pre-sets the websites and hashtags it monitors and crawls them all. For example, the server crawls news sites based on a pre-set URL list at 1:00 AM and 1:00 PM to collect election-related articles. It also collects social media posts using specific hashtags (e.g., "election 2023").

[1061] Data Reduction Module

[1062] The server analyzes the collected information and classifies it by category (political ideology, election campaign content, gossip, etc.). It uses natural language processing (NLP) technology to extract keywords and content from each piece of information and automatically classify it. It also filters out duplication and noise, leaving only useful information. For example, if the same news is collected from multiple sources, the server will only retain the most reliable source.

[1063] Authenticity Assessment Module

[1064] The server calculates a trust score based on the reliability of the source and its past evaluation history to assess the credibility of the collected information. Using AI algorithms, the server checks the reliability and consistency of a specific source and assigns a trust score. For example, the server evaluates the trust score of a news website and the credibility of an article based on that, and filters out information with low credibility.

[1065] Aggregation site generation module

[1066] The server generates a website based on the information that has been organized and credibility-evaluated. This website has a profile page for each candidate, and the latest information is displayed in categories such as election campaign details, policy proposals, and gossip. For example, the server creates a section on Candidate A's page that displays the latest policy proposals and information on election campaign events.

[1067] Auto Update Module

[1068] The server periodically retrieves new information and automatically updates the aggregation site. This ensures that the information on the site is always up to date. For example, after crawling twice a day, the server updates the aggregation site with new information and automatically archives old information.

[1069] User Access Module

[1070] Users can access the aggregation site from their devices (smartphones or PCs) and view the latest information on each candidate and category. They can also set up email notifications for updates on specific candidates. For example, a user can check the latest developments of candidate A on their smartphone and set up notifications to be sent by email when new information is added.

[1071] By combining the above modules, this invention can realize a system that properly collects, classifies, and evaluates information related to elections, and provides voters with reliable information.

[1072] The processing flow will be explained below.

[1073] Step 1: Gather information

[1074] The server loads a list of websites, news sources, and social media hashtags to monitor.

[1075] The server crawls monitored sites at designated times (for example, 1:00 AM and 1:00 PM) to collect new articles and posts related to the election.

[1076] The server temporarily stores the collected data in storage.

[1077] Step 2: Data Classification

[1078] The server analyzes the collected information and uses natural language processing (NLP) technology to extract keywords and content from each piece of information.

[1079] Based on the extracted keywords, the server classifies the information into categories (political ideology, election campaign content, gossip, etc.).

[1080] The server filters out redundant information and noise, leaving only the useful information.

[1081] Step 3: Credibility assessment

[1082] The server uses a credibility assessment algorithm to assess the authenticity of the collected information.

[1083] The server calculates a trust score based on the reliability of the source and its past rating history.

[1084] The server filters out information with a reliability score below a certain level, and only information with a high reliability score proceeds to the next step.

[1085] Step 4: Generate a website

[1086] The server generates a summary site based on the information that has been organized and evaluated for credibility.

[1087] The server creates a profile page for each candidate, displaying the latest information in categories such as political ideology, election activities, policy proposals, and gossip.

[1088] The server optimizes the site design for user accessibility.

[1089] Step 5: Automatic Updates

[1090] The server retrieves new information on a specified schedule and periodically updates the content of the aggregation site.

[1091] The server automatically archives old information and reflects the latest information.

[1092] The server crawls twice a day and updates the site with new information in real time.

[1093] Step 6: User Access and Notification

[1094] Users access the aggregation site from their device (smartphone or PC) and view information on candidates and categories that interest them.

[1095] Users can set up update notifications for specific candidates.

[1096] The server will send email notifications based on the user's settings when new information is added.

[1097] Through these processing steps, the system can efficiently collect, classify, and evaluate election-related information, providing voters with reliable information.

[1098] Example 1

[1099] 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."

[1100] Election-related information is diverse and collected from a variety of sources. This information is not necessarily reliable, and there is a lot of duplication and noise, making it difficult for voters to obtain accurate and reliable information about elections. Furthermore, because the information is scattered, there is a lack of efficient ways to obtain the latest information about specific candidates. Furthermore, there is the problem that it is difficult to always obtain the latest information during election periods, when information is frequently updated.

[1101] 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.

[1102] In this invention, the server includes: means for collecting election-related information from multiple sources on the Internet; means for categorizing and filtering the collected information using natural language processing technology; means for evaluating the credibility of the collected information using a reliability evaluation algorithm that calculates a reliability score based on the reliability of the information source and its past evaluation history; means for automatically displaying the information based on the reliability score and generating a summary site including a profile page for each candidate; and means for periodically updating the summary site to reflect the latest information. This allows voters to efficiently obtain the latest, reliable election information on a single site.

[1103] "Multiple sources on the internet" refers to online platforms such as websites, blogs and social media platforms that are used to provide data about the election.

[1104] "Means of collection" refers to programs and algorithms for automatically obtaining information on the Internet, and is a system for crawling based on specific keywords or URL lists.

[1105] "Natural language processing technology" refers to the general technology for analyzing text data to understand its meaning and process information written in human language, extracting, classifying, and filtering content.

[1106] "Categorizing and filtering" refers to the process of separating collected information based on specific themes or topics, and removing redundancies and noise to retain only the useful information.

[1107] "Source credibility" is an assessment of how accurate and reliable the source of information has been in the past, and serves as a criterion for judging the credibility of information.

[1108] "Past evaluation history" refers to a record of evaluations of the reliability and source of previously collected information, and is data used to determine the reliability of current information.

[1109] A "trust score" is a numerical representation of the credibility of collected information or information sources, with a higher score indicating higher reliability.

[1110] A "trustworthiness evaluation algorithm" refers to a calculation method or program for calculating the reliability of information based on the reliability of the information source and past evaluation history.

[1111] An "aggregator site" is a website that displays collected and classified information in a centralized manner, and is a platform that provides each candidate with a profile page and the latest information.

[1112] "Regular updating means" means a mechanism for automatically updating the contents of a database or website to collect new information at set intervals and keep existing data up to date.

[1113] "Means for enabling access via a web browser" refers to a mechanism that allows a user to access the aggregation site via a web browser using a terminal connected to the Internet.

[1114] "Means for setting up update notifications" refers to an interface that allows users to set up notifications, such as by email, when new information is added about a specific candidate or category.

[1115] The present invention relates to a system that efficiently collects, classifies, and evaluates election-related information and provides it to voters in an easy-to-understand manner. This system consists of three main components: a server, a terminal, and a user. The hardware and software required to implement the present invention are described in detail below.

[1116] The server is an internet-connected computer that runs a program using the Python programming language and related libraries (BeautifulSoup, SpaCy, etc.). The server first collects election-related information from news websites, blogs, social media, etc. on the internet. For example, the server crawls news sites based on a set list of URLs at 1:00 AM and 1:00 PM, and also collects social media posts using a specific hashtag (e.g., "Election 2023").

[1117] The server then analyzes the collected information using natural language processing (NLP) technology and classifies it by category (political ideology, election campaign details, gossip, etc.). Specifically, it uses the SpaCy library to extract text features and then uses machine learning algorithms such as SVM (Support Vector Machine) to classify the information. It also filters out duplicate and noisy information, leaving only the useful information. For example, if the same news is collected from multiple sources, the server will only retain the most reliable source.

[1118] The server then evaluates the credibility of the collected information by referencing past evaluation history and external credibility score databases (e.g., Media Bias / Fact Check) to assess the trustworthiness of sources and articles, and then calculating a credibility score using an AI model. Information with low credibility is filtered out, and only information with high credibility is retained.

[1119] After sorting and evaluating the credibility of the information, the server generates an aggregate website. This website has a profile page for each candidate, with the latest information displayed in categories such as election activities, policy proposals, and gossip. For example, the server creates a section on Candidate A's page that displays the latest policy proposals and information on election campaign events. The aggregate website is built using the Django framework.

[1120] In addition, the server periodically retrieves new information and automatically updates the aggregation site, ensuring that the information on the site is always up to date. After crawling twice a day, the server updates the aggregation site with new information and automatically archives old information.

[1121] Users can access the website through a web browser on their device (smartphone or PC) and view the latest information about each candidate and category. They can also set up email notifications for updates about specific candidates. For example, a user can check the latest information about candidate A on their smartphone and set up notifications to be sent by email when new information is added.

[1122] Below are some example prompts to input to a generative AI model:

[1123] (Example of a prompt)

[1124] "Collect news articles about specific candidates, including their latest policy proposals and campaign events, and organize them by category. Also, rate the credibility of the information you collect and display only the most credible information."

[1125] As described above, the present invention realizes a system for providing information about elections efficiently and reliably.

[1126] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1127] Step 1: Gather information

[1128] The server will crawl election information from news websites, blogs and social media across the internet at 1:00 AM and 1:00 PM.

[1129] Input: A pre-defined list of URLs or a specific hashtag (e.g., Election 2023).

[1130] What it does: The server uses Python's BeautifulSoup library to parse HTML and extract news articles and social media posts, and it also uses the Twitter API to collect tweets containing specific hashtags.

[1131] Output: A text data list of news articles and social media posts about the election.

[1132] Step 2: Data analysis and classification

[1133] The server analyzes the collected information using natural language processing (NLP) technology and classifies it into categories.

[1134] Input: The text data list collected in step 1.

[1135] What it does: The server uses the SpaCy library to extract text features, and then uses SVM (Support Vector Machine) and other classification algorithms to classify the data into categories such as political ideology, campaign content, gossip, etc. It also filters out duplicates and noise.

[1136] Output: A list of text data sorted by category.

[1137] Step 3: Credibility assessment

[1138] The server calculates a trust score based on the reliability of the source and past evaluation history to evaluate the credibility of the collected information.

[1139] Input: The text data list classified in step 2.

[1140] Specific operation: The server refers to each source's domain name, past rating history, and an external trust score database, and calculates a trust score using an AI model (e.g., random forest or neural network).

[1141] Output: A list of text data with a confidence score for each piece of information.

[1142] Step 4: Generate a website

[1143] The server generates a summary site based on the information that has been organized and evaluated for credibility.

[1144] Input: A list of text data with confidence scores assigned in Step 3.

[1145] What it does: The server adds data to a website built using the Django framework, updates each candidate's profile page, and dynamically generates HTML templates to display the information.

[1146] Output: A website that aggregates the latest election information.

[1147] Step 5: Automatic Updates

[1148] The server periodically retrieves new information and automatically updates the aggregation site.

[1149] Input: Historical database and newly collected information.

[1150] What it does: The server sets up a Cron job to run the crawl twice a day, updating the database so that new information is added and old information is archived.

[1151] Output: A website that aggregates information and keeps it up to date.

[1152] Step 6: User Access

[1153] Users can access the aggregation site from their devices (smartphones or PCs) and view the latest information on each candidate and category.

[1154] Input: The user's access request.

[1155] What happens: A user accesses the site through a web browser and views a specific candidate or category page. The user also configures email notifications in their account settings page to receive notifications when new information is added.

[1156] Output: Latest election information available to the user, along with email notification settings.

[1157] (Application example 1)

[1158] 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."

[1159] There is a wide range of information related to elections, and the challenge is to centrally organize it while evaluating its credibility and reliability and provide it to voters. Furthermore, in order to immediately reflect the collected information in actual election activities and choices, it is necessary to provide the latest information in near real time. Furthermore, there are insufficient means of providing interactive election-related information in brick-and-mortar stores, and a system that allows users to easily access it is needed.

[1160] 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.

[1161] In this invention, the server includes: means for collecting election-related information from multiple sources on the Internet, including news websites, blogs, and social networking sites; means for categorizing and filtering the collected information; means for evaluating the credibility of the collected information using a reliability evaluation algorithm and calculating a reliability score; means for automatically displaying the information and generating a website aggregation based on the reliability score; means for periodically updating the website aggregation to reflect the latest information; and means for providing an interface that makes the information available via smartphones, tablets, and interactive display devices. This makes it possible to centrally manage collected election-related information in a reliable manner and provide it interactively in physical stores.

[1162] "Election information" refers to general information such as election campaigns, political ideas, candidate profiles, policy proposals, and related news and events.

[1163] "Multiple sources on the Internet" refers to multiple online platforms, including news websites, blogs, and social media, and has a mechanism for collecting information from these.

[1164] "Classification by category" is a process of organizing collected information by theme, such as political ideology, election campaign details, or gossip, making it easier for users to understand the information.

[1165] "Filtering" is the process of removing redundancy and noise from collected information and selecting only useful information.

[1166] A "trustworthiness evaluation algorithm" is a method for calculating the reliability of collected information based on the reliability of the information source and past evaluation history.

[1167] A "trust score" is a numerical representation of the reliability of a source of information and the content of the information, with a higher score indicating more trustworthy information.

[1168] An "Omatome Site" is a website that displays and provides organized, categorized, and evaluated election information in a centralized manner.

[1169] "Periodic updating" refers to a process of incorporating new information at regular intervals to keep the information up-to-date.

[1170] "Interface provision means" refers to mechanisms that make it easier for users to access information through smartphones, tablets, and interactive display devices.

[1171] To implement this invention, the following system is constructed. A server collects election-related information from news websites, blogs, social networking sites, etc. on the Internet at a specific time each day. Specifically, the server uses a crawling tool to collect information based on a pre-set URL list and hashtags.

[1172] Information Collection Module

[1173] The server uses the requests library and BeautifulSoup to collect information from news websites and blogs. Information from social media sites is collected using the corresponding APIs. For example, news sites are crawled at 1:00 AM and 1:00 PM every day to collect election-related articles and posts. This also includes social media posts with specific hashtags such as "Election 2023."

[1174] Data Reduction Module

[1175] The server analyzes the collected information and classifies it by category (political ideology, election campaign details, gossip, etc.). It uses NLP (natural language processing) technology to automatically categorize information by analyzing keywords and context. Specifically, it uses spaCy and BERT models to extract key keywords from documents and categorize them based on those keywords. Additionally, if the same news is collected from multiple sources, it eliminates duplicates and retains only the most reliable source.

[1176] Authenticity Assessment Module

[1177] The server evaluates the credibility of the collected information by calculating a trust score based on the reliability of the source and past evaluation history. It uses AI algorithms to check the reliability and consistency of a specific source and assign a trust score. The evaluation uses machine learning libraries such as Scikit-learn and TensorFlow.

[1178] Aggregation site generation module

[1179] The server then generates a website based on the information that has been organized and credibility-assessed. This website has a profile page for each candidate, with the latest information displayed in categories such as election activities, policy proposals, and gossip.

[1180] Auto Update Module

[1181] The server periodically retrieves new information and automatically updates the aggregation site. This ensures that the information on the site is always up to date. For example, after crawling twice a day, new information is updated on the aggregation site, and old information is automatically archived.

[1182] User Access Module

[1183] Users can access the website from their smartphones, tablets, and interactive display devices to view the latest information on each candidate and category. They can also opt to receive email updates about specific candidates, providing real-time access to the election information they need.

[1184] Specific examples

[1185] A specific example is the prompt "Aggregate, categorize, and rate the credibility of the latest news about Japan's 2023 elections."

[1186] Example prompt:

[1187] "Please compile the latest news about the 2023 Japanese election and categorize it into the following categories: 'Political ideology,' 'Election campaign content,' and 'Gossip.' Also, please rate the trustworthiness of each news source."

[1188] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1189] Step 1:

[1190] The server collects election-related information from news websites, blogs, social media, and other sources on the Internet at designated times.

[1191] Input: a specific time, a set list of URLs, a specific hashtag (e.g., election 2023).

[1192] How it works: The server uses the requests library and BeautifulSoup to crawl each URL and retrieve election-related articles and posts. It also collects information from social media sites using their corresponding APIs.

[1193] Output: Collected election-related information (articles, posts).

[1194] Step 2:

[1195] The server analyzes the information collected in step 1, classifies it by category (political ideology, election campaign content, gossip, etc.), and filters it.

[1196] Input: Collected election-related information.

[1197] How it works: The server uses NLP techniques such as spaCy and BERT models to extract keywords and key content from documents and automatically classify them into predefined categories, filtering out redundant and noisy information.

[1198] Output: Useful information sorted by category.

[1199] Step 3:

[1200] The server evaluates the credibility of the information classified in step 2 and calculates a trust score.

[1201] Input: Useful information sorted by category.

[1202] How it works: The server uses machine learning libraries such as Scikit-learn or TensorFlow to calculate a trust score based on the reliability of the source and its past rating history.

[1203] Output: Information with a confidence score.

[1204] Step 4:

[1205] The server generates an aggregate site based on the information that was assigned a trust score in step 3.

[1206] Input: Information with a confidence score.

[1207] How it works: The server generates profile pages for each candidate, creating pages that display the latest information by category, such as campaign activities, policy proposals, and gossip.

[1208] Output: Aggregate site (web page).

[1209] Step 5:

[1210] The server periodically retrieves new information and automatically updates the aggregation site.

[1211] Input: Newly collected election information (reprocessed from step 1).

[1212] What happens: The server re-runs steps 1 through 4 with the new information to keep the site up to date.

[1213] Output: A summary site that reflects the latest information.

[1214] Step 6:

[1215] Users access the aggregation site from their smartphones, tablets, and interactive display devices to view the latest information about each candidate and category.

[1216] Input: URL of the aggregation site.

[1217] How it works: A device (smartphone, tablet, etc.) connects to the website through a browser, allowing users to interactively view the latest election information. Users can also opt to receive email updates about specific candidates.

[1218] Output: Interactive election updates and email notification options.

[1219] 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.

[1220] This invention is a system that efficiently collects, classifies, and evaluates election-related information, provides it to voters in an easy-to-understand manner, and recognizes the user's emotions and dynamically adjusts the way the information is presented. Below, we will explain the program processing of this system in natural language.

[1221] Information Collection Module

[1222] The server pre-configures websites and social media hashtags to monitor, crawls them at designated times (e.g., 1:00 AM and 1:00 PM) to collect new election-related information, and temporarily stores the collected data. For example, the server collects articles and posts related to "Election 2023" from designated news portals and social media.

[1223] Data Classification Module

[1224] The server analyzes the collected information and uses natural language processing (NLP) technology to extract keywords and content from each piece of information. This allows the information to be automatically categorized into categories such as political ideology, election campaign content, and gossip. It also filters out duplication and noise, retaining only useful information. For example, if similar news is obtained from multiple sources, the server selects the most reliable source and deletes the rest.

[1225] Authenticity Assessment Module

[1226] The server evaluates the credibility of the collected information using a credibility evaluation algorithm. The algorithm calculates a credibility score based on the reliability of the source and its past evaluation history. Information with a credibility score below a certain level is filtered out, and only highly credible information is advanced to the next step. For example, the server evaluates the credibility score of news sites and eliminates articles with low credibility.

[1227] Aggregation site generation module

[1228] The server generates a website based on the information that has been organized and credibility-evaluated. This website has a profile page for each candidate, displaying the latest information by category, such as political ideology, election campaign details, policy proposals, and gossip. For example, the server creates a section on Candidate A's page that displays the latest policy proposals and election campaign event information.

[1229] Auto Update Module

[1230] The server retrieves new information according to a specified schedule and periodically updates the contents of the aggregation site. This ensures that the information on the site is always up to date. For example, the server updates the new information after crawling twice a day, and automatically archives old information.

[1231] User Access and Notification Module

[1232] Users access the aggregation site from their devices (smartphones or PCs) and view the latest information on candidates and categories of interest. They can also set up update notifications for specific candidates. This allows users to receive email notifications when new information is added. For example, a user can check the latest developments of candidate A on their smartphone and set up email notifications when new information is added.

[1233] Emotion Engine Module

[1234] The server is equipped with an emotion engine to recognize the user's emotions. This engine analyzes the user's emotions based on the information the user is viewing and their interaction patterns. For example, the server analyzes the user's click history and browsing time to estimate their emotional state, such as their interests and stress level.

[1235] Dynamic Display Adjustment Module

[1236] The server dynamically adjusts the display format of information based on the emotional data obtained from the emotion engine. For example, if the user is feeling stressed, the displayed information is simplified. It also prioritizes the display of information about specific candidates based on the results of emotion analysis. For example, if the server determines that the user is interested in candidate B, it prioritizes displaying information about candidate B on the top page.

[1237] By combining the above modules, the present invention can realize a system that not only provides information but also dynamically presents information taking into account the emotional state of the user.

[1238] The processing flow will be explained below.

[1239] Step 1: Gather information

[1240] The server loads a list of websites, news sources, and social media hashtags to monitor.

[1241] The server crawls these sources at designated times (e.g., 1:00 AM and 1:00 PM) to collect election-related information.

[1242] The server temporarily stores the collected information in storage.

[1243] Step 2: Data Classification

[1244] The server analyzes the collected information and extracts keywords and content using natural language processing (NLP) technology.

[1245] Based on the extracted keywords, the server classifies the information into categories (political ideology, election campaign content, gossip, etc.).

[1246] The server filters out redundant information and noise, and keeps only the useful information.

[1247] Step 3: Credibility assessment

[1248] The server uses a credibility assessment algorithm to assess the authenticity of the collected information.

[1249] The server calculates a trust score based on the reliability of the source and its past rating history.

[1250] The server filters out information with a reliability score below a certain level, and only information with a high reliability score proceeds to the next step.

[1251] Step 4: Generate a website

[1252] The server generates a summary site based on the information that has been organized and evaluated for credibility.

[1253] The server creates a profile page for each candidate, displaying the latest information by category, such as political ideology, election campaign details, policy proposals, and gossip.

[1254] The server optimizes the site design for user accessibility.

[1255] Step 5: Automatic Updates

[1256] The server retrieves new information on a specified schedule and periodically updates the content of the aggregation site.

[1257] The server automatically archives old information and reflects the latest information.

[1258] The server crawls twice a day and updates the site with new information in real time.

[1259] Step 6: User Access and Notification

[1260] Users access the aggregation site from their device (smartphone or PC) and view information on candidates and categories that interest them.

[1261] Users can set up update notifications for specific candidates.

[1262] The server will send email notifications when new information is added based on the user's notification settings.

[1263] Step 7: Emotion Recognition

[1264] The server provides an emotion engine for recognizing the user's emotions.

[1265] The server collects user interaction patterns such as click history, viewing time, and mouse movements.

[1266] The server analyzes interaction patterns and estimates the user's emotional state (interests, concerns, stress, etc.).

[1267] Step 8: Dynamic display adjustment

[1268] The server dynamically adjusts the presentation of information based on data from the emotion engine.

[1269] The server simplifies the information displayed when the user is stressed.

[1270] Based on the results of the sentiment analysis, the server prioritizes displaying information about specific candidates.

[1271] For example, if the user shows a strong interest in candidate A, the server places information about candidate A in a prominent position on the top page.

[1272] Through these steps, the system can efficiently collect information about elections, evaluate its reliability, and present information according to the user's emotional state.

[1273] Example 2

[1274] 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."

[1275] Conventional election information systems have problems with the quality of information provided to users due to inefficient collection, classification, and reliability evaluation of information. Furthermore, they lack the ability to dynamically adjust information display according to user emotions, resulting in a suboptimal user experience.

[1276] 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.

[1277] In this invention, the server includes means for collecting election-related information from multiple sources on the Internet, means for categorizing and filtering the collected information using natural language processing technology, means for evaluating the credibility of the collected information using a reliability evaluation algorithm and calculating a reliability score, means for automatically displaying information and generating an aggregator site based on the reliability score, means for periodically updating the aggregator site to reflect the latest information, and means for analyzing user sentiment and dynamically adjusting the display format of the information based on the data, thereby improving the quality of the collected information and optimizing the user experience.

[1278] The "Internet" is a collection of globally connected computer networks that enable the exchange of data and the viewing of information.

[1279] "Sources" refer to media such as websites and social media that provide specific information.

[1280] "Natural language processing technology" refers to the technology used to process and analyze human language using a computer, and is used for text analysis and document classification.

[1281] A "category" is a unit of classification for grouping similar things together, and is a criterion for dividing information into specific groups.

[1282] "Filtering" refers to the process of selecting and removing information based on specific criteria.

[1283] A "trustworthiness assessment algorithm" refers to a set of methods and formulas for calculating and assessing the reliability of information sources or the information itself.

[1284] A "trust score" is a number calculated as part of an evaluation and is an indicator of the reliability of the information or source.

[1285] An "aggregator site" is a website that aggregates a large amount of information in one place and provides it in a format that is easy for users to view.

[1286] "Update" is the process of rewriting existing data or information to the latest version.

[1287] "Emotion analysis" is a technology for estimating and evaluating a user's emotional state, and is primarily based on behavioral and interaction data.

[1288] "Dynamic adjustment" refers to changing the display format or content of information in real time or according to the situation at hand.

[1289] This invention is a system that efficiently collects, classifies, and evaluates election-related information, provides it to voters in an easy-to-understand manner, and recognizes the user's emotions and dynamically adjusts the way the information is presented.

[1290] First, the server collects election-related information from multiple sources on the Internet. To do this, it uses Python scraping modules (e.g., BeautifulSoup or Scrapy) to extract text and metadata from specified URLs and social media hashtags. The collected data is temporarily stored in a database (e.g., MySQL).

[1291] The server then analyzes the collected information using natural language processing techniques (e.g., NLTK or spaCy). The text data is tokenized, and the keywords and content of each piece of information are extracted. This allows the information to be automatically classified into categories such as political ideology, election campaign content, and gossip. It also filters out redundancies and noise, and only useful information is retained.

[1292] The server then uses a credibility assessment algorithm to evaluate the credibility of the collected information. The algorithm refers to the past evaluation history of the data source and calculates a credibility score for the source. Information with a credibility score below a certain level is filtered out, and only information with a high credibility score is advanced to the next step.

[1293] After sorting and evaluating the credibility of the information, the server generates a website. This website is built using a web framework (e.g., Django or Flask) and dynamically generates a profile page for each candidate. The profile page displays the latest information by category, such as political ideology, election campaign details, policy proposals, and gossip.

[1294] In addition, the server periodically re-runs the crawling process to retrieve new information, which is then added to the database, and old information is automatically archived, ensuring that the aggregation site always reflects the latest information.

[1295] Users can access the aggregation site using a web browser on their smartphone or PC to view the latest information on candidates and categories they are interested in. They can also set up update notifications to receive email notifications when new information is added.

[1296] The server also runs an emotion engine to recognize the user's emotions. This engine analyzes the user's click history and browsing time, and uses an emotion analysis algorithm (e.g., Sentiment Analysis API) to estimate the user's emotional state. Based on this, the server dynamically adjusts the information display format. For example, if the user is feeling stressed, the server can simplify the displayed information.

[1297] For example, the server collects information related to "Election 2023" at 1:00 AM and 1:00 PM. It retrieves the latest news about candidates from news portals and collects posts using the hashtag "Election 2023" from social media. It then uses NLP technology to analyze the data and classify it into categories.

[1298] An example of a prompt for a generative AI model is shown below.

[1299] "Describe a system that collects election updates, rates and categorizes them for credibility, and generates an aggregator. It uses sentiment analysis to dynamically adjust the presentation of information based on the information the user is viewing."

[1300] By inputting this prompt sentence into a generative AI model, the processing content of the above system can be automatically written down.

[1301] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1302] Step 1:

[1303] Information gathering

[1304] The server is configured in advance with the websites and social media hashtags to be monitored. At the specified times (e.g., 1:00 AM and 1:00 PM), it uses Python to call a scraping module (e.g., BeautifulSoup or Scrapy) to extract text and metadata from the specified URLs and hashtags. The collected data is temporarily stored in a MySQL database. The input is the URLs and hashtags to be monitored, and the output is the collected text data and metadata.

[1305] Step 2:

[1306] Data Classification

[1307] The server analyzes the collected information using natural language processing technology (e.g., NLTK or spaCy). Specifically, it tokenizes the text data and extracts the keywords and content of each piece of information. This automatically classifies the information into categories such as political ideology, election campaign content, and gossip. It also filters out duplication and noise. The input is the collected text data and metadata, and the output is data classified by category.

[1308] Step 3:

[1309] Credibility assessment

[1310] The server uses a reliability evaluation algorithm to evaluate the credibility of the collected information. It refers to the evaluation history of past data sources and calculates the reliability score of the information source. As a result, information with a reliability score below a certain level is filtered out, and only information with a high reliability is advanced to the next step. The input is data classified by category, and the output is data with a reliability score.

[1311] Step 4:

[1312] Aggregate site generation

[1313] The server generates an aggregator site based on the information that has been organized and credibility-evaluated. Using a web framework (e.g., Django or Flask), it dynamically generates a profile page for each candidate. The page displays the latest information by category, such as political ideology, election campaign details, policy proposals, and gossip. The input is data with a credibility score, and the output is the aggregator site HTML page.

[1314] Step 5:

[1315] automatic update

[1316] The server periodically retrieves new information according to a specified schedule and updates the site content. It re-runs the crawling process at regular intervals to retrieve new information and add it to the database. Old information is automatically archived. The input is the latest collected information, and the output is the updated aggregated site.

[1317] Step 6:

[1318] User Access and Notifications

[1319] Users can access the aggregation site using a browser on their device (smartphone or PC) and view the latest information on candidates and categories they are interested in. They can also set up update notifications and receive email notifications when new information is added. The input is the user's access request and notification settings, and the output is the latest information displayed and the notification email.

[1320] Step 7:

[1321] Emotion Analysis

[1322] The server runs an emotion engine to recognize user emotions. It analyzes click history and browsing time, and uses emotion analysis algorithms (e.g., Sentiment Analysis API) to estimate the user's emotional state. The input is the user's operation log and interaction data, and the output is emotion data.

[1323] Step 8:

[1324] Dynamic display adjustment

[1325] The server dynamically adjusts the display format of information based on data obtained from the emotion engine. For example, if the user is feeling stressed, the information can be reorganized to be simpler. It is also possible to prioritize the display of information about specific candidates based on their level of interest. The input is emotion data and data with confidence scores, and the output is information in an adjusted display format.

[1326] (Application example 2)

[1327] 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."

[1328] In addition to efficiently collecting, classifying, and evaluating election information and providing it to voters in an easy-to-understand manner, there is a need to provide more appropriate information to real-world customers and improve their experience by recognizing user emotions and dynamically adjusting the way information is presented. In particular, there is a lack of technology that enables store staff to respond to customers quickly and accurately. Therefore, it is necessary to develop a new system based on election information collection systems that can provide information according to the customer's emotional state.

[1329] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting election-related information from multiple information sources on the Internet; means for categorizing and filtering the collected information; means for evaluating the credibility of the collected information using a reliability evaluation algorithm and calculating a reliability score; means for automatically displaying information and generating a summary website based on the reliability score; means for periodically updating the summary website to reflect the latest information; means for recognizing user emotions and dynamically adjusting the display format of information; and means for displaying information about real-world customers on staff terminals and providing information based on the customer's emotional state. This not only enables efficient collection and provision of election information, but also enables provision of appropriate information tailored to the situation to real-world customers, thereby improving the customer experience.

[1330] "Election information" is information about election campaigns, candidates, election results, policy proposals, campaign promises, and news and rumors related to elections.

[1331] "Multiple sources on the Internet" refers to various types of information sources published on the Internet, such as news sites, social media, blogs, forums, and portal sites.

[1332] "Means of collection" refers to technology that automatically collects information on the Internet using web crawlers and APIs.

[1333] "Means of categorizing and filtering" refers to technology that uses natural language processing and keyword extraction algorithms to classify collected information into categories such as political ideology, election campaign details, and gossip information, and eliminates unnecessary data.

[1334] A "trustworthiness evaluation algorithm" is an algorithm that calculates the reliability of collected information based on evaluation indicators such as the reliability of the information source and past evaluation history.

[1335] The "means for evaluating credibility and calculating a trust score" is a technology that uses a trust evaluation algorithm to calculate a trust score for each piece of collected information and evaluate its credibility.

[1336] An "omatome site" is a website that organizes collected election information and integrates it for easy access by users.

[1337] The "means for generating an aggregate site" is a technology for constructing a website that can be viewed by users based on information that has undergone an evaluation of its reliability.

[1338] "Means of periodic updating to reflect the latest information" refers to technology that recollects information at specified intervals to keep the content of the website up to date.

[1339] "Means for recognizing user emotions and dynamically adjusting the display format of information" is a technology that estimates the user's emotional state from their interactions and facial expressions, and changes the way information is presented based on the results.

[1340] "Information about real-world customers" refers to information about customers' purchasing history, interests, and behavior when visiting a physical store.

[1341] "Means of displaying information on staff devices and providing information based on the emotional state of the customer" refers to technology that allows staff to refer to customer information in real time using, for example, smart glasses or a head-mounted display, and present appropriate information using emotion recognition technology.

[1342] The system program required to implement this invention includes the steps of data collection, classification, evaluation, and display. Each module of this system and its function will be described below.

[1343] Information Collection Module

[1344] The server automatically collects election-related information from multiple sources on the Internet. This process involves using web crawlers and APIs to retrieve information from specific news sites and social media sites. For example, it collects the latest news articles and social media posts related to the "2023 Election."

[1345] Data Classification Module

[1346] The server analyzes the collected information using natural language processing technology and categorizes it based on keywords and content. The collected data is classified into categories such as political ideology, election campaign details, and gossip information. It also filters out duplicate and noisy information, retaining only the more useful information. For example, if the same news is obtained from multiple sources, the data from the most reliable source is used.

[1347] Reliability Evaluation Module

[1348] The server evaluates the credibility of the collected information using a credibility evaluation algorithm. This algorithm calculates a credibility score based on the source's credibility and past evaluation history. Information with a credibility score below a certain level is filtered out, and only highly credible information is advanced to the next step. For example, if a particular news site has provided credible information in the past, information from that site will be given a high credibility score.

[1349] Aggregation site generation module

[1350] The server generates a website based on the information after the reliability evaluation. This website has a profile page for each candidate, displaying the latest information by category, such as political ideology, election campaign details, policy proposals, and gossip. For example, Candidate A's page will have a section displaying recent policy proposals and information about election campaign events.

[1351] Auto Update Module

[1352] The server automatically retrieves new information according to a specified schedule and periodically updates the content of the aggregation site. This ensures that the information on the site is always up to date. For example, the server updates the site with new information after crawling twice a day, and automatically archives old information.

[1353] User Access and Notification Module

[1354] Users access the aggregation site from their devices (smartphones or PCs) to view the latest information on candidates and categories of interest. They can also set up update notifications for specific candidates. This allows users to receive email notifications when new information is added. For example, a user can check the latest developments of candidate A on their smartphone and set up email notifications when new information is added.

[1355] Emotion Engine Module

[1356] The server is equipped with an emotion engine to recognize the user's emotions. This engine analyzes the user's emotions based on the information the user is viewing and their interaction patterns. For example, the server analyzes the user's click history and browsing time to estimate their emotional state, such as their interests and stress level.

[1357] Dynamic Display Adjustment Module

[1358] The server dynamically adjusts the display format of information based on the emotional data obtained from the emotion engine. For example, if the user is feeling stressed, the displayed information is simplified. It also prioritizes the display of information about specific candidates based on the results of emotion analysis. For example, if the server determines that the user is interested in candidate B, it prioritizes displaying information about candidate B on the top page.

[1359] Improving real-world customer experiences

[1360] In addition to the above modules, the system also uses smart glasses and head-mounted displays to provide effective information to customers in the real world. Staff use these devices to provide appropriate information in real time based on the customer's emotional state. For example, store staff can wear smart glasses to suggest products based on a customer's purchasing history and interests, or provide simple information when a customer is feeling stressed.

[1361] Prompt Sentence Examples

[1362] "Imagine an AI support system that provides the latest campaign information and dynamically displays information based on the customer's emotions. For example, if the customer is stressed, it might only display simple information."

[1363] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1364] Step 1:

[1365] The server collects election-related information from multiple sources on the Internet. As input, it receives a list of specified news sites and social media hashtags. The server uses a web crawler or API to crawl these sources, collects election-related information, and temporarily stores it in storage. The output is the collected raw data.

[1366] Step 2:

[1367] The server analyzes the collected information and uses a data classification module to classify and filter it by category. It receives the collected raw data as input. It uses natural language processing technology to extract keywords and content from the information and classify it into categories such as political ideology, election campaign details, and gossip information. It then filters out duplicate information and noise data, organizing only useful information. The output is organized data categorized by category.

[1368] Step 3:

[1369] The server uses a trust evaluation module to evaluate the credibility of the collected information. It receives the organized data as input. The trust evaluation algorithm calculates a trust score based on the reliability of the source and its past evaluation history. Information with a trust score below a certain level is filtered out, and only highly reliable information is advanced to the next step. The output is data with a trust score.

[1370] Step 4:

[1371] The server uses an aggregator module to generate an aggregator site based on the information that has undergone the reliability evaluation. It receives the data with the reliability scores as input. This creates a profile page for each candidate, displaying the latest information by category, such as political ideology, election campaign details, policy proposals, and gossip information. The output is the aggregator site's HTML / CSS files.

[1372] Step 5:

[1373] The server uses an automatic update module to periodically retrieve new information on a specified schedule and update the content of the aggregation site. It receives new collected data as input, ensuring that the information on the site is always up-to-date. Old information is archived. The output is the updated aggregation site content.

[1374] Step 6:

[1375] Users access the aggregation site from their devices (smartphones or PCs) and browse the latest information about candidates and categories of interest. The system receives the user's access request as input. The user can also set up update notifications for specific candidates. This way, users can receive email notifications when new information is added. The system outputs the user's browsing history and notification settings data.

[1376] Step 7:

[1377] The server uses an emotion engine module to recognize the user's emotions. It receives the user's interaction data (click history, browsing time, etc.) as input. The emotion engine analyzes this data and estimates the user's emotional state (interests, stress level, etc.). The output is the user's emotional state data.

[1378] Step 8:

[1379] The server uses a dynamic display adjustment module to dynamically adjust the display format of information based on the emotional data obtained from the emotion engine. It receives the user's emotional state data as input. For example, if the user is feeling stressed, the displayed information is simplified. If it is determined that the user is interested in a particular candidate, information about that candidate is displayed preferentially. The output is the adjusted display content.

[1380] Step 9:

[1381] Information about real-world customers is displayed on staff devices (smart glasses or head-mounted displays), and information is provided based on the customer's emotional state. The input is real-time customer data received by the device worn by the staff, such as purchase history and interests. The server analyzes this data and displays the most appropriate information on the device. For example, if a customer is feeling emotionally stressed, the information displayed can be simplified to increase their desire to purchase. The output is customer response information displayed on the staff device.

[1382] 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.

[1383] 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.

[1384] 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.

[1385] 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.

[1386] 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.

[1387] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1388] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1389] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1390] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1391] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1392] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1393] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1394] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1395] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1396] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1397] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1398] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1399] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1400] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1401] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1402] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1403] The following is further disclosed regarding the above embodiment.

[1404] (Claim 1)

[1405] A means of collecting election-related information from multiple sources on the Internet;

[1406] A means of categorizing and filtering the collected information;

[1407] A means for evaluating the credibility of the collected information using a credibility evaluation algorithm and calculating a credibility score;

[1408] a means for automatically displaying information based on trust scores and generating aggregators;

[1409] A means of regularly updating the aggregation site to reflect the latest information,

[1410] A system including:

[1411] (Claim 2)

[1412] 2. The system of claim 1, wherein the trustworthiness evaluation algorithm calculates a trustworthiness score based on the trustworthiness of the information source and its past evaluation history.

[1413] (Claim 3)

[1414] 10. The system of claim 1, further comprising means for enabling a user to access the aggregation site through a browser and set up update notifications for a particular candidate.

[1415] "Example 1"

[1416] (Claim 1)

[1417] A means of collecting election-related information from multiple sources on the Internet;

[1418] A means for categorizing and filtering the collected information using natural language processing technology;

[1419] A means for evaluating the credibility of collected information using a credibility evaluation algorithm that calculates a credibility score based on the credibility and past evaluation history of the source of information;

[1420] a means for automatically displaying information based on the trust scores and generating an aggregate site including a profile page for each candidate;

[1421] A means of regularly updating the aggregation site to reflect the latest information,

[1422] A system including:

[1423] (Claim 2)

[1424] 2. The system of claim 1, wherein the credibility assessment algorithm calculates the credibility score by referring to the source's domain name, past reporting history, and an external credibility score database.

[1425] (Claim 3)

[1426] 10. The system of claim 1, further comprising means for enabling a user to access the aggregation site through a web browser and for setting up update notifications for a particular candidate.

[1427] "Application Example 1"

[1428] (Claim 1)

[1429] A means of collecting election-related information from multiple sources on the Internet;

[1430] Sources of information include news websites, blogs, and social media.

[1431] A means of categorizing and filtering the collected information;

[1432] A means for evaluating the credibility of the collected information using a credibility evaluation algorithm and calculating a credibility score;

[1433] a means for automatically displaying information based on trust scores and generating aggregators;

[1434] A means of regularly updating the aggregation site to reflect the latest information,

[1435] an interface providing means for making the information available through smartphones, tablets, and interactive display devices;

[1436] A system including:

[1437] (Claim 2)

[1438] 2. The system of claim 1, wherein the trustworthiness evaluation algorithm calculates a trustworthiness score based on the trustworthiness of the information source and its past evaluation history.

[1439] (Claim 3)

[1440] 10. The system of claim 1, further comprising means for enabling a user to access the aggregation site through a browser and set up update notifications for a particular candidate.

[1441] "Example 2: Combining Emotion Engines"

[1442] (Claim 1)

[1443] A means of collecting election-related information from multiple sources on the Internet;

[1444] A means for categorizing and filtering the collected information using natural language processing technology;

[1445] A means for evaluating the credibility of the collected information using a credibility evaluation algorithm and calculating a credibility score;

[1446] a means for automatically displaying information based on trust scores and generating aggregators;

[1447] A means of regularly updating the aggregation site to reflect the latest information,

[1448] means for analyzing a user's emotions and dynamically adjusting the display format of information based on the data;

[1449] A system including:

[1450] (Claim 2)

[1451] 2. The system of claim 1, wherein the trustworthiness evaluation algorithm calculates a trustworthiness score based on the trustworthiness of the information source and its past evaluation history.

[1452] (Claim 3)

[1453] 10. The system of claim 1, further comprising means for enabling a user to access the aggregation site through a browser and for setting up update notifications regarding a particular candidate.

[1454] "Application example 2 when combining emotion engines"

[1455] (Claim 1)

[1456] A means of collecting election-related information from multiple sources on the Internet;

[1457] A means of categorizing and filtering the collected information;

[1458] A means for evaluating the credibility of the collected information using a credibility evaluation algorithm and calculating a credibility score;

[1459] a means for automatically displaying information based on trust scores and generating aggregators;

[1460] A means of regularly updating the aggregation site to reflect the latest information,

[1461] means for recognizing a user's emotions and dynamically adjusting the display format of information;

[1462] a means for displaying information about real-world customers on staff terminals and providing information based on the customer's emotional state;

[1463] A system including:

[1464] (Claim 2)

[1465] 2. The system of claim 1, wherein the trustworthiness evaluation algorithm calculates a trustworthiness score based on the trustworthiness of the information source and its past evaluation history.

[1466] (Claim 3)

[1467] 10. The system of claim 1, further comprising means for enabling a user to access the aggregation site through a browser and set up update notifications for a particular candidate. [Explanation of symbols]

[1468] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting election-related information from multiple sources on the Internet; A means of categorizing and filtering the collected information; A means for evaluating the credibility of the collected information using a credibility evaluation algorithm and calculating a credibility score; a means for automatically displaying information based on trust scores and generating aggregators; A means of regularly updating the aggregation site to reflect the latest information, A system including:

2. 2. The system of claim 1, wherein the trustworthiness evaluation algorithm calculates a trustworthiness score based on the trustworthiness and past evaluation history of the information source.

3. 10. The system of claim 1, further comprising means for enabling a user to access the aggregation site through a browser and for setting up update notifications for a particular candidate.

Images