system

Abstract

We provide the system. [Solution] Information gathering methods that collect candidate information from online sources, An analytical means that analyzes and classifies the collected information using natural language processing, An evaluation method for assessing the feasibility of a candidate's promises based on analyzed information, An information provision means that presents evaluation results through a user interface, A means of providing purchase-related information that provides political information related to the purchase behavior of users, A response generation means that searches for relevant information based on user inquiries and generates answers, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern elections, there is a vast amount of information for voters to evaluate the platforms and records of each candidate, and it is difficult to judge the reliability and accuracy of such information. In particular, information on the Internet is a mixture of good and bad, and it is difficult for voters to obtain accurate and useful information quickly. In such a situation, voters cannot make a decision based on sufficient information when voting, and as a result, the quality of democracy may decline. Therefore, there is a need to provide a system that allows voters to easily collect and analyze information about election candidates.

Means for Solving the Problems

[0005] The present invention solves the above problems by providing a system comprising: an information gathering means for collecting candidate information from online information sources; an analysis means for analyzing and classifying the collected information using natural language processing; an evaluation means for evaluating the feasibility of fulfilling the candidates' promises based on the analyzed information; an information provision means for presenting the evaluation results through a user interface; and a response generation means for searching for relevant information and generating answers based on inquiries from users. With this system, users can easily obtain accurate and comprehensive information about candidates and perform comparative analysis, thereby supporting more informed voting behavior.

[0006] "Candidate information" refers to information including the pledges, achievements, statements of opinion, and related activity history of an individual running for election.

[0007] "Online information sources" refer to websites, social media, news articles, and other digital media that serve as sources of information available on the internet.

[0008] "Information gathering means" encompasses the technologies and processes for automatically collecting necessary data from designated information sources.

[0009] "Natural language processing" refers to the techniques and methods used by computers to understand and analyze human language, and to semantically analyze and classify text data.

[0010] "Analysis means" refers to the techniques and processes used to analyze collected data using a specific algorithm and extract particular patterns or information.

[0011] "Feasibility of campaign promises" is a measure that evaluates the degree to which a candidate's campaign promises are actually achievable, and is calculated based on past cases and relevant data.

[0012] "Evaluation means" include technologies and processes for determining the value and potential of collected and analyzed data according to specific criteria.

[0013] "Information provision means" refers to interfaces and communication technologies for presenting analysis and evaluation results to users in a visually easy-to-understand manner.

[0014] A "user interface" refers to the visual and functional components that enable a user to interact with a system, allowing for information display and input operations.

[0015] "Response generation means" includes technologies and processes that search for relevant data in response to user input or inquiries and generate appropriate answers. [Brief explanation of the drawing]

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

Mode for Carrying Out the Invention

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

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

[0019] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0020] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

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

[0026] As shown in Figure 1, the 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 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

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

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0033] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores the data generation model 58 and the 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 processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

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

[0037] This invention is specifically implemented as a system for collecting, analyzing, evaluating, and providing information about election candidates from online sources. This system provides important information that voters can use as a reference when voting, based on the promises and achievements presented by the candidates.

[0038] First, the server is equipped with an information gathering module that automatically collects data from the official social media accounts and related news articles of candidates running in elections. This module periodically visits designated information sources and collects new posts and articles.

[0039] Next, the collected data is analyzed on the server using natural language processing technology. This analysis module identifies texts that correspond to pledges, past achievements, political opinions, etc., and classifies them appropriately. Specifically, it analyzes keywords and context within the text and categorizes them according to the relevant information.

[0040] Based on the analyzed data, the server evaluates the feasibility of each candidate's promises. This evaluation is performed using a dataset of past successful policies and machine learning algorithms, and an evaluation score is calculated for each candidate. This score serves as an indicator of the promisingness of a candidate's policies, intended to inform users.

[0041] Next, the terminal displays the evaluation results provided by the server in the user interface. Through this interface, users can view policy comparisons by theme and detailed information on each candidate. The information is visually organized and presented using graphs and charts.

[0042] Furthermore, users can input specific questions about candidates through their terminals, and these questions are sent to the server. The server searches for relevant information based on the submitted questions and interactively generates responses. For example, in response to the question, "I want to know about candidate X's education policies," the user will be provided with information indicating candidate X's policy proposals, past achievements, and feasibility.

[0043] This system allows users to make more informed voting decisions based on comprehensive and reliable information. This process improves the efficiency of access to election information and enhances the quality of democratic decision-making.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The server activates an information gathering module and searches for the specified candidate's official social media accounts and related news articles. In this process, APIs and web scraping techniques are used to obtain the latest information based on the candidate's name and related keywords.

[0047] Step 2:

[0048] The server processes the collected text data through a natural language processing engine to analyze its content. This analysis classifies the text into categories such as pledges, achievements, and opinions, and stores the content as structured data in a database.

[0049] Step 3:

[0050] The server inputs the analyzed data into a machine learning model to evaluate the feasibility of the promises. This involves applying a predictive model based on historical datasets to calculate a score indicating whether each promise is realistically achievable.

[0051] Step 4:

[0052] The terminal displays evaluation results obtained from the server in a user interface. When the user selects a specific candidate or policy theme, relevant information is presented in charts and text formats, making it easy to understand intuitively.

[0053] Step 5:

[0054] Users input the information they want to know or specific questions through their device. For example, they might ask, "I want to know more about candidate Y's environmental policies."

[0055] Step 6:

[0056] The server receives inquiries from users and searches for relevant data. Based on the relevant materials and evaluation results, it generates responses to the user's questions and extracts the most relevant information.

[0057] Step 7:

[0058] The terminal displays the response from the server to the user. The information provided includes a detailed analysis of the candidate's policies and past performance, and also displays supplementary materials to aid the user's understanding.

[0059] (Example 1)

[0060] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0061] The amount of information available about candidates in elections is vast, making it difficult for individual voters to compare it appropriately and make reliable decisions. Therefore, there is a need for a system that efficiently collects and analyzes candidates' pledges and past performance to provide reliable evaluation information. Furthermore, the system needs to be able to accurately respond to specific user questions.

[0062] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0063] In this invention, the server includes data collection means for automatically collecting data about candidates from information sources, data analysis means for analyzing the collected data using natural language processing technology and classifying it based on keywords and context, and data evaluation means for evaluating the feasibility of candidates' promises by comparing them with past success stories based on the analyzed data. This enables users to obtain candidate information efficiently and reliably and make informed choices.

[0064] A "source of information" refers to an online platform or database used to obtain data about a candidate.

[0065] "Data collection means" refers to the function of a system that automatically retrieves data related to a candidate from information sources.

[0066] "Natural language processing technology" refers to the technology that enables computers to understand, analyze, and use human language.

[0067] "Data analysis means" refers to the function of a system that analyzes collected data and classifies it based on specific keywords or context.

[0068] A "data evaluation tool" is a system function that evaluates the feasibility of a candidate's promises by comparing them with past cases based on analyzed data.

[0069] A "generative AI model" is an artificial intelligence system that generates responses in natural language in response to input.

[0070] A "response generation means" is a system function that uses a generation AI model based on user inquiries to search for relevant information and generate answers.

[0071] This invention is a system for automatically collecting, analyzing, and evaluating information about candidates and providing it to users. The following describes embodiments of the system in detail.

[0072] The server first uses an information gathering module to automatically collect data about candidates from multiple sources on the network. Specifically, it analyzes web pages using programming languages ​​and scraping techniques to extract data. Software tools such as Python's Beautiful Soup and Selenium may be used for this process.

[0073] The collected data is analyzed on the server using natural language processing techniques. The server utilizes libraries such as Python's NLTK and spaCy to detect and classify keywords and context within the text data. This makes it possible to organize information such as candidates' pledges and past achievements.

[0074] Subsequently, the server performs a process to evaluate the feasibility of the candidates' promises based on the analyzed data. In this step, machine learning frameworks such as TENSORFLOW® and Scikit-learn can be used to compare the candidates' current promises with past success stories and calculate an evaluation score.

[0075] The terminal features a user interface that intuitively displays evaluation results generated by the server. The terminal runs in a browser using React.js, allowing users to visually review various policy comparisons and candidate information. D3.js or a similar visualization library is used to draw graphs and charts.

[0076] Users can submit specific questions about candidates they are interested in via their device. These questions are sent to the server as text-based prompts, such as "Please tell me more about candidate Y's economic policies." Based on these questions, the server uses a generative AI model to generate natural language answers based on relevant information and provides them to the user.

[0077] Thus, the present invention enables users to efficiently and accurately grasp candidate information and make informed decisions. This improves access to election information and contributes to strengthening the democratic process.

[0078] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0079] Step 1:

[0080] The server uses an information gathering module to collect data about candidates from multiple online sources. This involves crawling web pages using tools such as Python's Beautiful Soup and Selenium, and extracting text data such as social media posts and news articles. The input is a list of URLs for the information sources, and the output is the retrieved raw text data.

[0081] Step 2:

[0082] The server performs natural language processing on the collected text data. Here, it uses Python's NLTK and spaCy to extract keywords and phrases from the data and classify them based on context. The input is the text data collected in step 1, and the output is data classified as pledges or past performance. Specifically, it identifies necessary information through morphological analysis and sentence structure analysis.

[0083] Step 3:

[0084] The server evaluates the feasibility of candidates' promises based on the analyzed data. It builds machine learning models using TensorFlow and Scikit-learn and compares them to past success stories. The input is the analyzed data obtained in step 2, and the output is the feasibility of the candidates' promises, quantified as an evaluation score. This evaluation is achieved by the machine learning algorithm reflecting past data.

[0085] Step 4:

[0086] The terminal displays the evaluation results sent from the server on the user interface. The terminal uses React.js to intuitively present information in the browser, allowing users to easily compare policies and view detailed information. The input is the evaluation score calculated in step 3, and the output is a visually organized graph or chart.

[0087] Step 5:

[0088] The user enters questions about candidates they are interested in through their terminal. The specific question is submitted as a text prompt. For example, "Please tell me more about Candidate X's educational policies." At this stage, the user's query is the input, and the request sent to the server is the output.

[0089] Step 6:

[0090] The server uses a generative AI model to search for relevant information based on the user's question and generates a natural language response. The input is a prompt from the user, and the output is a text message as a response. This response is based on the analyzed data and additional information found.

[0091] Step 7:

[0092] The terminal displays the server-generated response to the user. The input is the generated response message, and the output is the response as a notification or display to the user. This allows the user to quickly access the information they are looking for.

[0093] (Application Example 1)

[0094] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0095] A problem with modern elections is that voters often lack sufficient information about candidates' policies and feasibility. Furthermore, the limited opportunities to connect everyday consumer activities with political concerns make it difficult for citizens to reflect their choices in political decision-making. There is a need for a system that addresses these challenges and enables more voters to make informed decisions.

[0096] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0097] In this invention, the server includes information gathering means for collecting candidate information from online information sources, analysis means for analyzing and classifying the collected information using natural language processing, evaluation means for evaluating the feasibility of candidates' promises based on the analyzed information, information providing means for presenting the evaluation results through a user interface, purchase-related information providing means for providing political information related to the user's purchasing behavior, and response generation means for searching for relevant information and generating answers based on user inquiries. This effectively links consumer interests with political information, enabling users to make more informed political decisions.

[0098] "Candidate information" refers to a collection of data that includes election candidates' pledges, past achievements, political opinions, and other relevant information.

[0099] "Online information sources" refer to information sources that exist on the internet, such as websites and social media platforms, from which candidate information can be obtained.

[0100] "Information gathering means" refers to technology or modules used to automatically obtain necessary candidate information from designated online information sources.

[0101] "Natural language processing" is a technique for analyzing collected text data, structuring the data through processes such as keyword extraction, grammatical analysis, and semantic analysis.

[0102] "Analysis means" refers to a technology or module designed to classify and analyze collected candidate information using natural language processing.

[0103] "Evaluation tools" refer to methods or techniques for evaluating the feasibility of a candidate's promises based on analyzed information.

[0104] A "user interface" is a visual display method for presenting information and receiving user input, and includes charts, graphs, and other visual elements.

[0105] "Purchase-related information provision means" refers to methods or technologies for providing users with political information on topics related to their consumer behavior.

[0106] "Response generation means" refers to a technology or module for generating a response to a user inquiry based on relevant information.

[0107] Embodiments of this invention are embodied in a system that collects data on election candidates from online information sources and provides relevant political information according to the user's consumption behavior.

[0108] The server automatically collects candidate information from online sources using an information gathering module. This process utilizes web scraping techniques and API access to obtain text data from candidates' official websites and social media accounts. The collected data is processed by an analysis module on the server, which uses natural language processing techniques to classify and evaluate candidates' promises and achievements. The natural language processing techniques used here include keyword extraction, text classification, and sentiment analysis.

[0109] The server then uses machine learning algorithms to evaluate the feasibility of the analyzed information. In this process, it calculates a candidate's score by referring to past policy data and comparing it with the newly obtained information.

[0110] The terminal displays evaluation results provided by the server through a user interface. The evaluation information is presented in a visually easy-to-understand format using charts and graphs, allowing users to easily access detailed information about candidates and compare policies on different themes.

[0111] Furthermore, the system processes information related to users' purchasing behavior on the server side and provides political information through a purchase-related information provision mechanism. In this process, relevant policy information is recommended based on the electronic payment history, and users are given the opportunity to delve deeper into topics of interest to them.

[0112] As a concrete example, when a user purchases organic food using a terminal, they will be notified of relevant information, including information about candidates who advocate environmental policies related to that food. This information includes visual representations to facilitate understanding. Furthermore, this system can also respond to user inquiries using a generative AI model.

[0113] Example of a prompt:

[0114] "I would like to learn more about the latest environmental policies related to purchasing organic food. Please provide information to compare the candidates' proposals."

[0115] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0116] Step 1:

[0117] The server collects candidate information from online sources. Using APIs and web scraping techniques, it periodically crawls specified social media and news sites to retrieve new articles and posts. The input to this process is the URL or API endpoint of each source, and the output is raw text data.

[0118] Step 2:

[0119] The server analyzes the collected raw text data using natural language processing techniques. It extracts keywords and performs contextual analysis from the text to identify promises and achievements, and then classifies them into categories. The input to this process is text data, and the output is a structured information set.

[0120] Step 3:

[0121] The server applies a machine learning model to evaluate the feasibility of each candidate's promises based on the analyzed information. It compares the input information with similar past promise data and calculates an evaluation score for each candidate. The input to this process is a structured set of information, and the output is the evaluation score.

[0122] Step 4:

[0123] The terminal visually displays the evaluation results received from the server through a user interface. Graphs and charts are used to present candidate information and evaluations to the user in an intuitive way. The input to this process is the evaluation score, and the output is visual information for the user.

[0124] Step 5:

[0125] The server analyzes relevant purchase information based on the user's electronic payment history and transmits relevant political information to the terminal using a purchase-related information provision system. It searches for policies related to the purchased category and provides the user with that policy information. The input to this process is the electronic payment history, and the output is relevant policy information.

[0126] Step 6:

[0127] Users can ask specific questions through their device. These questions are sent to a server, where a generative AI model searches for relevant information and generates a response. An example of a prompt might be, "I would like to learn more about the latest environmental policies related to purchasing organic food. Please provide information comparing the proposals of the candidates." The input to this process is the user's question, and the output is the generated response.

[0128] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0129] This invention is implemented in a form that combines a conventional AI system for collecting and analyzing information on election candidates with an emotion engine that recognizes the user's emotions. When providing voters with information about candidates' promises and achievements, this system takes the user's emotional state into consideration, providing a more interactive experience.

[0130] The server first collects data from candidates' online information sources. The information gathering module retrieves the latest information on candidates via APIs from social media and news sites. As soon as this data is collected, it is analyzed using a natural language processing engine and classified as the candidate's promises and achievements. Then, it is evaluated by a machine learning model to predict the likelihood of the promises actually being fulfilled.

[0131] Once the data has been collected and analyzed, it is presented to the user on the terminal. When the user enters a question or inquiry, the system analyzes the input using an emotion engine to recognize the user's emotional state. The emotion engine infers emotions from the input text, identifying states such as favorable, anxious, or suspicious, and adjusts the way information is presented accordingly.

[0132] Specifically, the server adjusts the tone and level of detail of the information based on the emotions the user feels when entering a question. For example, if the user expresses concern or anxiety, more detailed explanations about the risks and disruptive factors of the promises will be added. If the user expresses positive emotions, information about the candidate's strengths and achievements will be emphasized.

[0133] Furthermore, emotional data provided by users is returned to the system as feedback. This allows the server to analyze user interaction trends and use that information to improve future information delivery methods. This feedback loop improves the overall performance of the system.

[0134] This invention allows users to receive information tailored to their emotional state, supporting them in making more meaningful decisions. This design provides the system with a more personalized experience.

[0135] The following describes the processing flow.

[0136] Step 1:

[0137] The server utilizes an information gathering module to collect data from the official social media accounts and news sites of designated candidates. This collection is performed regularly, with the update frequency increased during election periods. The collected data includes posts containing candidates' pledges and statements of opinion, as well as news articles.

[0138] Step 2:

[0139] The server analyzes the collected data through a natural language processing engine. This engine categorizes the text data into groups such as pledges, achievements, and opinions, identifying keywords and phrases and storing them in a database. The analysis results are then used in subsequent evaluation processes.

[0140] Step 3:

[0141] The server uses a machine learning model to evaluate the feasibility of candidates' promises based on the analyzed data. This model utilizes predictive algorithms based on past performance and similar cases to calculate a score for the feasibility of each promise. The evaluation results are stored in a database and used to provide information to users.

[0142] Step 4:

[0143] The terminal displays the analysis and evaluation results obtained from the server to the user. The user interface is designed to show publicly available information for each candidate in list or graph format, allowing users to easily search for details about policy areas and candidates that interest them.

[0144] Step 5:

[0145] Users enter their questions and concerns in text format through the displayed interface. This input may include questions about a specific candidate's policies or instructions regarding comparison criteria.

[0146] Step 6:

[0147] The server passes user input to the emotion engine, which analyzes the emotional state of the entered text. The analyzed emotional state is categorized into common emotion categories (joy, anger, surprise, etc.) and reflected in the information provided.

[0148] Step 7:

[0149] The server takes the emotion engine's output into account and adjusts the information to match the user's emotional state. For example, if an emotion indicating anxiety is detected, detailed and reassuring explanations will be provided when presenting information.

[0150] Step 8:

[0151] The terminal displays the server's generated response to the user. Sentiment-sensitive explanations and recommended candidate information are provided in a visually easy-to-understand format to support the user's decision-making.

[0152] Step 9:

[0153] Users make decisions regarding candidate selection based on information obtained through system interaction. They can also contribute to system improvement by using the feedback function to submit evaluations of the information provided by the system.

[0154] (Example 2)

[0155] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0156] In providing information about election candidates, there is a need for a system that can present personalized information in accordance with each user's emotional state and interactions. Conventional information provision methods have made it difficult to support users in making optimal decisions by providing uniform information without considering the user's emotions. Therefore, the present invention aims to provide a system that individualizes information and takes user emotions into consideration.

[0157] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0158] In this invention, the server includes means for collecting candidate information from information sources, means for analyzing and classifying the collected information using language analysis technology, and means for analyzing the emotional state from the user's input and adjusting the method of presenting information according to that emotion. This makes it possible to provide information that takes the user's emotional state into consideration.

[0159] "Candidate information" refers to all information about a candidate in an election, including their campaign promises, past achievements, online posts, and media coverage.

[0160] "Information sources" is a general term for media and platforms that provide data on the internet, including social networking services (SNS), news sites, and blogs.

[0161] "Means" refers to the methods or processes used to achieve a specific objective, or the devices or programs used to implement them.

[0162] "Language analysis technology" refers to techniques for analyzing text data written in natural language and structuring, classifying, and understanding the information contained within it.

[0163] A "user" refers to an individual or group that utilizes the information provision system, typically consisting of voters or related stakeholders who require election information.

[0164] "Emotional state" refers to the emotional response or mental state a user exhibits in response to a particular situation or information, and includes feelings such as favorability, anxiety, and doubt.

[0165] "Information provision" refers to the process of presenting analyzed data and evaluation results in a format that is easy for users to understand.

[0166] "Personalization" refers to the method of providing information and services that are individually tailored to the needs, preferences, and emotions of each user.

[0167] This invention is an AI system for providing users with information about election candidates, and its configuration includes functions for information gathering, language analysis, sentiment analysis, and personalized information provision.

[0168] The server collects data about election candidates from internet sources. These sources include social media and news sites, and the server retrieves data using APIs and RSS feeds. After retrieval, the server uses natural language processing techniques to classify data about candidates' promises and achievements, and then uses machine learning frameworks such as TensorFlow and PyTorch to analyze it.

[0169] Next, the server uses the analyzed data to evaluate whether the candidate's promises are feasible. This evaluation involves comparisons with similar past cases and machine learning-based prediction methods.

[0170] The terminal provides an interface for users to access information. Users can input questions and inquiries into the system through the terminal. At this time, the server analyzes the input and activates an emotion engine to recognize the user's emotional state. Through this emotion analysis, the server understands the emotions expressed by the user (e.g., affection, anxiety, suspicion, etc.) and adjusts how information is presented.

[0171] As a concrete example, if a user enters the text "Please tell me about the recent election candidates' promises. I would like to know the likelihood of those promises being fulfilled," the server will first analyze this request and retrieve and present information accordingly. If the user expresses concerns, a detailed analysis of the risks will be provided; if they express positive sentiments, the candidates' strengths will be highlighted.

[0172] Furthermore, emotional data obtained from users is returned to the system as feedback. The server uses this data to analyze trends in user interaction and improve future information delivery methods. This enhances personalized information delivery, allowing users to receive information that helps them make better decisions.

[0173] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0174] Step 1:

[0175] The server collects data about candidates from online sources such as social media and news sites. Input is raw data obtained via APIs and RSS feeds. This data includes information related to candidates' statements, news articles, election promises, and past performance. Output is data formatted for information analysis.

[0176] Step 2:

[0177] The server inputs the collected data into a natural language processing engine. The input data undergoes processing such as tokenization, part-of-speech tagging, and entity recognition. This allows for more accurate classification of candidates' promises and achievements. The output consists of structured data and information categorized for each candidate.

[0178] Step 3:

[0179] The server evaluates the feasibility of the campaign promises using a machine learning model based on the analyzed information. The input is the data organized in step 2. The model uses historical datasets to perform data calculations to predict the likelihood of a candidate's promises succeeding. The output is the feasibility evaluation result for each candidate's promises.

[0180] Step 4:

[0181] The terminal displays the evaluation results from the server on the user interface, providing information to the user. The input is the evaluation results obtained in step 3. The terminal presents the information in text, graphs, and tables to facilitate understanding. The output of this step is an interactive information display that the user can use.

[0182] Step 5:

[0183] The user enters questions or inquiries in text format based on the displayed information. The input is text information from the user. The server receives this input, analyzes it with an emotion engine, and infers the user's emotions. The output is the analysis result regarding the user's emotional state.

[0184] Step 6:

[0185] The server adjusts the tone and level of detail of the information presented based on the user's sentiment analysis results. The input is the result of the sentiment analysis in step 5. Specifically, if the user shows anxiety, additional explanations are added, and if they show positive emotions, the candidate's success stories are highlighted. The output is the adjusted content and presentation of the information.

[0186] Step 7:

[0187] The server uses sentiment data collected from users as a feedback loop to improve future information delivery methods. The input is the user's sentiment tendency data obtained in step 6. This improves the overall system performance. The output is a data-driven suggestion for improving future information delivery methods.

[0188] (Application Example 2)

[0189] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0190] In providing information about election candidates, a challenge is that conventional information presentation methods fail to consider the emotional state of individual users, leading to reduced information acceptability and reliability when users understand and make decisions based on that information. Furthermore, there is a lack of mechanisms to improve information presentation using user feedback.

[0191] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0192] In this invention, the server includes information gathering means for collecting candidate information from online information sources, analysis means for analyzing and classifying the collected information using natural language processing, and emotion analysis means for analyzing the user's emotions on a smart device and adjusting the information presentation based on the results. This makes it possible to provide appropriate information according to the user's emotions.

[0193] "Information gathering methods" refer to mechanisms for collecting candidate information from online sources.

[0194] "Analysis method" refers to the process of analyzing and classifying collected information using natural language processing technology.

[0195] "Evaluation methods" refer to methods for assessing the feasibility of fulfilling campaign promises based on analyzed candidate information.

[0196] "Information provision means" refers to means of presenting evaluation results through a user interface.

[0197] A "response generation means" is a function that searches for relevant information in response to a user's inquiry and generates an answer.

[0198] "Emotion analysis means" refers to a process for analyzing a user's emotions on a smart device and adjusting the information presented based on the results.

[0199] This invention is a system for efficiently collecting information about election candidates and providing that information to users in a personalized manner. The server first collects candidate information from online sources. In this process, it obtains a large amount of data using the Twitter API and news API.

[0200] The collected data is analyzed using natural language processing libraries such as Spacy and NLTK to classify candidates' promises and achievements. During this analysis process, machine learning libraries such as TensorFlow and PyTorch are used to evaluate the feasibility of fulfilling the promises.

[0201] On the device (such as the user's smartphone), information is presented through a user interface. To analyze the user's emotional state, text input is used for sentiment analysis. A sentiment analysis engine is employed to infer emotions from the user's input. If the user expresses confusion, the tone of the information presentation changes, and details about the risks of the promises are added. Conversely, if the emotion is positive, the candidate's strengths are emphasized.

[0202] As a concrete example, suppose a user enters a question about a candidate's education policy via a terminal at an election-related event held at a local shopping mall. If the user's question is positive, the system will highlight and present examples of successful education policies.

[0203] An example of a prompt for a generative AI model might be, "Suggest how to explain success stories to a user who has asked a positive question about a candidate's education policy." Based on this prompt, the system will consider the optimal way to present the information.

[0204] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0205] Step 1:

[0206] The server collects candidate information from online sources. Specifically, it uses the Twitter API and news APIs to retrieve data. The input is candidate-related information publicly available on the internet, and the output is stored on the server in raw data form. The collected information is then prepared for analysis in the next processing step.

[0207] Step 2:

[0208] The server analyzes the collected data using natural language processing techniques. Specifically, it uses Spacy or NLTK to tokenize, tag parts of speech, and classify candidates' promises and achievements. The input for this step is the raw data collected in step 1, and the output is the analyzed, structured data. This analyzed data is used for evaluation.

[0209] Step 3:

[0210] The server inputs the analyzed data into a machine learning model and implements an evaluation method to assess the feasibility of the campaign promises. Using libraries such as TensorFlow and PyTorch, it derives evaluation results by comparing them with similar past cases. In this step, the analyzed data obtained in step 2 is used as input, and the output is an evaluation score regarding the feasibility of each candidate's campaign promises.

[0211] Step 4:

[0212] The terminal presents the evaluation results through a user interface. Specifically, it uses an application that visually displays the evaluation score to the user. The user can ask further questions based on the evaluation results. The input for this step is the evaluation score obtained in step 3, and the output is a graphical representation of the evaluation displayed on the user screen.

[0213] Step 5:

[0214] On the device, when the user enters text, the sentiment analysis engine analyzes it. The input is a sentence from the user, and based on this, it infers whether the emotion is positive or negative. This analysis uses a pre-trained sentiment analysis model. The output is evaluation information about the user's emotional state.

[0215] Step 6:

[0216] The server adjusts the information presentation method based on the sentiment analysis results. If positive sentiment is indicated, the information is restructured to emphasize the candidate's success stories and strengths. If negative sentiment is indicated, risks and countermeasures are explained in detail. The input for this step is the sentiment evaluation information obtained in step 5, and the output is the adjusted information presentation.

[0217] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0218] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0219] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0220] [Second Embodiment]

[0221] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0222] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0223] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0224] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0225] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0226] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0227] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0228] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0229] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0230] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0231] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0232] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0233] This invention is specifically implemented as a system for collecting, analyzing, evaluating, and providing information about election candidates from online sources. This system provides important information that voters can use as a reference when voting, based on the promises and achievements presented by the candidates.

[0234] First, the server is equipped with an information gathering module that automatically collects data from the official social media accounts and related news articles of candidates running in elections. This module periodically visits designated information sources and collects new posts and articles.

[0235] Next, the collected data is analyzed on the server using natural language processing technology. This analysis module identifies texts that correspond to pledges, past achievements, political opinions, etc., and classifies them appropriately. Specifically, it analyzes keywords and context within the text and categorizes them according to the relevant information.

[0236] Based on the analyzed data, the server evaluates the feasibility of each candidate's promises. This evaluation is performed using a dataset of past successful policies and machine learning algorithms, and an evaluation score is calculated for each candidate. This score serves as an indicator of the promisingness of a candidate's policies, intended to inform users.

[0237] Next, the terminal displays the evaluation results provided by the server in the user interface. Through this interface, users can view policy comparisons by theme and detailed information on each candidate. The information is visually organized and presented using graphs and charts.

[0238] Furthermore, users can input specific questions about candidates through their terminals, and these questions are sent to the server. The server searches for relevant information based on the submitted questions and interactively generates responses. For example, in response to the question, "I want to know about candidate X's education policies," the user will be provided with information indicating candidate X's policy proposals, past achievements, and feasibility.

[0239] This system allows users to make more informed voting decisions based on comprehensive and reliable information. This process improves the efficiency of access to election information and enhances the quality of democratic decision-making.

[0240] The following describes the processing flow.

[0241] Step 1:

[0242] The server activates an information gathering module and searches for the specified candidate's official social media accounts and related news articles. In this process, APIs and web scraping techniques are used to obtain the latest information based on the candidate's name and related keywords.

[0243] Step 2:

[0244] The server processes the collected text data through a natural language processing engine to analyze its content. This analysis classifies the text into categories such as pledges, achievements, and opinions, and stores the content as structured data in a database.

[0245] Step 3:

[0246] The server inputs the analyzed data into a machine learning model to evaluate the feasibility of the promises. This involves applying a predictive model based on historical datasets to calculate a score indicating whether each promise is realistically achievable.

[0247] Step 4:

[0248] The terminal displays evaluation results obtained from the server in a user interface. When the user selects a specific candidate or policy theme, relevant information is presented in charts and text formats, making it easy to understand intuitively.

[0249] Step 5:

[0250] Users input the information they want to know or specific questions through their device. For example, they might ask, "I want to know more about candidate Y's environmental policies."

[0251] Step 6:

[0252] The server receives inquiries from users and searches for relevant data. Based on the relevant materials and evaluation results, it generates responses to the user's questions and extracts the most relevant information.

[0253] Step 7:

[0254] The terminal displays the response from the server to the user. The information provided includes a detailed analysis of the candidate's policies and past performance, and also displays supplementary materials to aid the user's understanding.

[0255] (Example 1)

[0256] Next, we will describe Example 1. 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."

[0257] The amount of information available about candidates in elections is vast, making it difficult for individual voters to compare it appropriately and make reliable decisions. Therefore, there is a need for a system that efficiently collects and analyzes candidates' pledges and past performance to provide reliable evaluation information. Furthermore, the system needs to be able to accurately respond to specific user questions.

[0258] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0259] In this invention, the server includes data collection means for automatically collecting data about candidates from information sources, data analysis means for analyzing the collected data using natural language processing technology and classifying it based on keywords and context, and data evaluation means for evaluating the feasibility of candidates' promises by comparing them with past success stories based on the analyzed data. This enables users to obtain candidate information efficiently and reliably and make informed choices.

[0260] A "source of information" refers to an online platform or database used to obtain data about a candidate.

[0261] "Data collection means" refers to the function of a system that automatically retrieves data related to a candidate from information sources.

[0262] "Natural language processing technology" refers to the technology that enables computers to understand, analyze, and use human language.

[0263] "Data analysis means" refers to the function of a system that analyzes collected data and classifies it based on specific keywords or context.

[0264] A "data evaluation tool" is a system function that evaluates the feasibility of a candidate's promises by comparing them with past cases based on analyzed data.

[0265] A "generative AI model" is an artificial intelligence system that generates responses in natural language in response to input.

[0266] A "response generation means" is a system function that uses a generation AI model based on user inquiries to search for relevant information and generate answers.

[0267] This invention is a system for automatically collecting, analyzing, and evaluating information about candidates and providing it to users. The following describes embodiments of the system in detail.

[0268] The server first uses an information gathering module to automatically collect data about candidates from multiple sources on the network. Specifically, it analyzes web pages using programming languages ​​and scraping techniques to extract data. Software tools such as Python's Beautiful Soup and Selenium may be used for this process.

[0269] The collected data is analyzed on the server using natural language processing techniques. The server utilizes libraries such as Python's NLTK and spaCy to detect and classify keywords and context within the text data. This makes it possible to organize information such as candidates' pledges and past achievements.

[0270] Subsequently, the server performs a process to evaluate the feasibility of the candidates' promises based on the analyzed data. In this step, machine learning frameworks such as TensorFlow and Scikit-learn can be used to compare the candidates' promises with past successes and calculate an evaluation score.

[0271] The terminal features a user interface that intuitively displays evaluation results generated by the server. The terminal runs in a browser using React.js, allowing users to visually review various policy comparisons and candidate information. D3.js or a similar visualization library is used to draw graphs and charts.

[0272] Users can submit specific questions about candidates they are interested in via their device. These questions are sent to the server as text-based prompts, such as "Please tell me more about candidate Y's economic policies." Based on these questions, the server uses a generative AI model to generate natural language answers based on relevant information and provides them to the user.

[0273] Thus, the present invention enables users to efficiently and accurately grasp candidate information and make informed decisions. This improves access to election information and contributes to strengthening the democratic process.

[0274] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0275] Step 1:

[0276] The server uses an information gathering module to collect data about candidates from multiple online sources. This involves crawling web pages using tools such as Python's Beautiful Soup and Selenium, and extracting text data such as social media posts and news articles. The input is a list of URLs for the information sources, and the output is the retrieved raw text data.

[0277] Step 2:

[0278] The server performs natural language processing on the collected text data. Here, keywords and phrases are extracted from the data using NLTK or spaCy in Python and classified based on the context. The input is the text data collected in Step 1, and the output is the data classified into conventions and past performance. Specifically, the necessary information is identified through morphological analysis and sentence structure analysis.

[0279] Step 3:

[0280] The server evaluates the feasibility of the candidate's convention based on the analyzed data. A machine learning model is built using TensorFlow or Scikit-learn and compared with the past success case data. The input is the analyzed data obtained in Step 2, and the output is the feasibility of the candidate's convention quantified as an evaluation score. This evaluation is realized by the machine learning algorithm reflecting the past data.

[0281] Step 4:

[0282] The terminal displays the evaluation results sent from the server on the user interface. On the terminal side, React.js is used to intuitively present the information on the browser, and the user can easily compare policies and check detailed information. The input is the evaluation score calculated in Step 3, and the output is visually organized graphs and charts.

[0283] Step 5:

[0284] The user inputs questions about the candidates of interest through the terminal. Specific question content is submitted in text form as a prompt sentence. For example, a question like "Please tell me more about candidate X's education policy." At this stage, the user's query is the input, and the output is that the request is sent to the server.

[0285] Step 6:

[0286] Based on the question received from the user, the server uses the generative AI model to search for relevant information and generate an answer in natural language. The input is the prompt text from the user, and the output is the text message as the response. This response is based on the parsed data and additional information search results.

[0287] Step 7:

[0288] The terminal displays the answer generated by the server to the user. The input is the generated response message, and the output is the reaction as a notification or display to the user. This enables the user to quickly access the information they are seeking.

[0289] (Application Example 1)

[0290] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0291] Regarding modern elections, there is a problem that it is difficult for voters to obtain sufficient information about the policies and feasibility of candidates. In addition, there are few opportunities to connect daily consumption activities with political interests, which makes it difficult for citizens to reflect their own choices in political decision-making. There is a need for a system that can solve such problems and enable more voters to take information-based voting actions.

[0292] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0293] In this invention, the server includes information gathering means for collecting candidate information from online information sources, analysis means for analyzing and classifying the collected information using natural language processing, evaluation means for evaluating the feasibility of candidates' promises based on the analyzed information, information providing means for presenting the evaluation results through a user interface, purchase-related information providing means for providing political information related to the user's purchasing behavior, and response generation means for searching for relevant information and generating answers based on user inquiries. This effectively links consumer interests with political information, enabling users to make more informed political decisions.

[0294] "Candidate information" refers to a collection of data that includes election candidates' pledges, past achievements, political opinions, and other relevant information.

[0295] "Online information sources" refer to information sources that exist on the internet, such as websites and social media platforms, from which candidate information can be obtained.

[0296] "Information gathering means" refers to technology or modules used to automatically obtain necessary candidate information from designated online information sources.

[0297] "Natural language processing" is a technique for analyzing collected text data, structuring the data through processes such as keyword extraction, grammatical analysis, and semantic analysis.

[0298] "Analysis means" refers to a technology or module designed to classify and analyze collected candidate information using natural language processing.

[0299] "Evaluation tools" refer to methods or techniques for evaluating the feasibility of a candidate's promises based on analyzed information.

[0300] A "user interface" is a visual display method for presenting information and receiving user input, and includes charts, graphs, and other visual elements.

[0301] "Purchase-related information provision means" refers to methods or technologies for providing users with political information on topics related to their consumer behavior.

[0302] "Response generation means" refers to a technology or module for generating a response to a user inquiry based on relevant information.

[0303] Embodiments of this invention are embodied in a system that collects data on election candidates from online information sources and provides relevant political information according to the user's consumption behavior.

[0304] The server automatically collects candidate information from online sources using an information gathering module. This process utilizes web scraping techniques and API access to obtain text data from candidates' official websites and social media accounts. The collected data is processed by an analysis module on the server, which uses natural language processing techniques to classify and evaluate candidates' promises and achievements. The natural language processing techniques used here include keyword extraction, text classification, and sentiment analysis.

[0305] The server then uses machine learning algorithms to evaluate the feasibility of the analyzed information. In this process, it calculates a candidate's score by referring to past policy data and comparing it with the newly obtained information.

[0306] The terminal displays evaluation results provided by the server through a user interface. The evaluation information is presented in a visually easy-to-understand format using charts and graphs, allowing users to easily access detailed information about candidates and compare policies on different themes.

[0307] Furthermore, the system processes information related to users' purchasing behavior on the server side and provides political information through a purchase-related information provision mechanism. In this process, relevant policy information is recommended based on the electronic payment history, and users are given the opportunity to delve deeper into topics of interest to them.

[0308] As a specific example, when a user purchases organic food using a terminal, information about candidates who disclose the environmental policies related to the food is notified as related information. At this time, the notified information includes a visual display, which makes it easier to understand. In addition, this system can also respond to user inquiries using a generative AI model.

[0309] Example of a prompt sentence:

[0310] "I would like to know more about the latest environmental policies related to the purchase of organic food. Please provide information for comparing the proposals of candidates."

[0311] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0312] Step 1:

[0313] The server collects candidate information from online information sources. Using APIs and web scraping technologies, it periodically crawls specified social media and news sites to obtain new articles and posts. The input to this process is the URL or API endpoint of each information source, and the output is raw text data.

[0314] Step 2:

[0315] The server analyzes the collected raw text data using natural language processing techniques. It extracts keywords and performs context analysis from the text to identify conventions and performance information, and classifies them by category. The input to this process is text data, and the output is a structured information set.

[0316] Step 3:

[0317] The server applies a machine learning model to evaluate the feasibility of each candidate's promises based on the analyzed information. It compares the input information with similar past promise data and calculates an evaluation score for each candidate. The input to this process is a structured set of information, and the output is the evaluation score.

[0318] Step 4:

[0319] The terminal visually displays the evaluation results received from the server through a user interface. Graphs and charts are used to present candidate information and evaluations to the user in an intuitive way. The input to this process is the evaluation score, and the output is visual information for the user.

[0320] Step 5:

[0321] The server analyzes relevant purchase information based on the user's electronic payment history and transmits relevant political information to the terminal using a purchase-related information provision system. It searches for policies related to the purchased category and provides the user with that policy information. The input to this process is the electronic payment history, and the output is relevant policy information.

[0322] Step 6:

[0323] Users can ask specific questions through their device. These questions are sent to a server, where a generative AI model searches for relevant information and generates a response. An example of a prompt might be, "I would like to learn more about the latest environmental policies related to purchasing organic food. Please provide information comparing the proposals of the candidates." The input to this process is the user's question, and the output is the generated response.

[0324] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0325] This invention is implemented in a form that combines a conventional AI system for collecting and analyzing information on election candidates with an emotion engine that recognizes the user's emotions. When providing voters with information about candidates' promises and achievements, this system takes the user's emotional state into consideration, providing a more interactive experience.

[0326] The server first collects data from candidates' online information sources. The information gathering module retrieves the latest information on candidates via APIs from social media and news sites. As soon as this data is collected, it is analyzed using a natural language processing engine and classified as the candidate's promises and achievements. Then, it is evaluated by a machine learning model to predict the likelihood of the promises actually being fulfilled.

[0327] Once the data has been collected and analyzed, it is presented to the user on the terminal. When the user enters a question or inquiry, the system analyzes the input using an emotion engine to recognize the user's emotional state. The emotion engine infers emotions from the input text, identifying states such as favorable, anxious, or suspicious, and adjusts the way information is presented accordingly.

[0328] Specifically, the server adjusts the tone and level of detail of the information based on the emotions the user feels when entering a question. For example, if the user expresses concern or anxiety, more detailed explanations about the risks and disruptive factors of the promises will be added. If the user expresses positive emotions, information about the candidate's strengths and achievements will be emphasized.

[0329] Furthermore, emotional data provided by users is returned to the system as feedback. This allows the server to analyze user interaction trends and use that information to improve future information delivery methods. This feedback loop improves the overall performance of the system.

[0330] This invention allows users to receive information tailored to their emotional state, supporting them in making more meaningful decisions. This design provides the system with a more personalized experience.

[0331] The following describes the processing flow.

[0332] Step 1:

[0333] The server utilizes an information gathering module to collect data from the official social media accounts and news sites of designated candidates. This collection is performed regularly, with the update frequency increased during election periods. The collected data includes posts containing candidates' pledges and statements of opinion, as well as news articles.

[0334] Step 2:

[0335] The server analyzes the collected data through a natural language processing engine. This engine categorizes the text data into groups such as pledges, achievements, and opinions, identifying keywords and phrases and storing them in a database. The analysis results are then used in subsequent evaluation processes.

[0336] Step 3:

[0337] The server uses a machine learning model to evaluate the feasibility of candidates' promises based on the analyzed data. This model utilizes predictive algorithms based on past performance and similar cases to calculate a score for the feasibility of each promise. The evaluation results are stored in a database and used to provide information to users.

[0338] Step 4:

[0339] The terminal displays the analysis and evaluation results obtained from the server to the user. The user interface is designed to show publicly available information for each candidate in list or graph format, allowing users to easily search for details about policy areas and candidates that interest them.

[0340] Step 5:

[0341] Users enter their questions and concerns in text format through the displayed interface. This input may include questions about a specific candidate's policies or instructions regarding comparison criteria.

[0342] Step 6:

[0343] The server passes user input to the emotion engine, which analyzes the emotional state of the entered text. The analyzed emotional state is categorized into common emotion categories (joy, anger, surprise, etc.) and reflected in the information provided.

[0344] Step 7:

[0345] The server takes the emotion engine's output into account and adjusts the information to match the user's emotional state. For example, if an emotion indicating anxiety is detected, detailed and reassuring explanations will be provided when presenting information.

[0346] Step 8:

[0347] The terminal displays the server's generated response to the user. Sentiment-sensitive explanations and recommended candidate information are provided in a visually easy-to-understand format to support the user's decision-making.

[0348] Step 9:

[0349] Users make decisions regarding candidate selection based on information obtained through system interaction. They can also contribute to system improvement by using the feedback function to submit evaluations of the information provided by the system.

[0350] (Example 2)

[0351] Next, we will describe Example 2. 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".

[0352] In providing information about election candidates, there is a need for a system that can present personalized information in accordance with each user's emotional state and interactions. Conventional information provision methods have made it difficult to support users in making optimal decisions by providing uniform information without considering the user's emotions. Therefore, the present invention aims to provide a system that individualizes information and takes user emotions into consideration.

[0353] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0354] In this invention, the server includes means for collecting candidate information from information sources, means for analyzing and classifying the collected information using language analysis technology, and means for analyzing the emotional state from the user's input and adjusting the method of presenting information according to that emotion. This makes it possible to provide information that takes the user's emotional state into consideration.

[0355] "Candidate information" refers to all information about a candidate in an election, including their campaign promises, past achievements, online posts, and media coverage.

[0356] "Information sources" is a general term for media and platforms that provide data on the internet, including social networking services (SNS), news sites, and blogs.

[0357] "Means" refers to the methods or processes used to achieve a specific objective, or the devices or programs used to implement them.

[0358] "Language analysis technology" refers to techniques for analyzing text data written in natural language and structuring, classifying, and understanding the information contained within it.

[0359] A "user" refers to an individual or group that utilizes the information provision system, typically consisting of voters or related stakeholders who require election information.

[0360] "Emotional state" refers to the emotional response or mental state a user exhibits in response to a particular situation or information, and includes feelings such as favorability, anxiety, and doubt.

[0361] "Information provision" refers to the process of presenting analyzed data and evaluation results in a format that is easy for users to understand.

[0362] "Personalization" refers to the method of providing information and services that are individually tailored to the needs, preferences, and emotions of each user.

[0363] This invention is an AI system for providing users with information about election candidates, and its configuration includes functions for information gathering, language analysis, sentiment analysis, and personalized information provision.

[0364] The server collects data about election candidates from internet sources. These sources include social media and news sites, and the server retrieves data using APIs and RSS feeds. After retrieval, the server uses natural language processing techniques to classify data about candidates' promises and achievements, and then uses machine learning frameworks such as TensorFlow and PyTorch to analyze it.

[0365] Next, the server uses the analyzed data to evaluate whether the candidate's promises are feasible. This evaluation involves comparisons with similar past cases and machine learning-based prediction methods.

[0366] The terminal provides an interface for users to access information. Users can input questions and inquiries into the system through the terminal. At this time, the server analyzes the input and activates an emotion engine to recognize the user's emotional state. Through this emotion analysis, the server understands the emotions expressed by the user (e.g., affection, anxiety, suspicion, etc.) and adjusts how information is presented.

[0367] As a concrete example, if a user enters the text "Please tell me about the recent election candidates' promises. I would like to know the likelihood of those promises being fulfilled," the server will first analyze this request and retrieve and present information accordingly. If the user expresses concerns, a detailed analysis of the risks will be provided; if they express positive sentiments, the candidates' strengths will be highlighted.

[0368] Furthermore, emotional data obtained from users is returned to the system as feedback. The server uses this data to analyze trends in user interaction and improve future information delivery methods. This enhances personalized information delivery, allowing users to receive information that helps them make better decisions.

[0369] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0370] Step 1:

[0371] The server collects data about candidates from online sources such as social media and news sites. Input is raw data obtained via APIs and RSS feeds. This data includes information related to candidates' statements, news articles, election promises, and past performance. Output is data formatted for information analysis.

[0372] Step 2:

[0373] The server inputs the collected data into a natural language processing engine. The input data undergoes processing such as tokenization, part-of-speech tagging, and entity recognition. This allows for more accurate classification of candidates' promises and achievements. The output consists of structured data and information categorized for each candidate.

[0374] Step 3:

[0375] The server evaluates the feasibility of the campaign promises using a machine learning model based on the analyzed information. The input is the data organized in step 2. The model uses historical datasets to perform data calculations to predict the likelihood of a candidate's promises succeeding. The output is the feasibility evaluation result for each candidate's promises.

[0376] Step 4:

[0377] The terminal displays the evaluation results from the server on the user interface, providing information to the user. The input is the evaluation results obtained in step 3. The terminal presents the information in text, graphs, and tables to facilitate understanding. The output of this step is an interactive information display that the user can use.

[0378] Step 5:

[0379] The user enters questions or inquiries in text format based on the displayed information. The input is text information from the user. The server receives this input, analyzes it with an emotion engine, and infers the user's emotions. The output is the analysis result regarding the user's emotional state.

[0380] Step 6:

[0381] The server adjusts the tone and level of detail of the information presented based on the user's sentiment analysis results. The input is the result of the sentiment analysis in step 5. Specifically, if the user shows anxiety, additional explanations are added, and if they show positive emotions, the candidate's success stories are highlighted. The output is the adjusted content and presentation of the information.

[0382] Step 7:

[0383] The server uses sentiment data collected from users as a feedback loop to improve future information delivery methods. The input is the user's sentiment tendency data obtained in step 6. This improves the overall system performance. The output is a data-driven suggestion for improving future information delivery methods.

[0384] (Application Example 2)

[0385] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0386] In providing information about election candidates, a challenge is that conventional information presentation methods fail to consider the emotional state of individual users, leading to reduced information acceptability and reliability when users understand and make decisions based on that information. Furthermore, there is a lack of mechanisms to improve information presentation using user feedback.

[0387] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0388] In this invention, the server includes information gathering means for collecting candidate information from online information sources, analysis means for analyzing and classifying the collected information using natural language processing, and emotion analysis means for analyzing the user's emotions on a smart device and adjusting the information presentation based on the results. This makes it possible to provide appropriate information according to the user's emotions.

[0389] "Information gathering methods" refer to mechanisms for collecting candidate information from online sources.

[0390] "Analysis method" refers to the process of analyzing and classifying collected information using natural language processing technology.

[0391] "Evaluation methods" refer to methods for assessing the feasibility of fulfilling campaign promises based on analyzed candidate information.

[0392] "Information provision means" refers to means of presenting evaluation results through a user interface.

[0393] A "response generation means" is a function that searches for relevant information in response to a user's inquiry and generates an answer.

[0394] "Emotion analysis means" refers to a process for analyzing a user's emotions on a smart device and adjusting the information presented based on the results.

[0395] This invention is a system for efficiently collecting information about election candidates and providing that information to users in a personalized manner. The server first collects candidate information from online sources. In this process, it obtains a large amount of data using the Twitter API and news API.

[0396] The collected data is analyzed using natural language processing libraries such as Spacy and NLTK to classify candidates' promises and achievements. During this analysis process, machine learning libraries such as TensorFlow and PyTorch are used to evaluate the feasibility of fulfilling the promises.

[0397] On the device (such as the user's smartphone), information is presented through a user interface. To analyze the user's emotional state, text input is used for sentiment analysis. A sentiment analysis engine is employed to infer emotions from the user's input. If the user expresses confusion, the tone of the information presentation changes, and details about the risks of the promises are added. Conversely, if the emotion is positive, the candidate's strengths are emphasized.

[0398] As a concrete example, suppose a user enters a question about a candidate's education policy via a terminal at an election-related event held at a local shopping mall. If the user's question is positive, the system will highlight and present examples of successful education policies.

[0399] An example of a prompt for a generative AI model might be, "Suggest how to explain success stories to a user who has asked a positive question about a candidate's education policy." Based on this prompt, the system will consider the optimal way to present the information.

[0400] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0401] Step 1:

[0402] The server collects candidate information from online sources. Specifically, it uses the Twitter API and news APIs to retrieve data. The input is candidate-related information publicly available on the internet, and the output is stored on the server in raw data form. The collected information is then prepared for analysis in the next processing step.

[0403] Step 2:

[0404] The server analyzes the collected data using natural language processing techniques. Specifically, it uses Spacy or NLTK to tokenize, tag parts of speech, and classify candidates' promises and achievements. The input for this step is the raw data collected in step 1, and the output is the analyzed, structured data. This analyzed data is used for evaluation.

[0405] Step 3:

[0406] The server inputs the analyzed data into a machine learning model and implements an evaluation method to assess the feasibility of the campaign promises. Using libraries such as TensorFlow and PyTorch, it derives evaluation results by comparing them with similar past cases. In this step, the analyzed data obtained in step 2 is used as input, and the output is an evaluation score regarding the feasibility of each candidate's campaign promises.

[0407] Step 4:

[0408] The terminal presents the evaluation results through a user interface. Specifically, it uses an application that visually displays the evaluation score to the user. The user can ask further questions based on the evaluation results. The input for this step is the evaluation score obtained in step 3, and the output is a graphical representation of the evaluation displayed on the user screen.

[0409] Step 5:

[0410] On the device, when the user enters text, the sentiment analysis engine analyzes it. The input is a sentence from the user, and based on this, it infers whether the emotion is positive or negative. This analysis uses a pre-trained sentiment analysis model. The output is evaluation information about the user's emotional state.

[0411] Step 6:

[0412] The server adjusts the information presentation method based on the sentiment analysis results. If positive sentiment is indicated, the information is restructured to emphasize the candidate's success stories and strengths. If negative sentiment is indicated, risks and countermeasures are explained in detail. The input for this step is the sentiment evaluation information obtained in step 5, and the output is the adjusted information presentation.

[0413] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0414] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0415] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0416] [Third Embodiment]

[0417] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0418] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0419] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0420] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0421] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0422] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0423] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0424] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0425] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0426] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0427] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0428] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0429] This invention is specifically implemented as a system for collecting, analyzing, evaluating, and providing information about election candidates from online sources. This system provides important information that voters can use as a reference when voting, based on the promises and achievements presented by the candidates.

[0430] First, the server is equipped with an information gathering module that automatically collects data from the official social media accounts and related news articles of candidates running in elections. This module periodically visits designated information sources and collects new posts and articles.

[0431] Next, the collected data is analyzed on the server using natural language processing technology. This analysis module identifies texts that correspond to pledges, past achievements, political opinions, etc., and classifies them appropriately. Specifically, it analyzes keywords and context within the text and categorizes them according to the relevant information.

[0432] Based on the analyzed data, the server evaluates the feasibility of each candidate's promises. This evaluation is performed using a dataset of past successful policies and machine learning algorithms, and an evaluation score is calculated for each candidate. This score serves as an indicator of the promisingness of a candidate's policies, intended to inform users.

[0433] Next, the terminal displays the evaluation results provided by the server in the user interface. Through this interface, users can view policy comparisons by theme and detailed information on each candidate. The information is visually organized and presented using graphs and charts.

[0434] Furthermore, users can input specific questions about candidates through their terminals, and these questions are sent to the server. The server searches for relevant information based on the submitted questions and interactively generates responses. For example, in response to the question, "I want to know about candidate X's education policies," the user will be provided with information indicating candidate X's policy proposals, past achievements, and feasibility.

[0435] This system allows users to make more informed voting decisions based on comprehensive and reliable information. This process improves the efficiency of access to election information and enhances the quality of democratic decision-making.

[0436] The following describes the processing flow.

[0437] Step 1:

[0438] The server activates an information gathering module and searches for the specified candidate's official social media accounts and related news articles. In this process, APIs and web scraping techniques are used to obtain the latest information based on the candidate's name and related keywords.

[0439] Step 2:

[0440] The server processes the collected text data through a natural language processing engine to analyze its content. This analysis classifies the text into categories such as pledges, achievements, and opinions, and stores the content as structured data in a database.

[0441] Step 3:

[0442] The server inputs the analyzed data into a machine learning model to evaluate the feasibility of the promises. This involves applying a predictive model based on historical datasets to calculate a score indicating whether each promise is realistically achievable.

[0443] Step 4:

[0444] The terminal displays evaluation results obtained from the server in a user interface. When the user selects a specific candidate or policy theme, relevant information is presented in charts and text formats, making it easy to understand intuitively.

[0445] Step 5:

[0446] Users input the information they want to know or specific questions through their device. For example, they might ask, "I want to know more about candidate Y's environmental policies."

[0447] Step 6:

[0448] The server receives inquiries from users and searches for relevant data. Based on the relevant materials and evaluation results, it generates responses to the user's questions and extracts the most relevant information.

[0449] Step 7:

[0450] The terminal displays the response from the server to the user. The information provided includes a detailed analysis of the candidate's policies and past performance, and also displays supplementary materials to aid the user's understanding.

[0451] (Example 1)

[0452] Next, we will describe Example 1. 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."

[0453] The amount of information available about candidates in elections is vast, making it difficult for individual voters to compare it appropriately and make reliable decisions. Therefore, there is a need for a system that efficiently collects and analyzes candidates' pledges and past performance to provide reliable evaluation information. Furthermore, the system needs to be able to accurately respond to specific user questions.

[0454] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0455] In this invention, the server includes data collection means for automatically collecting data about candidates from information sources, data analysis means for analyzing the collected data using natural language processing technology and classifying it based on keywords and context, and data evaluation means for evaluating the feasibility of candidates' promises by comparing them with past success stories based on the analyzed data. This enables users to obtain candidate information efficiently and reliably and make informed choices.

[0456] A "source of information" refers to an online platform or database used to obtain data about a candidate.

[0457] "Data collection means" refers to the function of a system that automatically retrieves data related to a candidate from information sources.

[0458] "Natural language processing technology" refers to the technology that enables computers to understand, analyze, and use human language.

[0459] "Data analysis means" refers to the function of a system that analyzes collected data and classifies it based on specific keywords or context.

[0460] A "data evaluation tool" is a system function that evaluates the feasibility of a candidate's promises by comparing them with past cases based on analyzed data.

[0461] A "generative AI model" is an artificial intelligence system that generates responses in natural language in response to input.

[0462] A "response generation means" is a system function that uses a generation AI model based on user inquiries to search for relevant information and generate answers.

[0463] This invention is a system for automatically collecting, analyzing, and evaluating information about candidates and providing it to users. The following describes embodiments of the system in detail.

[0464] The server first uses an information gathering module to automatically collect data about candidates from multiple sources on the network. Specifically, it analyzes web pages using programming languages ​​and scraping techniques to extract data. Software tools such as Python's Beautiful Soup and Selenium may be used for this process.

[0465] The collected data is analyzed on the server using natural language processing techniques. The server utilizes libraries such as Python's NLTK and spaCy to detect and classify keywords and context within the text data. This makes it possible to organize information such as candidates' pledges and past achievements.

[0466] Subsequently, the server performs a process to evaluate the feasibility of the candidates' promises based on the analyzed data. In this step, machine learning frameworks such as TensorFlow and Scikit-learn can be used to compare the candidates' promises with past successes and calculate an evaluation score.

[0467] The terminal features a user interface that intuitively displays evaluation results generated by the server. The terminal runs in a browser using React.js, allowing users to visually review various policy comparisons and candidate information. D3.js or a similar visualization library is used to draw graphs and charts.

[0468] Users can submit specific questions about candidates they are interested in via their device. These questions are sent to the server as text-based prompts, such as "Please tell me more about candidate Y's economic policies." Based on these questions, the server uses a generative AI model to generate natural language answers based on relevant information and provides them to the user.

[0469] Thus, the present invention enables users to efficiently and accurately grasp candidate information and make informed decisions. This improves access to election information and contributes to strengthening the democratic process.

[0470] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0471] Step 1:

[0472] The server uses an information gathering module to collect data about candidates from multiple online sources. This involves crawling web pages using tools such as Python's Beautiful Soup and Selenium, and extracting text data such as social media posts and news articles. The input is a list of URLs for the information sources, and the output is the retrieved raw text data.

[0473] Step 2:

[0474] The server performs natural language processing on the collected text data. Here, it uses Python's NLTK and spaCy to extract keywords and phrases from the data and classify them based on context. The input is the text data collected in step 1, and the output is data classified as pledges or past performance. Specifically, it identifies necessary information through morphological analysis and sentence structure analysis.

[0475] Step 3:

[0476] The server evaluates the feasibility of candidates' promises based on the analyzed data. It builds machine learning models using TensorFlow and Scikit-learn and compares them to past success stories. The input is the analyzed data obtained in step 2, and the output is the feasibility of the candidates' promises, quantified as an evaluation score. This evaluation is achieved by the machine learning algorithm reflecting past data.

[0477] Step 4:

[0478] The terminal displays the evaluation results sent from the server on the user interface. The terminal uses React.js to intuitively present information in the browser, allowing users to easily compare policies and view detailed information. The input is the evaluation score calculated in step 3, and the output is a visually organized graph or chart.

[0479] Step 5:

[0480] The user enters questions about candidates they are interested in through their terminal. The specific question is submitted as a text prompt. For example, "Please tell me more about Candidate X's educational policies." At this stage, the user's query is the input, and the request sent to the server is the output.

[0481] Step 6:

[0482] The server uses a generative AI model to search for relevant information based on the user's question and generates a natural language response. The input is a prompt from the user, and the output is a text message as a response. This response is based on the analyzed data and additional information found.

[0483] Step 7:

[0484] The terminal displays the server-generated response to the user. The input is the generated response message, and the output is the response as a notification or display to the user. This allows the user to quickly access the information they are looking for.

[0485] (Application Example 1)

[0486] Next, we will explain Application Example 1. In the following explanation, 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."

[0487] A problem with modern elections is that voters often lack sufficient information about candidates' policies and feasibility. Furthermore, the limited opportunities to connect everyday consumer activities with political concerns make it difficult for citizens to reflect their choices in political decision-making. There is a need for a system that addresses these challenges and enables more voters to make informed decisions.

[0488] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0489] In this invention, the server includes information gathering means for collecting candidate information from online information sources, analysis means for analyzing and classifying the collected information using natural language processing, evaluation means for evaluating the feasibility of candidates' promises based on the analyzed information, information providing means for presenting the evaluation results through a user interface, purchase-related information providing means for providing political information related to the user's purchasing behavior, and response generation means for searching for relevant information and generating answers based on user inquiries. This effectively links consumer interests with political information, enabling users to make more informed political decisions.

[0490] "Candidate information" refers to a collection of data that includes election candidates' pledges, past achievements, political opinions, and other relevant information.

[0491] "Online information sources" refer to information sources that exist on the internet, such as websites and social media platforms, from which candidate information can be obtained.

[0492] "Information gathering means" refers to technology or modules used to automatically obtain necessary candidate information from designated online information sources.

[0493] "Natural language processing" is a technique for analyzing collected text data, structuring the data through processes such as keyword extraction, grammatical analysis, and semantic analysis.

[0494] "Analysis means" refers to a technology or module designed to classify and analyze collected candidate information using natural language processing.

[0495] "Evaluation tools" refer to methods or techniques for evaluating the feasibility of a candidate's promises based on analyzed information.

[0496] A "user interface" is a visual display method for presenting information and receiving user input, and includes charts, graphs, and other visual elements.

[0497] "Purchase-related information provision means" refers to methods or technologies for providing users with political information on topics related to their consumer behavior.

[0498] "Response generation means" refers to a technology or module for generating a response to a user inquiry based on relevant information.

[0499] Embodiments of this invention are embodied in a system that collects data on election candidates from online information sources and provides relevant political information according to the user's consumption behavior.

[0500] The server automatically collects candidate information from online sources using an information gathering module. This process utilizes web scraping techniques and API access to obtain text data from candidates' official websites and social media accounts. The collected data is processed by an analysis module on the server, which uses natural language processing techniques to classify and evaluate candidates' promises and achievements. The natural language processing techniques used here include keyword extraction, text classification, and sentiment analysis.

[0501] The server then uses machine learning algorithms to evaluate the feasibility of the analyzed information. In this process, it calculates a candidate's score by referring to past policy data and comparing it with the newly obtained information.

[0502] The terminal displays evaluation results provided by the server through a user interface. The evaluation information is presented in a visually easy-to-understand format using charts and graphs, allowing users to easily access detailed information about candidates and compare policies on different themes.

[0503] Furthermore, the system processes information related to users' purchasing behavior on the server side and provides political information through a purchase-related information provision mechanism. In this process, relevant policy information is recommended based on the electronic payment history, and users are given the opportunity to delve deeper into topics of interest to them.

[0504] As a concrete example, when a user purchases organic food using a terminal, they will be notified of relevant information, including information about candidates who advocate environmental policies related to that food. This information includes visual representations to facilitate understanding. Furthermore, this system can also respond to user inquiries using a generative AI model.

[0505] Example of a prompt:

[0506] "I would like to learn more about the latest environmental policies related to purchasing organic food. Please provide information to compare the candidates' proposals."

[0507] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0508] Step 1:

[0509] The server collects candidate information from online sources. Using APIs and web scraping techniques, it periodically crawls specified social media and news sites to retrieve new articles and posts. The input to this process is the URL or API endpoint of each source, and the output is raw text data.

[0510] Step 2:

[0511] The server analyzes the collected raw text data using natural language processing techniques. It extracts keywords and performs contextual analysis from the text to identify promises and achievements, and then classifies them into categories. The input to this process is text data, and the output is a structured information set.

[0512] Step 3:

[0513] The server applies a machine learning model to evaluate the feasibility of each candidate's promises based on the analyzed information. It compares the input information with similar past promise data and calculates an evaluation score for each candidate. The input to this process is a structured set of information, and the output is the evaluation score.

[0514] Step 4:

[0515] The terminal visually displays the evaluation results received from the server through a user interface. Graphs and charts are used to present candidate information and evaluations to the user in an intuitive way. The input to this process is the evaluation score, and the output is visual information for the user.

[0516] Step 5:

[0517] The server analyzes relevant purchase information based on the user's electronic payment history and transmits relevant political information to the terminal using a purchase-related information provision system. It searches for policies related to the purchased category and provides the user with that policy information. The input to this process is the electronic payment history, and the output is relevant policy information.

[0518] Step 6:

[0519] Users can ask specific questions through their device. These questions are sent to a server, where a generative AI model searches for relevant information and generates a response. An example of a prompt might be, "I would like to learn more about the latest environmental policies related to purchasing organic food. Please provide information comparing the proposals of the candidates." The input to this process is the user's question, and the output is the generated response.

[0520] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0521] This invention is implemented in a form that combines a conventional AI system for collecting and analyzing information on election candidates with an emotion engine that recognizes the user's emotions. When providing voters with information about candidates' promises and achievements, this system takes the user's emotional state into consideration, providing a more interactive experience.

[0522] The server first collects data from candidates' online information sources. The information gathering module retrieves the latest information on candidates via APIs from social media and news sites. As soon as this data is collected, it is analyzed using a natural language processing engine and classified as the candidate's promises and achievements. Then, it is evaluated by a machine learning model to predict the likelihood of the promises actually being fulfilled.

[0523] Once the data has been collected and analyzed, it is presented to the user on the terminal. When the user enters a question or inquiry, the system analyzes the input using an emotion engine to recognize the user's emotional state. The emotion engine infers emotions from the input text, identifying states such as favorable, anxious, or suspicious, and adjusts the way information is presented accordingly.

[0524] Specifically, the server adjusts the tone and level of detail of the information based on the emotions the user feels when entering a question. For example, if the user expresses concern or anxiety, more detailed explanations about the risks and disruptive factors of the promises will be added. If the user expresses positive emotions, information about the candidate's strengths and achievements will be emphasized.

[0525] Furthermore, emotional data provided by users is returned to the system as feedback. This allows the server to analyze user interaction trends and use that information to improve future information delivery methods. This feedback loop improves the overall performance of the system.

[0526] This invention allows users to receive information tailored to their emotional state, supporting them in making more meaningful decisions. This design provides the system with a more personalized experience.

[0527] The following describes the processing flow.

[0528] Step 1:

[0529] The server utilizes an information gathering module to collect data from the official social media accounts and news sites of designated candidates. This collection is performed regularly, with the update frequency increased during election periods. The collected data includes posts containing candidates' pledges and statements of opinion, as well as news articles.

[0530] Step 2:

[0531] The server analyzes the collected data through a natural language processing engine. This engine categorizes the text data into groups such as pledges, achievements, and opinions, identifying keywords and phrases and storing them in a database. The analysis results are then used in subsequent evaluation processes.

[0532] Step 3:

[0533] The server uses a machine learning model to evaluate the feasibility of candidates' promises based on the analyzed data. This model utilizes predictive algorithms based on past performance and similar cases to calculate a score for the feasibility of each promise. The evaluation results are stored in a database and used to provide information to users.

[0534] Step 4:

[0535] The terminal displays the analysis and evaluation results obtained from the server to the user. The user interface is designed to show publicly available information for each candidate in list or graph format, allowing users to easily search for details about policy areas and candidates that interest them.

[0536] Step 5:

[0537] Users enter their questions and concerns in text format through the displayed interface. This input may include questions about a specific candidate's policies or instructions regarding comparison criteria.

[0538] Step 6:

[0539] The server passes user input to the emotion engine, which analyzes the emotional state of the entered text. The analyzed emotional state is categorized into common emotion categories (joy, anger, surprise, etc.) and reflected in the information provided.

[0540] Step 7:

[0541] The server takes the emotion engine's output into account and adjusts the information to match the user's emotional state. For example, if an emotion indicating anxiety is detected, detailed and reassuring explanations will be provided when presenting information.

[0542] Step 8:

[0543] The terminal displays the server's generated response to the user. Sentiment-sensitive explanations and recommended candidate information are provided in a visually easy-to-understand format to support the user's decision-making.

[0544] Step 9:

[0545] Users make decisions regarding candidate selection based on information obtained through system interaction. They can also contribute to system improvement by using the feedback function to submit evaluations of the information provided by the system.

[0546] (Example 2)

[0547] Next, we will describe Example 2. 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."

[0548] In providing information about election candidates, there is a need for a system that can present personalized information in accordance with each user's emotional state and interactions. Conventional information provision methods have made it difficult to support users in making optimal decisions by providing uniform information without considering the user's emotions. Therefore, the present invention aims to provide a system that individualizes information and takes user emotions into consideration.

[0549] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0550] In this invention, the server includes means for collecting candidate information from information sources, means for analyzing and classifying the collected information using language analysis technology, and means for analyzing the emotional state from the user's input and adjusting the method of presenting information according to that emotion. This makes it possible to provide information that takes the user's emotional state into consideration.

[0551] "Candidate information" refers to all information about a candidate in an election, including their campaign promises, past achievements, online posts, and media coverage.

[0552] "Information sources" is a general term for media and platforms that provide data on the internet, including social networking services (SNS), news sites, and blogs.

[0553] "Means" refers to the methods or processes used to achieve a specific objective, or the devices or programs used to implement them.

[0554] "Language analysis technology" refers to techniques for analyzing text data written in natural language and structuring, classifying, and understanding the information contained within it.

[0555] A "user" refers to an individual or group that utilizes the information provision system, typically consisting of voters or related stakeholders who require election information.

[0556] "Emotional state" refers to the emotional response or mental state a user exhibits in response to a particular situation or information, and includes feelings such as favorability, anxiety, and doubt.

[0557] "Information provision" refers to the process of presenting analyzed data and evaluation results in a format that is easy for users to understand.

[0558] "Personalization" refers to the method of providing information and services that are individually tailored to the needs, preferences, and emotions of each user.

[0559] This invention is an AI system for providing users with information about election candidates, and its configuration includes functions for information gathering, language analysis, sentiment analysis, and personalized information provision.

[0560] The server collects data about election candidates from internet sources. These sources include social media and news sites, and the server retrieves data using APIs and RSS feeds. After retrieval, the server uses natural language processing techniques to classify data about candidates' promises and achievements, and then uses machine learning frameworks such as TensorFlow and PyTorch to analyze it.

[0561] Next, the server uses the analyzed data to evaluate whether the candidate's promises are feasible. This evaluation involves comparisons with similar past cases and machine learning-based prediction methods.

[0562] The terminal provides an interface for users to access information. Users can input questions and inquiries into the system through the terminal. At this time, the server analyzes the input and activates an emotion engine to recognize the user's emotional state. Through this emotion analysis, the server understands the emotions expressed by the user (e.g., affection, anxiety, suspicion, etc.) and adjusts how information is presented.

[0563] As a concrete example, if a user enters the text "Please tell me about the recent election candidates' promises. I would like to know the likelihood of those promises being fulfilled," the server will first analyze this request and retrieve and present information accordingly. If the user expresses concerns, a detailed analysis of the risks will be provided; if they express positive sentiments, the candidates' strengths will be highlighted.

[0564] Furthermore, emotional data obtained from users is returned to the system as feedback. The server uses this data to analyze trends in user interaction and improve future information delivery methods. This enhances personalized information delivery, allowing users to receive information that helps them make better decisions.

[0565] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0566] Step 1:

[0567] The server collects data about candidates from online sources such as social media and news sites. Input is raw data obtained via APIs and RSS feeds. This data includes information related to candidates' statements, news articles, election promises, and past performance. Output is data formatted for information analysis.

[0568] Step 2:

[0569] The server inputs the collected data into a natural language processing engine. The input data undergoes processing such as tokenization, part-of-speech tagging, and entity recognition. This allows for more accurate classification of candidates' promises and achievements. The output consists of structured data and information categorized for each candidate.

[0570] Step 3:

[0571] The server evaluates the feasibility of the campaign promises using a machine learning model based on the analyzed information. The input is the data organized in step 2. The model uses historical datasets to perform data calculations to predict the likelihood of a candidate's promises succeeding. The output is the feasibility evaluation result for each candidate's promises.

[0572] Step 4:

[0573] The terminal displays the evaluation results from the server on the user interface, providing information to the user. The input is the evaluation results obtained in step 3. The terminal presents the information in text, graphs, and tables to facilitate understanding. The output of this step is an interactive information display that the user can use.

[0574] Step 5:

[0575] The user enters questions or inquiries in text format based on the displayed information. The input is text information from the user. The server receives this input, analyzes it with an emotion engine, and infers the user's emotions. The output is the analysis result regarding the user's emotional state.

[0576] Step 6:

[0577] The server adjusts the tone and level of detail of the information presented based on the user's sentiment analysis results. The input is the result of the sentiment analysis in step 5. Specifically, if the user shows anxiety, additional explanations are added, and if they show positive emotions, the candidate's success stories are highlighted. The output is the adjusted content and presentation of the information.

[0578] Step 7:

[0579] The server uses sentiment data collected from users as a feedback loop to improve future information delivery methods. The input is the user's sentiment tendency data obtained in step 6. This improves the overall system performance. The output is a data-driven suggestion for improving future information delivery methods.

[0580] (Application Example 2)

[0581] Next, we will explain application example 2. In the following explanation, 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."

[0582] In providing information about election candidates, a challenge is that conventional information presentation methods fail to consider the emotional state of individual users, leading to reduced information acceptability and reliability when users understand and make decisions based on that information. Furthermore, there is a lack of mechanisms to improve information presentation using user feedback.

[0583] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0584] In this invention, the server includes information gathering means for collecting candidate information from online information sources, analysis means for analyzing and classifying the collected information using natural language processing, and emotion analysis means for analyzing the user's emotions on a smart device and adjusting the information presentation based on the results. This makes it possible to provide appropriate information according to the user's emotions.

[0585] "Information gathering methods" refer to mechanisms for collecting candidate information from online sources.

[0586] "Analysis method" refers to the process of analyzing and classifying collected information using natural language processing technology.

[0587] "Evaluation methods" refer to methods for assessing the feasibility of fulfilling campaign promises based on analyzed candidate information.

[0588] "Information provision means" refers to means of presenting evaluation results through a user interface.

[0589] A "response generation means" is a function that searches for relevant information in response to a user's inquiry and generates an answer.

[0590] "Emotion analysis means" refers to a process for analyzing a user's emotions on a smart device and adjusting the information presented based on the results.

[0591] This invention is a system for efficiently collecting information about election candidates and providing that information to users in a personalized manner. The server first collects candidate information from online sources. In this process, it obtains a large amount of data using the Twitter API and news API.

[0592] The collected data is analyzed using natural language processing libraries such as Spacy and NLTK to classify candidates' promises and achievements. During this analysis process, machine learning libraries such as TensorFlow and PyTorch are used to evaluate the feasibility of fulfilling the promises.

[0593] On the device (such as the user's smartphone), information is presented through a user interface. To analyze the user's emotional state, text input is used for sentiment analysis. A sentiment analysis engine is employed to infer emotions from the user's input. If the user expresses confusion, the tone of the information presentation changes, and details about the risks of the promises are added. Conversely, if the emotion is positive, the candidate's strengths are emphasized.

[0594] As a concrete example, suppose a user enters a question about a candidate's education policy via a terminal at an election-related event held at a local shopping mall. If the user's question is positive, the system will highlight and present examples of successful education policies.

[0595] An example of a prompt for a generative AI model might be, "Suggest how to explain success stories to a user who has asked a positive question about a candidate's education policy." Based on this prompt, the system will consider the optimal way to present the information.

[0596] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0597] Step 1:

[0598] The server collects candidate information from online sources. Specifically, it uses the Twitter API and news APIs to retrieve data. The input is candidate-related information publicly available on the internet, and the output is stored on the server in raw data form. The collected information is then prepared for analysis in the next processing step.

[0599] Step 2:

[0600] The server analyzes the collected data using natural language processing techniques. Specifically, it uses Spacy or NLTK to tokenize, tag parts of speech, and classify candidates' promises and achievements. The input for this step is the raw data collected in step 1, and the output is the analyzed, structured data. This analyzed data is used for evaluation.

[0601] Step 3:

[0602] The server inputs the analyzed data into a machine learning model and implements an evaluation method to assess the feasibility of the campaign promises. Using libraries such as TensorFlow and PyTorch, it derives evaluation results by comparing them with similar past cases. In this step, the analyzed data obtained in step 2 is used as input, and the output is an evaluation score regarding the feasibility of each candidate's campaign promises.

[0603] Step 4:

[0604] The terminal presents the evaluation results through a user interface. Specifically, it uses an application that visually displays the evaluation score to the user. The user can ask further questions based on the evaluation results. The input for this step is the evaluation score obtained in step 3, and the output is a graphical representation of the evaluation displayed on the user screen.

[0605] Step 5:

[0606] On the device, when the user enters text, the sentiment analysis engine analyzes it. The input is a sentence from the user, and based on this, it infers whether the emotion is positive or negative. This analysis uses a pre-trained sentiment analysis model. The output is evaluation information about the user's emotional state.

[0607] Step 6:

[0608] The server adjusts the information presentation method based on the sentiment analysis results. If positive sentiment is indicated, the information is restructured to emphasize the candidate's success stories and strengths. If negative sentiment is indicated, risks and countermeasures are explained in detail. The input for this step is the sentiment evaluation information obtained in step 5, and the output is the adjusted information presentation.

[0609] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0610] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0611] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0612] [Fourth Embodiment]

[0613] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0614] As shown in Figure 7, the 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.

[0615] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0616] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0617] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0618] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0619] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0620] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0621] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0622] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0623] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0624] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0625] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0626] This invention is specifically implemented as a system for collecting, analyzing, evaluating, and providing information about election candidates from online sources. This system provides important information that voters can use as a reference when voting, based on the promises and achievements presented by the candidates.

[0627] First, the server is equipped with an information gathering module that automatically collects data from the official social media accounts and related news articles of candidates running in elections. This module periodically visits designated information sources and collects new posts and articles.

[0628] Next, the collected data is analyzed on the server using natural language processing technology. This analysis module identifies texts that correspond to pledges, past achievements, political opinions, etc., and classifies them appropriately. Specifically, it analyzes keywords and context within the text and categorizes them according to the relevant information.

[0629] Based on the analyzed data, the server evaluates the feasibility of each candidate's promises. This evaluation is performed using a dataset of past successful policies and machine learning algorithms, and an evaluation score is calculated for each candidate. This score serves as an indicator of the promisingness of a candidate's policies, intended to inform users.

[0630] Next, the terminal displays the evaluation results provided by the server in the user interface. Through this interface, users can view policy comparisons by theme and detailed information on each candidate. The information is visually organized and presented using graphs and charts.

[0631] Furthermore, users can input specific questions about candidates through their terminals, and these questions are sent to the server. The server searches for relevant information based on the submitted questions and interactively generates responses. For example, in response to the question, "I want to know about candidate X's education policies," the user will be provided with information indicating candidate X's policy proposals, past achievements, and feasibility.

[0632] This system allows users to make more informed voting decisions based on comprehensive and reliable information. This process improves the efficiency of access to election information and enhances the quality of democratic decision-making.

[0633] The following describes the processing flow.

[0634] Step 1:

[0635] The server activates an information gathering module and searches for the specified candidate's official social media accounts and related news articles. In this process, APIs and web scraping techniques are used to obtain the latest information based on the candidate's name and related keywords.

[0636] Step 2:

[0637] The server processes the collected text data through a natural language processing engine to analyze its content. This analysis classifies the text into categories such as pledges, achievements, and opinions, and stores the content as structured data in a database.

[0638] Step 3:

[0639] The server inputs the analyzed data into a machine learning model to evaluate the feasibility of the promises. This involves applying a predictive model based on historical datasets to calculate a score indicating whether each promise is realistically achievable.

[0640] Step 4:

[0641] The terminal displays evaluation results obtained from the server in a user interface. When the user selects a specific candidate or policy theme, relevant information is presented in charts and text formats, making it easy to understand intuitively.

[0642] Step 5:

[0643] Users input the information they want to know or specific questions through their device. For example, they might ask, "I want to know more about candidate Y's environmental policies."

[0644] Step 6:

[0645] The server receives inquiries from users and searches for relevant data. Based on the relevant materials and evaluation results, it generates responses to the user's questions and extracts the most relevant information.

[0646] Step 7:

[0647] The terminal displays the response from the server to the user. The information provided includes a detailed analysis of the candidate's policies and past performance, and also displays supplementary materials to aid the user's understanding.

[0648] (Example 1)

[0649] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0650] The amount of information available about candidates in elections is vast, making it difficult for individual voters to compare it appropriately and make reliable decisions. Therefore, there is a need for a system that efficiently collects and analyzes candidates' pledges and past performance to provide reliable evaluation information. Furthermore, the system needs to be able to accurately respond to specific user questions.

[0651] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0652] In this invention, the server includes data collection means for automatically collecting data about candidates from information sources, data analysis means for analyzing the collected data using natural language processing technology and classifying it based on keywords and context, and data evaluation means for evaluating the feasibility of candidates' promises by comparing them with past success stories based on the analyzed data. This enables users to obtain candidate information efficiently and reliably and make informed choices.

[0653] A "source of information" refers to an online platform or database used to obtain data about a candidate.

[0654] "Data collection means" refers to the function of a system that automatically retrieves data related to a candidate from information sources.

[0655] "Natural language processing technology" refers to the technology that enables computers to understand, analyze, and use human language.

[0656] "Data analysis means" refers to the function of a system that analyzes collected data and classifies it based on specific keywords or context.

[0657] A "data evaluation tool" is a system function that evaluates the feasibility of a candidate's promises by comparing them with past cases based on analyzed data.

[0658] A "generative AI model" is an artificial intelligence system that generates responses in natural language in response to input.

[0659] A "response generation means" is a system function that uses a generation AI model based on user inquiries to search for relevant information and generate answers.

[0660] This invention is a system for automatically collecting, analyzing, and evaluating information about candidates and providing it to users. The following describes embodiments of the system in detail.

[0661] The server first uses an information gathering module to automatically collect data about candidates from multiple sources on the network. Specifically, it analyzes web pages using programming languages ​​and scraping techniques to extract data. Software tools such as Python's Beautiful Soup and Selenium may be used for this process.

[0662] The collected data is analyzed on the server using natural language processing techniques. The server utilizes libraries such as Python's NLTK and spaCy to detect and classify keywords and context within the text data. This makes it possible to organize information such as candidates' pledges and past achievements.

[0663] Subsequently, the server performs a process to evaluate the feasibility of the candidates' promises based on the analyzed data. In this step, machine learning frameworks such as TensorFlow and Scikit-learn can be used to compare the candidates' promises with past successes and calculate an evaluation score.

[0664] The terminal features a user interface that intuitively displays evaluation results generated by the server. The terminal runs in a browser using React.js, allowing users to visually review various policy comparisons and candidate information. D3.js or a similar visualization library is used to draw graphs and charts.

[0665] Users can submit specific questions about candidates they are interested in via their device. These questions are sent to the server as text-based prompts, such as "Please tell me more about candidate Y's economic policies." Based on these questions, the server uses a generative AI model to generate natural language answers based on relevant information and provides them to the user.

[0666] Thus, the present invention enables users to efficiently and accurately grasp candidate information and make informed decisions. This improves access to election information and contributes to strengthening the democratic process.

[0667] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0668] Step 1:

[0669] The server uses an information gathering module to collect data about candidates from multiple online sources. This involves crawling web pages using tools such as Python's Beautiful Soup and Selenium, and extracting text data such as social media posts and news articles. The input is a list of URLs for the information sources, and the output is the retrieved raw text data.

[0670] Step 2:

[0671] The server performs natural language processing on the collected text data. Here, it uses Python's NLTK and spaCy to extract keywords and phrases from the data and classify them based on context. The input is the text data collected in step 1, and the output is data classified as pledges or past performance. Specifically, it identifies necessary information through morphological analysis and sentence structure analysis.

[0672] Step 3:

[0673] The server evaluates the feasibility of candidates' promises based on the analyzed data. It builds machine learning models using TensorFlow and Scikit-learn and compares them to past success stories. The input is the analyzed data obtained in step 2, and the output is the feasibility of the candidates' promises, quantified as an evaluation score. This evaluation is achieved by the machine learning algorithm reflecting past data.

[0674] Step 4:

[0675] The terminal displays the evaluation results sent from the server on the user interface. The terminal uses React.js to intuitively present information in the browser, allowing users to easily compare policies and view detailed information. The input is the evaluation score calculated in step 3, and the output is a visually organized graph or chart.

[0676] Step 5:

[0677] The user enters questions about candidates they are interested in through their terminal. The specific question is submitted as a text prompt. For example, "Please tell me more about Candidate X's educational policies." At this stage, the user's query is the input, and the request sent to the server is the output.

[0678] Step 6:

[0679] The server uses a generative AI model to search for relevant information based on the user's question and generates a natural language response. The input is a prompt from the user, and the output is a text message as a response. This response is based on the analyzed data and additional information found.

[0680] Step 7:

[0681] The terminal displays the server-generated response to the user. The input is the generated response message, and the output is the response as a notification or display to the user. This allows the user to quickly access the information they are looking for.

[0682] (Application Example 1)

[0683] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0684] A problem with modern elections is that voters often lack sufficient information about candidates' policies and feasibility. Furthermore, the limited opportunities to connect everyday consumer activities with political concerns make it difficult for citizens to reflect their choices in political decision-making. There is a need for a system that addresses these challenges and enables more voters to make informed decisions.

[0685] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0686] In this invention, the server includes information gathering means for collecting candidate information from online information sources, analysis means for analyzing and classifying the collected information using natural language processing, evaluation means for evaluating the feasibility of candidates' promises based on the analyzed information, information providing means for presenting the evaluation results through a user interface, purchase-related information providing means for providing political information related to the user's purchasing behavior, and response generation means for searching for relevant information and generating answers based on user inquiries. This effectively links consumer interests with political information, enabling users to make more informed political decisions.

[0687] "Candidate information" refers to a collection of data that includes election candidates' pledges, past achievements, political opinions, and other relevant information.

[0688] "Online information sources" refer to information sources that exist on the internet, such as websites and social media platforms, from which candidate information can be obtained.

[0689] "Information gathering means" refers to technology or modules used to automatically obtain necessary candidate information from designated online information sources.

[0690] "Natural language processing" is a technique for analyzing collected text data, structuring the data through processes such as keyword extraction, grammatical analysis, and semantic analysis.

[0691] "Analysis means" refers to a technology or module designed to classify and analyze collected candidate information using natural language processing.

[0692] "Evaluation tools" refer to methods or techniques for evaluating the feasibility of a candidate's promises based on analyzed information.

[0693] A "user interface" is a visual display method for presenting information and receiving user input, and includes charts, graphs, and other visual elements.

[0694] "Purchase-related information provision means" refers to methods or technologies for providing users with political information on topics related to their consumer behavior.

[0695] "Response generation means" refers to a technology or module for generating a response to a user inquiry based on relevant information.

[0696] Embodiments of this invention are embodied in a system that collects data on election candidates from online information sources and provides relevant political information according to the user's consumption behavior.

[0697] The server automatically collects candidate information from online sources using an information gathering module. This process utilizes web scraping techniques and API access to obtain text data from candidates' official websites and social media accounts. The collected data is processed by an analysis module on the server, which uses natural language processing techniques to classify and evaluate candidates' promises and achievements. The natural language processing techniques used here include keyword extraction, text classification, and sentiment analysis.

[0698] The server then uses machine learning algorithms to evaluate the feasibility of the analyzed information. In this process, it calculates a candidate's score by referring to past policy data and comparing it with the newly obtained information.

[0699] The terminal displays evaluation results provided by the server through a user interface. The evaluation information is presented in a visually easy-to-understand format using charts and graphs, allowing users to easily access detailed information about candidates and compare policies on different themes.

[0700] Furthermore, the system processes information related to users' purchasing behavior on the server side and provides political information through a purchase-related information provision mechanism. In this process, relevant policy information is recommended based on the electronic payment history, and users are given the opportunity to delve deeper into topics of interest to them.

[0701] As a concrete example, when a user purchases organic food using a terminal, they will be notified of relevant information, including information about candidates who advocate environmental policies related to that food. This information includes visual representations to facilitate understanding. Furthermore, this system can also respond to user inquiries using a generative AI model.

[0702] Example of a prompt:

[0703] "I would like to learn more about the latest environmental policies related to purchasing organic food. Please provide information to compare the candidates' proposals."

[0704] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0705] Step 1:

[0706] The server collects candidate information from online sources. Using APIs and web scraping techniques, it periodically crawls specified social media and news sites to retrieve new articles and posts. The input to this process is the URL or API endpoint of each source, and the output is raw text data.

[0707] Step 2:

[0708] The server analyzes the collected raw text data using natural language processing techniques. It extracts keywords and performs contextual analysis from the text to identify promises and achievements, and then classifies them into categories. The input to this process is text data, and the output is a structured information set.

[0709] Step 3:

[0710] The server applies a machine learning model to evaluate the feasibility of each candidate's promises based on the analyzed information. It compares the input information with similar past promise data and calculates an evaluation score for each candidate. The input to this process is a structured set of information, and the output is the evaluation score.

[0711] Step 4:

[0712] The terminal visually displays the evaluation results received from the server through a user interface. Graphs and charts are used to present candidate information and evaluations to the user in an intuitive way. The input to this process is the evaluation score, and the output is visual information for the user.

[0713] Step 5:

[0714] The server analyzes relevant purchase information based on the user's electronic payment history and transmits relevant political information to the terminal using a purchase-related information provision system. It searches for policies related to the purchased category and provides the user with that policy information. The input to this process is the electronic payment history, and the output is relevant policy information.

[0715] Step 6:

[0716] Users can ask specific questions through their device. These questions are sent to a server, where a generative AI model searches for relevant information and generates a response. An example of a prompt might be, "I would like to learn more about the latest environmental policies related to purchasing organic food. Please provide information comparing the proposals of the candidates." The input to this process is the user's question, and the output is the generated response.

[0717] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0718] This invention is implemented in a form that combines a conventional AI system for collecting and analyzing information on election candidates with an emotion engine that recognizes the user's emotions. When providing voters with information about candidates' promises and achievements, this system takes the user's emotional state into consideration, providing a more interactive experience.

[0719] The server first collects data from candidates' online information sources. The information gathering module retrieves the latest information on candidates via APIs from social media and news sites. As soon as this data is collected, it is analyzed using a natural language processing engine and classified as the candidate's promises and achievements. Then, it is evaluated by a machine learning model to predict the likelihood of the promises actually being fulfilled.

[0720] Once the data has been collected and analyzed, it is presented to the user on the terminal. When the user enters a question or inquiry, the system analyzes the input using an emotion engine to recognize the user's emotional state. The emotion engine infers emotions from the input text, identifying states such as favorable, anxious, or suspicious, and adjusts the way information is presented accordingly.

[0721] Specifically, the server adjusts the tone and level of detail of the information based on the emotions the user feels when entering a question. For example, if the user expresses concern or anxiety, more detailed explanations about the risks and disruptive factors of the promises will be added. If the user expresses positive emotions, information about the candidate's strengths and achievements will be emphasized.

[0722] Furthermore, emotional data provided by users is returned to the system as feedback. This allows the server to analyze user interaction trends and use that information to improve future information delivery methods. This feedback loop improves the overall performance of the system.

[0723] This invention allows users to receive information tailored to their emotional state, supporting them in making more meaningful decisions. This design provides the system with a more personalized experience.

[0724] The following describes the processing flow.

[0725] Step 1:

[0726] The server utilizes an information gathering module to collect data from the official social media accounts and news sites of designated candidates. This collection is performed regularly, with the update frequency increased during election periods. The collected data includes posts containing candidates' pledges and statements of opinion, as well as news articles.

[0727] Step 2:

[0728] The server analyzes the collected data through a natural language processing engine. This engine categorizes the text data into groups such as pledges, achievements, and opinions, identifying keywords and phrases and storing them in a database. The analysis results are then used in subsequent evaluation processes.

[0729] Step 3:

[0730] The server uses a machine learning model to evaluate the feasibility of candidates' promises based on the analyzed data. This model utilizes predictive algorithms based on past performance and similar cases to calculate a score for the feasibility of each promise. The evaluation results are stored in a database and used to provide information to users.

[0731] Step 4:

[0732] The terminal displays the analysis and evaluation results obtained from the server to the user. The user interface is designed to show publicly available information for each candidate in list or graph format, allowing users to easily search for details about policy areas and candidates that interest them.

[0733] Step 5:

[0734] Users enter their questions and concerns in text format through the displayed interface. This input may include questions about a specific candidate's policies or instructions regarding comparison criteria.

[0735] Step 6:

[0736] The server passes user input to the emotion engine, which analyzes the emotional state of the entered text. The analyzed emotional state is categorized into common emotion categories (joy, anger, surprise, etc.) and reflected in the information provided.

[0737] Step 7:

[0738] The server takes the emotion engine's output into account and adjusts the information to match the user's emotional state. For example, if an emotion indicating anxiety is detected, detailed and reassuring explanations will be provided when presenting information.

[0739] Step 8:

[0740] The terminal displays the server's generated response to the user. Sentiment-sensitive explanations and recommended candidate information are provided in a visually easy-to-understand format to support the user's decision-making.

[0741] Step 9:

[0742] Users make decisions regarding candidate selection based on information obtained through system interaction. They can also contribute to system improvement by using the feedback function to submit evaluations of the information provided by the system.

[0743] (Example 2)

[0744] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0745] In providing information about election candidates, there is a need for a system that can present personalized information in accordance with each user's emotional state and interactions. Conventional information provision methods have made it difficult to support users in making optimal decisions by providing uniform information without considering the user's emotions. Therefore, the present invention aims to provide a system that individualizes information and takes user emotions into consideration.

[0746] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0747] In this invention, the server includes means for collecting candidate information from information sources, means for analyzing and classifying the collected information using language analysis technology, and means for analyzing the emotional state from the user's input and adjusting the method of presenting information according to that emotion. This makes it possible to provide information that takes the user's emotional state into consideration.

[0748] "Candidate information" refers to all information about a candidate in an election, including their campaign promises, past achievements, online posts, and media coverage.

[0749] "Information sources" is a general term for media and platforms that provide data on the internet, including social networking services (SNS), news sites, and blogs.

[0750] "Means" refers to the methods or processes used to achieve a specific objective, or the devices or programs used to implement them.

[0751] "Language analysis technology" refers to techniques for analyzing text data written in natural language and structuring, classifying, and understanding the information contained within it.

[0752] A "user" refers to an individual or group that utilizes the information provision system, typically consisting of voters or related stakeholders who require election information.

[0753] "Emotional state" refers to the emotional response or mental state a user exhibits in response to a particular situation or information, and includes feelings such as favorability, anxiety, and doubt.

[0754] "Information provision" refers to the process of presenting analyzed data and evaluation results in a format that is easy for users to understand.

[0755] "Personalization" refers to the method of providing information and services that are individually tailored to the needs, preferences, and emotions of each user.

[0756] This invention is an AI system for providing users with information about election candidates, and its configuration includes functions for information gathering, language analysis, sentiment analysis, and personalized information provision.

[0757] The server collects data about election candidates from internet sources. These sources include social media and news sites, and the server retrieves data using APIs and RSS feeds. After retrieval, the server uses natural language processing techniques to classify data about candidates' promises and achievements, and then uses machine learning frameworks such as TensorFlow and PyTorch to analyze it.

[0758] Next, the server uses the analyzed data to evaluate whether the candidate's promises are feasible. This evaluation involves comparisons with similar past cases and machine learning-based prediction methods.

[0759] The terminal provides an interface for users to access information. Users can input questions and inquiries into the system through the terminal. At this time, the server analyzes the input and activates an emotion engine to recognize the user's emotional state. Through this emotion analysis, the server understands the emotions expressed by the user (e.g., affection, anxiety, suspicion, etc.) and adjusts how information is presented.

[0760] As a concrete example, if a user enters the text "Please tell me about the recent election candidates' promises. I would like to know the likelihood of those promises being fulfilled," the server will first analyze this request and retrieve and present information accordingly. If the user expresses concerns, a detailed analysis of the risks will be provided; if they express positive sentiments, the candidates' strengths will be highlighted.

[0761] Furthermore, emotional data obtained from users is returned to the system as feedback. The server uses this data to analyze trends in user interaction and improve future information delivery methods. This enhances personalized information delivery, allowing users to receive information that helps them make better decisions.

[0762] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0763] Step 1:

[0764] The server collects data about candidates from online sources such as social media and news sites. Input is raw data obtained via APIs and RSS feeds. This data includes information related to candidates' statements, news articles, election promises, and past performance. Output is data formatted for information analysis.

[0765] Step 2:

[0766] The server inputs the collected data into a natural language processing engine. The input data undergoes processing such as tokenization, part-of-speech tagging, and entity recognition. This allows for more accurate classification of candidates' promises and achievements. The output consists of structured data and information categorized for each candidate.

[0767] Step 3:

[0768] The server evaluates the feasibility of the campaign promises using a machine learning model based on the analyzed information. The input is the data organized in step 2. The model uses historical datasets to perform data calculations to predict the likelihood of a candidate's promises succeeding. The output is the feasibility evaluation result for each candidate's promises.

[0769] Step 4:

[0770] The terminal displays the evaluation results from the server on the user interface, providing information to the user. The input is the evaluation results obtained in step 3. The terminal presents the information in text, graphs, and tables to facilitate understanding. The output of this step is an interactive information display that the user can use.

[0771] Step 5:

[0772] The user enters questions or inquiries in text format based on the displayed information. The input is text information from the user. The server receives this input, analyzes it with an emotion engine, and infers the user's emotions. The output is the analysis result regarding the user's emotional state.

[0773] Step 6:

[0774] The server adjusts the tone and level of detail of the information presented based on the user's sentiment analysis results. The input is the result of the sentiment analysis in step 5. Specifically, if the user shows anxiety, additional explanations are added, and if they show positive emotions, the candidate's success stories are highlighted. The output is the adjusted content and presentation of the information.

[0775] Step 7:

[0776] The server uses sentiment data collected from users as a feedback loop to improve future information delivery methods. The input is the user's sentiment tendency data obtained in step 6. This improves the overall system performance. The output is a data-driven suggestion for improving future information delivery methods.

[0777] (Application Example 2)

[0778] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0779] In providing information about election candidates, a challenge is that conventional information presentation methods fail to consider the emotional state of individual users, leading to reduced information acceptability and reliability when users understand and make decisions based on that information. Furthermore, there is a lack of mechanisms to improve information presentation using user feedback.

[0780] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0781] In this invention, the server includes information gathering means for collecting candidate information from online information sources, analysis means for analyzing and classifying the collected information using natural language processing, and emotion analysis means for analyzing the user's emotions on a smart device and adjusting the information presentation based on the results. This makes it possible to provide appropriate information according to the user's emotions.

[0782] "Information gathering methods" refer to mechanisms for collecting candidate information from online sources.

[0783] "Analysis method" refers to the process of analyzing and classifying collected information using natural language processing technology.

[0784] "Evaluation methods" refer to methods for assessing the feasibility of fulfilling campaign promises based on analyzed candidate information.

[0785] "Information provision means" refers to means of presenting evaluation results through a user interface.

[0786] A "response generation means" is a function that searches for relevant information in response to a user's inquiry and generates an answer.

[0787] "Emotion analysis means" refers to a process for analyzing a user's emotions on a smart device and adjusting the information presented based on the results.

[0788] This invention is a system for efficiently collecting information about election candidates and providing that information to users in a personalized manner. The server first collects candidate information from online sources. In this process, it obtains a large amount of data using the Twitter API and news API.

[0789] The collected data is analyzed using natural language processing libraries such as Spacy and NLTK to classify candidates' promises and achievements. During this analysis process, machine learning libraries such as TensorFlow and PyTorch are used to evaluate the feasibility of fulfilling the promises.

[0790] On the device (such as the user's smartphone), information is presented through a user interface. To analyze the user's emotional state, text input is used for sentiment analysis. A sentiment analysis engine is employed to infer emotions from the user's input. If the user expresses confusion, the tone of the information presentation changes, and details about the risks of the promises are added. Conversely, if the emotion is positive, the candidate's strengths are emphasized.

[0791] As a concrete example, suppose a user enters a question about a candidate's education policy via a terminal at an election-related event held at a local shopping mall. If the user's question is positive, the system will highlight and present examples of successful education policies.

[0792] An example of a prompt for a generative AI model might be, "Suggest how to explain success stories to a user who has asked a positive question about a candidate's education policy." Based on this prompt, the system will consider the optimal way to present the information.

[0793] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0794] Step 1:

[0795] The server collects candidate information from online sources. Specifically, it uses the Twitter API and news APIs to retrieve data. The input is candidate-related information publicly available on the internet, and the output is stored on the server in raw data form. The collected information is then prepared for analysis in the next processing step.

[0796] Step 2:

[0797] The server analyzes the collected data using natural language processing techniques. Specifically, it uses Spacy or NLTK to tokenize, tag parts of speech, and classify candidates' promises and achievements. The input for this step is the raw data collected in step 1, and the output is the analyzed, structured data. This analyzed data is used for evaluation.

[0798] Step 3:

[0799] The server inputs the analyzed data into a machine learning model and implements an evaluation method to assess the feasibility of the campaign promises. Using libraries such as TensorFlow and PyTorch, it derives evaluation results by comparing them with similar past cases. In this step, the analyzed data obtained in step 2 is used as input, and the output is an evaluation score regarding the feasibility of each candidate's campaign promises.

[0800] Step 4:

[0801] The terminal presents the evaluation results through a user interface. Specifically, it uses an application that visually displays the evaluation score to the user. The user can ask further questions based on the evaluation results. The input for this step is the evaluation score obtained in step 3, and the output is a graphical representation of the evaluation displayed on the user screen.

[0802] Step 5:

[0803] On the device, when the user enters text, the sentiment analysis engine analyzes it. The input is a sentence from the user, and based on this, it infers whether the emotion is positive or negative. This analysis uses a pre-trained sentiment analysis model. The output is evaluation information about the user's emotional state.

[0804] Step 6:

[0805] The server adjusts the information presentation method based on the sentiment analysis results. If positive sentiment is indicated, the information is restructured to emphasize the candidate's success stories and strengths. If negative sentiment is indicated, risks and countermeasures are explained in detail. The input for this step is the sentiment evaluation information obtained in step 5, and the output is the adjusted information presentation.

[0806] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0807] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0808] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0809] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0810] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. In the upper and lower directions of the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. Also, the upper side of the concentric circles is where "pleasant" emotions are located, and the lower side is where "unpleasant" emotions are located. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0811] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0812] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0813] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0814] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0815] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0816] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0817] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0818] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0819] 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.

[0820] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0821] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0822] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0823] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0824] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0825] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0826] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0827] The following is further disclosed regarding the embodiments described above.

[0828] (Claim 1)

[0829] Information gathering methods that collect candidate information from online sources,

[0830] An analytical means that analyzes and classifies the collected information using natural language processing,

[0831] An evaluation method for assessing the feasibility of a candidate's promises based on analyzed information,

[0832] An information provision means that presents evaluation results through a user interface,

[0833] A response generation means that searches for relevant information based on user inquiries and generates answers,

[0834] A system that includes this.

[0835] (Claim 2)

[0836] The system according to claim 1, comprising means for predicting the feasibility of fulfilling a promise by applying a machine learning model to evaluate collected information and comparing it with similar past cases.

[0837] (Claim 3)

[0838] The system according to claim 1, comprising means for receiving user feedback and analyzing it to improve the overall performance of the system.

[0839] "Example 1"

[0840] (Claim 1)

[0841] A data collection method that automatically collects data about candidates from information sources,

[0842] A data analysis method that uses natural language processing technology to analyze collected data and classifies it based on keywords and context,

[0843] A data evaluation method that assesses the feasibility of a candidate's promises by comparing them to past success stories based on analyzed data,

[0844] A means of presenting information that visually organizes evaluation results and presents them through a user interface,

[0845] A response generation means that receives inquiries from users, searches for relevant information using a generation AI model, and generates answers,

[0846] A system that includes this.

[0847] (Claim 2)

[0848] The system according to claim 1, comprising means for evaluating and predicting the feasibility of a candidate's promises based on past data using machine learning technology.

[0849] (Claim 3)

[0850] The system according to claim 1, comprising means for collecting user feedback and performing analysis to improve the system's performance.

[0851] "Application Example 1"

[0852] (Claim 1)

[0853] Information gathering methods that collect candidate information from online sources,

[0854] An analytical means that analyzes and classifies the collected information using natural language processing,

[0855] An evaluation method for assessing the feasibility of a candidate's promises based on analyzed information,

[0856] An information provision means that presents evaluation results through a user interface,

[0857] A means of providing purchase-related information that provides political information related to the purchase behavior of users,

[0858] A response generation means that searches for relevant information based on user inquiries and generates answers,

[0859] A system that includes this.

[0860] (Claim 2)

[0861] The system according to claim 1, comprising means for predicting the feasibility of fulfilling pledges by applying a machine learning model to evaluate collected information and comparing it with similar past cases, and providing relevant political information based on consumer interests.

[0862] (Claim 3)

[0863] The system according to claim 1, comprising means for receiving user feedback and analyzing it to improve the overall performance of the system.

[0864] "Example 2 of combining an emotion engine"

[0865] (Claim 1)

[0866] Means of collecting candidate information from sources,

[0867] A means of analyzing and classifying collected information using language analysis techniques,

[0868] A means of evaluating the feasibility of a candidate's promises based on the analyzed information,

[0869] A means of presenting the evaluation results through an information display device,

[0870] A means for processing relevant information based on user inquiries and generating responses,

[0871] A means for analyzing the user's emotional state from their input and adjusting the way information is presented according to that emotion,

[0872] A means of collecting user sentiment data, analyzing trends, and improving information delivery methods,

[0873] A system that includes this.

[0874] (Claim 2)

[0875] The system according to claim 1, comprising means for evaluating information using a machine learning model and predicting the feasibility of fulfilling a promise while comparing it with past cases.

[0876] (Claim 3)

[0877] The system according to claim 1, comprising means for analyzing user feedback and improving the overall functionality.

[0878] "Application example 2 when combining with an emotional engine"

[0879] (Claim 1)

[0880] Information gathering methods that collect candidate information from online sources,

[0881] An analytical means that analyzes and classifies the collected information using natural language processing,

[0882] An evaluation method for assessing the feasibility of a candidate's promises based on analyzed information,

[0883] An information provision means that presents evaluation results through a user interface,

[0884] A response generation means that searches for relevant information based on user inquiries and generates answers,

[0885] An emotion analysis means that analyzes the user's emotions on a smart device and adjusts the information presentation based on the results,

[0886] A system that includes this.

[0887] (Claim 2)

[0888] The system according to claim 1, comprising means for predicting the feasibility of fulfilling a promise by applying a machine learning model to evaluate collected information and comparing it with similar past cases.

[0889] (Claim 3)

[0890] The system according to claim 1, comprising means for receiving user feedback and analyzing it to improve the overall performance of the system. [Explanation of Symbols]

[0891] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Information gathering methods that collect candidate information from online sources, An analytical means that analyzes and classifies the collected information using natural language processing, An evaluation method for assessing the feasibility of a candidate's promises based on analyzed information, An information provision means that presents evaluation results through a user interface, A means of providing purchase-related information that provides political information related to the purchase behavior of users, A response generation means that searches for relevant information based on user inquiries and generates answers, A system that includes this.

2. The system according to claim 1, comprising means for predicting the feasibility of fulfilling pledges by applying a machine learning model to evaluate collected information and comparing it with similar past cases, and providing relevant political information based on consumer interests.

3. The system according to claim 1, comprising means for receiving user feedback and analyzing it to improve the overall performance of the system.

Images