system

Abstract

We provide the system. [Solution] A means of automatically collecting election-related information from public institutions, news media, and social networking services, A method for fairly extracting policy information for each candidate by analyzing information collected using natural language processing technology, A means of displaying the analysis results to the user in a customized way via a user interface, A means for generating responses using artificial intelligence technology in response to user questions, Means used to receive user feedback and improve the accuracy of the information provided, 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, which is performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to 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] Since information related to elections is vast and transmitted from various media, it is difficult for voters to efficiently access the information they need. For this reason, there is a problem that it is difficult to provide accurate and unbiased information regarding elections and policies. In addition, it is also an issue to present information in a form that voters can be interested in while minimizing biases and misunderstandings in the provision of election information.

Means for Solving the Problems

[0005] This invention automatically collects election-related information from multiple public institutions, news media, and social networking services, and analyzes it using natural language processing technology to fairly extract policy information for each candidate. Furthermore, it promotes deeper understanding by displaying the analysis results in a customized manner based on the user's interests through a user interface, and by responding to user questions using generative artificial intelligence technology. It also includes functions to improve the accuracy of the information provided based on user feedback, and to detect and reduce bias in election information. This provides voters with a system that allows them to quickly and easily access unbiased and accurate election information.

[0006] "Election-related information" refers to data that voters need when choosing a candidate and deciding who to vote for, such as candidates' policies, electoral district information, and voting methods.

[0007] "Public institutions" refer to organizations that officially provide election information, such as the government and local authorities, and this information includes accurate election data and candidate information.

[0008] "News media" refers to media outlets that report election-related information to the general public, such as newspapers, television, and online news sites.

[0009] A "social networking service" is an online platform for users to share information, and is particularly used as a venue for candidates and political parties to directly disseminate official information.

[0010] "Natural language processing technology" is a technology that enables computers to understand and analyze human language, making it possible to extract meaning and context from large amounts of text data.

[0011] "Generative artificial intelligence technology" is a technology that uses AI to generate answers in natural language to human questions, and is used to obtain information that is easy for humans to understand from complex data.

[0012] A "user interface" refers to the screens and input methods that users use to interact with an information system, and is a means of presenting information through user interaction.

[0013] "Feedback" refers to comments and evaluations that users provide in response to the information offered by the system, and which are used to improve and adjust the system.

[0014] "Bias" refers to the skewness or misleading influence contained in election information, and is a problematic concept as it represents information lacking fairness. [Brief explanation of the drawing]

[0015] [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] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 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 Embodiment 2 when a sentiment engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when a sentiment engine is combined.

Mode for Carrying Out the Invention

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a processor with a reference number (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple 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.

[0019] In the following embodiments, a RAM (Random Access Memory) with a reference number is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] 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.

[0021] 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).

[0022] 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."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] This invention is a system for providing election information to voters efficiently and unbiasedly, and is primarily composed of the interaction of a server, terminals, and users. The server continuously collects election-related data from public institutions, news media, and social networking services during the election period. This data is analyzed on the server using natural language processing technology, and policy information for each candidate is fairly extracted.

[0037] The terminal presents the analysis results received from the server to the user via a user interface. The user interface can adjust the displayed content based on the user's profile, providing information tailored to their interests. This helps users quickly find information on political concerns or specific policies based on their own interests.

[0038] Furthermore, users can directly input questions about the election through their terminal. The server processes this information using artificial intelligence technology to generate responses to the user's questions. These responses provide detailed explanations on election-related topics that the user is curious about.

[0039] Furthermore, users can provide feedback on the accuracy and usefulness of the information provided through their devices. The server collects this feedback and uses it to further improve the accuracy of the information. The feedback also helps to detect potential biases in election information and improve the fairness of information provision.

[0040] As a concrete example, the server collects policy pledges of all candidates in a local election from news media and social networking services and analyzes them through natural language processing. The results of this analysis are then provided via the terminal as detailed information on policy areas of particular interest to the user (e.g., environmental policy or economic policy). The user can input questions about the main differences in each candidate's policies and receive instantly generated responses.

[0041] In this embodiment of the invention, the entire process of collecting, analyzing, presenting, and gathering feedback on election information is carried out seamlessly, enabling voters to gain an accurate and unbiased understanding of the election.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The server automatically collects election-related data from public institutions, news media, and social networking services. It uses web scraping techniques and APIs to obtain large amounts of text data and store it on the server.

[0045] Step 2:

[0046] The server analyzes the collected data using natural language processing technology. It extracts candidate policy information from text data and integrates and organizes data from different sources. The server performs bias checks and collects additional data as needed to ensure unbiased information.

[0047] Step 3:

[0048] The server sends the analysis results to the terminal. The terminal presents the analyzed election information to the user via a user interface. Using the user profile, the information displayed is customized to each user's interests and preferences.

[0049] Step 4:

[0050] Users enter election-related questions they are interested in into the terminal. For example, they can enter questions such as, "What are the key points of candidate A's economic policies?"

[0051] Step 5:

[0052] The device sends the user's question to the server. The server generates a response to the question using generative artificial intelligence technology. The server then sends the response back to the device.

[0053] Step 6:

[0054] The terminal presents the user with the response received from the server. Users can instantly obtain detailed policy information and answers to their questions.

[0055] Step 7:

[0056] The user sends feedback to the server regarding the information provided through their device. This feedback includes evaluations of the accuracy and usefulness of the information.

[0057] Step 8:

[0058] The server aggregates user feedback and modifies the model to improve the accuracy of the information. It also uses the feedback to improve the bias detection algorithm, increasing the fairness of future information provision.

[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] Election-related information is vast and complex, making it difficult for voters to understand it accurately and without bias. Information comes from a wide range of sources, each containing different perspectives and biases, making it challenging to grasp the overall picture. Furthermore, insufficient information tailored to individual user interests and needs hinders the effective use of this information. Therefore, there is a need for a system that efficiently provides voters with the information they need to make informed decisions.

[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 means for automatically collecting information from public institutions, media, and network services; means for analyzing the collected information using natural language processing technology and extracting policy information for each subject; and means for generating responses using artificial intelligence technology in response to inquiries from users. This enables users to obtain election-related information fairly and accurately from diverse sources. Furthermore, by providing information tailored to the individual interests of users, it becomes possible to efficiently acquire the information necessary for decision-making.

[0064] "Information" refers to all election-related data collected from public institutions, media, and network services.

[0065] "Public institutions" refer to organizations and agencies managed and operated by the government or local authorities, and which provide official information related to elections.

[0066] "Media" refers to a medium that distributes information through various platforms, such as newspapers, television, radio, and the internet.

[0067] "Network services" refer to services provided over the internet for information sharing and communication, and specifically include social media platforms.

[0068] "Automated collection" refers to the process by which a system automatically acquires and stores election-related information without human intervention.

[0069] "Natural language processing technology" refers to the technology that enables computers to understand and process human language, and in particular, it refers to methods for text analysis and semantic extraction.

[0070] "Policy information" refers to the detailed content of the policies and measures that election candidates put forward as their campaign promises.

[0071] A "user interface" refers to the screens and operating methods used by a system to exchange information with a user.

[0072] "User" refers to an individual who seeks to obtain election-related information by using this system.

[0073] "Artificial intelligence technology" refers to the technology that allows computers to mimic human intellectual tasks, particularly their ability to answer questions and generate information.

[0074] "Reliability" refers to the degree to which the information provided is accurate and free from errors and biases.

[0075] "Structured data" refers to data that is organized in a format that allows for efficient use and analysis of information.

[0076] This invention is a system for providing election-related information to voters fairly and efficiently. The system is implemented through the interaction of a server, a terminal, and a user.

[0077] First, the server automatically collects information from public institutions, media, and network services. This process uses APIs and web scraping techniques, and periodically collects information using the Python library Requests, storing it in a database. Next, the server analyzes the collected data using natural language processing (NLTK) techniques. Specifically, it tokenizes text data using Python's natural language processing libraries NLTK and spaCy, and extracts policy information for each candidate. The analyzed information is structured in JSON format, enabling efficient data access.

[0078] The terminal presents the analysis results received from the server to the user via a user interface. This user interface is built with HTML / CSS and JavaScript (registered trademark) and customizes the displayed content based on the user's profile information. Users can easily obtain information related to their specific areas of interest using the terminal.

[0079] Furthermore, users can input questions about the election through their terminal. The server receives these questions and generates appropriate responses using a generative AI model. For example, the OpenAI® GPT series is used as a generative AI model. An example of a prompt is, "I would like to know more about candidate A's environmental policies." Based on this prompt, a response is generated and provided to the user.

[0080] Users can also provide feedback on the information provided. This feedback is analyzed on the server to improve the reliability of the information and to help detect and correct bias. Examples of feedback include "I was satisfied with the accuracy of the information" or "I need more details." In this way, the system provides an environment in which voters can accurately understand election-related information and use it to inform their decision-making.

[0081] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0082] Step 1:

[0083] The server automatically collects information from public institutions, media, and network services. It takes API and web data as input and periodically collects data using the Python Requests library. This data is stored in a database, enabling real-time information management. As output, unstructured raw data is stored in the database.

[0084] Step 2:

[0085] The server processes the collected data using natural language processing techniques. It uses raw data from a database as input, tokenizes the text data using Python's NLTK and spaCy, and then cleans and normalizes the data. In particular, it extracts candidate policy information through keyword extraction and contextual analysis. The output is structured policy information data in JSON format.

[0086] Step 3:

[0087] The server structures the information based on the analysis results and stores it in a database. Using the JSON data obtained in the previous step as input, it classifies the information by theme, enabling efficient access. The output is well-organized data that can be efficiently searched.

[0088] Step 4:

[0089] The terminal displays structured data received from the server in a user interface. It receives parsed data from the server as input and displays it on the screen using HTML / CSS and JavaScript. Based on the displayed information, users can view policy information tailored to their interests. The output provides a user-optimized visual interface.

[0090] Step 5:

[0091] The user enters election-related questions through a terminal. The user enters questions in free format as input, and the terminal sends these questions to the server. The user's question data is sent to the server as output.

[0092] Step 6:

[0093] The server provides user questions as prompts to a generative AI model and generates responses. It takes user questions as input and sends them to a generative AI model (e.g., GPT series). The generative AI model generates detailed answers to the questions, and the natural language response is returned to the server as output.

[0094] Step 7:

[0095] The terminal displays the user's response from the generated AI model. It receives AI-generated responses from the server as input and displays them in the user interface. The user can view the presented information and use it to aid in decision-making. As output, the information is presented on the screen in a format that is easy for the user to understand.

[0096] Step 8:

[0097] Users send feedback on the provided information via their devices. The device receives user feedback as input and sends it to the server. The feedback information is then collected on the server as output.

[0098] Step 9:

[0099] The server analyzes the collected feedback to improve the accuracy of the information and correct biases. It takes feedback data as input and uses statistical analysis and machine learning techniques to evaluate the reliability of the information. As output, the improved quality information is reflected back in the database.

[0100] (Application Example 1)

[0101] 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."

[0102] Obtaining information for voters during elections is difficult due to bias, inaccuracies, and information from multiple sources. In particular, the challenge lies in fairly collecting the information necessary for voters to make informed decisions and providing support based on their individual political interests. Furthermore, there is a need to provide reliable information-based guidance on donations to voters who are unsure which candidate or policy to support financially.

[0103] 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.

[0104] This invention includes a server that automatically collects election-related information from public institutions, media outlets, and social networks; a server that analyzes the collected information using natural language processing technology to fairly extract policy information for each candidate; and a server that makes suggestions for donations to specific policies or candidates based on the user's political interests. This enables voters to obtain appropriate and fair information and to support reliable donation activities based on that information.

[0105] "Election-related information" refers to information about candidates' policies and the election process obtained from public institutions, media outlets, and social networks.

[0106] "Natural language processing technology" is a technology that uses computers to analyze, understand, and process human language, making it possible to extract meaning and intent from large amounts of text information.

[0107] A "user interface" is a screen or means of operation through which a user interacts with a system and receives information, and it can customize and present information according to the user's interests and preferences.

[0108] "Generative artificial intelligence technology" is a technology based on artificial intelligence that automatically generates responses and information based on questions and inputs from users.

[0109] "Feedback" refers to opinions and evaluations that users provide regarding the accuracy and usefulness of the information they receive. This information is used to improve services and systems.

[0110] A "donation suggestion" refers to a proposal designed to encourage users to provide financial support to specific policies or candidates, tailored to their political interests.

[0111] The system implementing this invention consists of a cloud server and client terminals (e.g., smartphones and computers). The server automatically collects election-related data from news media, official organizations, and social networks. The collected data is obtained using web scraping techniques with Python. Next, this data is analyzed using SpaCy, a library for natural language processing, to analyze text related to policy information and candidates. The information obtained from the analysis is then filtered based on each user's profile and customized.

[0112] On the device, the application is built with Flutter® and receives information pushed from the server via Firebase. The user interface visually displays information about policies and candidates of interest to the user and supports the acquisition of further detailed information. In addition, generative artificial intelligence technology (e.g., OpenAI's GPT-4®) instantly generates responses to user questions and sends them back to the device.

[0113] Users can make donation decisions based on their interests, focusing on specific candidates or policies suggested by the system, which also provides information to support their decision-making. The collected feedback is used to further improve the accuracy and presentation of the information.

[0114] For example, a user might enter a prompt such as, "Tell me about candidates who support environmentally friendly energy policies." When this prompt is sent to the system, the server analyzes the relevant data and provides the results to the user's terminal, allowing the user to receive detailed policy information through the interface.

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

[0116] Step 1:

[0117] The server automatically collects election-related data from news media, official organizations, and social networks. The input is publicly available election-related information sources on the web, and the output is a collection of this data in text format. Specifically, it uses Python and scraping libraries to efficiently extract the necessary information.

[0118] Step 2:

[0119] The server analyzes the collected data using natural language processing techniques. The input is the collected text data, and the output is structured data containing policy information for each candidate. Specifically, it uses SpaCy to analyze the text and identify and tag key policies and phrases.

[0120] Step 3:

[0121] The server filters the analysis results based on each user's profile. The input consists of analyzed structured data and user profile data, while the output is customized information tailored to the user. Specifically, it extracts and efficiently organizes only the information that matches the user's interests and concerns.

[0122] Step 4:

[0123] The device displays customized information received from the server. The input is information data pushed from the server, and the output is the information displayed on the user interface. Specifically, it receives information via Firebase and displays it graphically on an app built with Flutter.

[0124] Step 5:

[0125] The user enters a specific question through the interface. A prompt (e.g., "Tell me about candidates who support environmentally friendly energy policies") is entered, and additional information is requested based on this.

[0126] Step 6:

[0127] The server generates responses using generative artificial intelligence technology in response to user prompts. The input is the user's prompt, and the output is the response. Specifically, it uses OpenAI's GPT-4 to generate the optimal answer and respond immediately to the user's questions.

[0128] Step 7:

[0129] The user makes a decision to donate to a specific candidate or policy based on the responses and information sent from the server. The input is the presented information and the user's choices, and the output is the donation decision.

[0130] Step 8:

[0131] User feedback is collected via the terminal and sent to the server. Input consists of user ratings, comments, and opinions, while output is this feedback data. The server uses this feedback to analyze and improve the accuracy of the information and the quality of the service.

[0132] 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.

[0133] This invention is a system incorporating an emotion engine to efficiently and fairly provide election-related information to users, and it functions through the interaction of a server, terminal, and user. The server first automatically collects election-related data from public institutions, news media, and social networking services. This data is analyzed using natural language processing technology, and policy information for each candidate is extracted fairly.

[0134] The analysis results are sent from the server to the terminal and presented to the user via the user interface. During this process, the emotion engine recognizes the user's emotions in real time and dynamically adjusts the information displayed. For example, if a user shows a high level of interest in a particular policy, more detailed information related to that policy will be displayed. The emotion engine analyzes the user's emotional data and optimizes the content and presentation of the information provided.

[0135] Users can input election-related questions through their devices, and the server uses generative artificial intelligence technology to generate responses to those questions and present them to the user. In this process, an emotion engine adjusts the tone and level of detail of the response based on the user's emotions. This results in more personalized answers to the specific questions voters have.

[0136] Furthermore, users send feedback to the server regarding the information provided. This feedback is used to improve the overall accuracy of the system and also helps to improve the sentiment engine's algorithms. The sentiment engine helps detect biases hidden in election information.

[0137] For example, if a user wants to research the economic policies of a candidate in a local election, the server collects and analyzes relevant information and displays it on the user's device as customized information through an emotion engine. By continuously assessing the user's interests and reactions, it becomes possible to provide more in-depth and useful information tailored to their attributes. In this way, by combining an emotion engine, it is possible to create an election information delivery environment that is tailored to each user's individual interests and emotions.

[0138] The following describes the processing flow.

[0139] Step 1:

[0140] The server automatically collects election-related data from public institutions, news media, and social networking services. This involves the use of web scraping techniques and APIs, resulting in a large amount of text data being accumulated on the server.

[0141] Step 2:

[0142] The server uses natural language processing technology to analyze the collected data. Policy information about candidates is extracted from the text, and data from different sources is integrated and organized. The bias check process also takes place here.

[0143] Step 3:

[0144] The server sends the analyzed data to the terminal. The terminal then uses a user interface to display the information to the user. During this process, the user's profile information is taken into consideration, and the information is customized according to their individual interests.

[0145] Step 4:

[0146] The device activates an emotion engine to recognize the user's emotional state in real time. The emotion engine analyzes facial expressions, tone of voice, input content, etc., to determine the user's emotions.

[0147] Step 5:

[0148] The user enters election-related questions into a terminal. The terminal sends the input and the user's emotional state to the server.

[0149] Step 6:

[0150] The server uses artificial intelligence technology to generate responses to user questions. The user's emotional state is also taken into consideration, and the responses are tailored based on their individual emotions.

[0151] Step 7:

[0152] The device receives a response from the server and displays the response through the user interface based on the analysis results of the emotion engine. For example, if the user is feeling anxious, the response will be more polite and reassuring.

[0153] Step 8:

[0154] Users submit feedback about the information through their devices. This feedback includes evaluations of the accuracy and usefulness of the information.

[0155] Step 9:

[0156] The server analyzes the feedback to improve the system's accuracy and the sentiment engine's algorithms. This results in improved performance in future information deliveries and reduces bias towards election information.

[0157] (Example 2)

[0158] 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".

[0159] Election-related information is diverse, making it difficult for users to efficiently and fairly obtain information that matches their specific areas of interest. Furthermore, information may be biased or lack the ability to cater to individual user sentiments. This makes it difficult for voters to obtain the information necessary to make informed decisions.

[0160] 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.

[0161] In this invention, the server includes means for automatically collecting election-related information from information sources, means for analyzing the collected information using natural language processing technology and fairly extracting policy information for each candidate, and means for analyzing the user's emotions in real time using emotion recognition technology and dynamically adjusting the information display. This makes it possible to provide users with efficient and personalized election information.

[0162] "Information sources" refers to all sources that provide election-related data, such as public institutions, news media, and social networking services.

[0163] "Natural language processing technology" refers to techniques that enable computers to understand and analyze human language, and includes methods for extracting useful information through the analysis of text data.

[0164] "Emotion recognition technology" refers to technology that analyzes a user's emotional state in real time from their facial expressions and voice, and adjusts the way information is presented based on that analysis.

[0165] "Generative artificial intelligence technology" is a technology that uses artificial intelligence to generate responses in natural human language, making it possible to provide appropriate answers even to complex questions.

[0166] "Feedback" refers to information that includes evaluations and opinions from users regarding the information presented, and is used as data to improve the system and enhance the accuracy of the information.

[0167] "Bias" refers to biases or skews in collected election information, and includes elements that undermine the fairness of the information.

[0168] "Optimization" refers to the process of adjusting the content and format of displayed information based on user interests and emotions to make it as useful as possible for the user.

[0169] This invention is a system that provides election-related information to users efficiently and fairly, and includes information collection, analysis, display, response generation, and collection of user feedback from diverse data sources.

[0170] Data collection and analysis

[0171] The server automatically collects election-related data from sources such as public institutions, news media, and social networking services. This process utilizes web scraping techniques and APIs, such as Python's requests and BeautifulSoup libraries. The collected data is analyzed using natural language processing techniques. Specifically, Python's NLTK and SpaCy are used to analyze text data and fairly extract policy information for each candidate.

[0172] Customized display of information

[0173] The analysis results are sent from the server to the terminal. The user sees the obtained information through the user interface on the terminal. The interface, built with HTML and CSS, visually organizes the information so that the user can easily understand it. Furthermore, the terminal is equipped with emotion recognition technology, which analyzes the user's emotions in real time via OpenCV and the Emotion API and dynamically adjusts the information display.

[0174] Question answering function

[0175] Users can input election-related questions via their terminal. For example, a possible question might be, "Who is most committed to environmental policies in the next local election?" The server uses a generative AI model (e.g., GPT-3®) to generate detailed responses to the input questions and provides the appropriately edited responses to the user via their terminal.

[0176] Feedback and system accuracy improvement

[0177] Users can send feedback on the information provided to the server via their device. This feedback is used to improve the overall system performance and the emotion engine algorithm. Based on user feedback, bias in election information will be reduced, and more accurate and unbiased information will be provided.

[0178] The above describes a specific embodiment of the present invention, in which the system provides users with personalized information and responses, enabling them to access election information more effectively.

[0179] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0180] Step 1:

[0181] Data collection

[0182] The server collects election-related data from sources such as public institutions, news media, and social networking services. Specific API endpoints or web URLs are used as input, and data is retrieved based on these through web scraping or API communication. For example, the Python requests library is used to retrieve the latest information from news sites. The output is raw text data.

[0183] Step 2:

[0184] Data Analysis

[0185] The server analyzes the collected raw data using natural language processing techniques. In this step, important key phrases and policy-related information are extracted from the input data, and policy information for each candidate is compiled. Specifically, Python's NLTK and SpaCy are used to tokenize the text, perform POS tagging, and extract important information. The output is the analyzed policy information.

[0186] Step 3:

[0187] Data transmission and display

[0188] The server sends the analysis results to the terminal. The terminal displays the received data in the user interface. Analyzed policy information is received as input and displayed in a user-friendly format using HTML and CSS. Specifically, the policy information is organized in tables and lists and provided to the user in a visually clear manner. The output is the user's visual display.

[0189] Step 4:

[0190] Emotion recognition and display adjustment

[0191] The device uses emotion recognition technology to analyze the user's emotions in real time from their facial expressions and voice. Data from the camera and microphone is used as input, and analysis is performed using OpenCV and the Emotion API. Based on the user's emotions, the device dynamically adjusts the priority and level of detail of information and updates the displayed content as needed. The output is a customized information display adapted to the user's emotions.

[0192] Step 5:

[0193] Question and Answer Generation

[0194] The user enters an election-related question through the terminal. The input is provided in text format and sent to the server as a prompt. The server generates a response to the question using a generative AI model (e.g., GPT-3). The generative AI model analyzes the question, searches for relevant information, formats it, and creates a natural language answer. The output is text containing the generated answer, which is returned to the terminal and displayed to the user.

[0195] Step 6:

[0196] Feedback gathering and system improvement

[0197] Users can send feedback on the provided information and responses to the server via their terminal. Input consists of ratings and comments, which the server analyzes and uses to improve the system. Specifically, the feedback is text-mined to help fine-tune the algorithm and improve the accuracy of the information. Output consists of insights and suggestions for system improvement.

[0198] (Application Example 2)

[0199] 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".

[0200] In providing election-related information to voters fairly and efficiently, there is a need for methods that dynamically optimize information based on users' emotions and individual interests to support their decision-making process. In particular, information that users can accept is necessary regarding donations and fundraising for election campaigns.

[0201] 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.

[0202] In this invention, the server includes means for automatically collecting election-related information from information providers, news organizations, and information sharing services; means for analyzing the collected information using natural language processing technology and fairly extracting policy information for each candidate; and means for recognizing the user's emotions in real time using sentiment analysis technology and adjusting the display order and level of detail of the information. This enables the system to dynamically display detailed election-related information in the donation system based on the user's emotions and interests, thereby supporting the user's decision-making.

[0203] "Information providers" are public institutions, media outlets, and other major sources of information that provide data related to elections.

[0204] "Natural language processing technology" is a technique that mechanically analyzes text data and organizes and extracts information in a way that humans can understand.

[0205] "Emotion analysis technology" is a technology that recognizes a user's emotions in real time and adjusts the system's operation based on those emotions.

[0206] A "donation system" is a mechanism used in election campaigns to allow users to provide financial support to candidates or policies.

[0207] "Dynamic display" is a function that instantly changes the content and presentation of information based on the user's current interests and emotions.

[0208] "Supporting decision-making" refers to the act of providing information to enable users to make appropriate choices and take appropriate actions based on election-related information.

[0209] To implement this invention, a system is needed in which the server performs the following roles. First, the server automatically collects election-related data from information providers, news organizations, and information sharing services and stores it in a database. This collected data is analyzed using natural language processing technology with Google® Cloud Natural Language API to accurately extract policy information for each candidate.

[0210] Next, the analyzed information is evaluated in real time on the user's device using sentiment analysis technology with Microsoft® Azure® Emotion API. The device dynamically adjusts the display order and level of detail of the information via the user interface according to this sentiment data. As a result, users can obtain a more personalized election information acquisition experience.

[0211] Users can indicate their willingness to donate to election campaigns through a smartphone application and make donation decisions after obtaining relevant policy information. Upon receiving user input, the server utilizes generative artificial intelligence technology, using Google Cloud AI to generate responses to the questions.

[0212] For example, a user might be considering donating to a particular election candidate but wants more detailed information about that candidate's economic policies. In this case, if sentiment analysis detects a high level of interest in that information, it will be provided in a detailed and easy-to-understand format.

[0213] An example of a prompt message is, "Display detailed information on Candidate A's latest economic policies, highlighting information that the user is emotionally interested in." This is expected to make the user's decision-making more confident and supportive.

[0214] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0215] Step 1:

[0216] The server collects election-related data from information providers, news organizations, and information sharing services. The input data is initially unprocessed. The server uses web scraping techniques to retrieve the necessary data and saves it to a database.

[0217] Step 2:

[0218] The server analyzes the stored data using the Google Cloud Natural Language API. Using the election-related text data obtained as input, it fairly extracts policy information for each candidate. The output is organized policy information.

[0219] Step 3:

[0220] The server utilizes the Microsoft Azure Emotion API to evaluate the user's emotions in real time. It receives the user's facial expressions and voice as input data from the device and performs emotion analysis. Based on the results, it determines the priority of information display according to the emotion.

[0221] Step 4:

[0222] The terminal receives analysis results and sentiment data, and displays the information using a user interface. Using policy information and sentiment evaluations from the server as input, it dynamically displays information tailored to the user's interests. This results in output that is easier for the user to understand.

[0223] Step 5:

[0224] Users view election campaign information and make donation decisions on a smartphone application. The application displays detailed information about candidates the user is interested in and allows them to answer additional questions as needed.

[0225] Step 6:

[0226] The server uses generative artificial intelligence technology to generate responses to user questions. It receives user questions as input and creates answers using a generative AI model. The generated answers are output and provided to the user again via the terminal.

[0227] 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.

[0228] 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.

[0229] 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.

[0230] [Second Embodiment]

[0231] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0232] 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.

[0233] 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).

[0234] 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.

[0235] 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.

[0236] 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).

[0237] 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.

[0238] 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.

[0239] 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.

[0240] 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.

[0241] 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.

[0242] 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".

[0243] This invention is a system for providing election information to voters efficiently and unbiasedly, and is primarily composed of the interaction of a server, terminals, and users. The server continuously collects election-related data from public institutions, news media, and social networking services during the election period. This data is analyzed on the server using natural language processing technology, and policy information for each candidate is fairly extracted.

[0244] The terminal presents the analysis results received from the server to the user via a user interface. The user interface can adjust the displayed content based on the user's profile, providing information tailored to their interests. This helps users quickly find information on political concerns or specific policies based on their own interests.

[0245] Furthermore, users can directly input questions about the election through their terminal. The server processes this information using artificial intelligence technology to generate responses to the user's questions. These responses provide detailed explanations on election-related topics that the user is curious about.

[0246] Furthermore, users can provide feedback on the accuracy and usefulness of the information provided through their devices. The server collects this feedback and uses it to further improve the accuracy of the information. The feedback also helps to detect potential biases in election information and improve the fairness of information provision.

[0247] As a concrete example, the server collects policy pledges of all candidates in a local election from news media and social networking services and analyzes them through natural language processing. The results of this analysis are then provided via the terminal as detailed information on policy areas of particular interest to the user (e.g., environmental policy or economic policy). The user can input questions about the main differences in each candidate's policies and receive instantly generated responses.

[0248] In this embodiment of the invention, the entire process of collecting, analyzing, presenting, and gathering feedback on election information is carried out seamlessly, enabling voters to gain an accurate and unbiased understanding of the election.

[0249] The following describes the processing flow.

[0250] Step 1:

[0251] The server automatically collects election-related data from public institutions, news media, and social networking services. It uses web scraping techniques and APIs to obtain large amounts of text data and store it on the server.

[0252] Step 2:

[0253] The server analyzes the collected data using natural language processing technology. It extracts candidate policy information from text data and integrates and organizes data from different sources. The server performs bias checks and collects additional data as needed to ensure unbiased information.

[0254] Step 3:

[0255] The server sends the analysis results to the terminal. The terminal presents the analyzed election information to the user via a user interface. Using the user profile, the information displayed is customized to each user's interests and preferences.

[0256] Step 4:

[0257] Users enter election-related questions they are interested in into the terminal. For example, they can enter questions such as, "What are the key points of candidate A's economic policies?"

[0258] Step 5:

[0259] The device sends the user's question to the server. The server generates a response to the question using generative artificial intelligence technology. The server then sends the response back to the device.

[0260] Step 6:

[0261] The terminal presents the user with the response received from the server. Users can instantly obtain detailed policy information and answers to their questions.

[0262] Step 7:

[0263] The user sends feedback to the server regarding the information provided through their device. This feedback includes evaluations of the accuracy and usefulness of the information.

[0264] Step 8:

[0265] The server aggregates user feedback and modifies the model to improve the accuracy of the information. It also uses the feedback to improve the bias detection algorithm, increasing the fairness of future information provision.

[0266] (Example 1)

[0267] 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 as the "terminal".

[0268] Election-related information is vast and complex, making it difficult for voters to understand it accurately and without bias. Information comes from a wide range of sources, each containing different perspectives and biases, making it challenging to grasp the overall picture. Furthermore, insufficient information tailored to individual user interests and needs hinders the effective use of this information. Therefore, there is a need for a system that efficiently provides voters with the information they need to make informed decisions.

[0269] 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.

[0270] In this invention, the server includes means for automatically collecting information from public institutions, media, and network services; means for analyzing the collected information using natural language processing technology and extracting policy information for each subject; and means for generating responses using artificial intelligence technology in response to inquiries from users. This enables users to obtain election-related information fairly and accurately from diverse sources. Furthermore, by providing information tailored to the individual interests of users, it becomes possible to efficiently acquire the information necessary for decision-making.

[0271] "Information" refers to all election-related data collected from public institutions, media, and network services.

[0272] "Public institutions" refer to organizations and agencies managed and operated by the government or local authorities, and which provide official information related to elections.

[0273] "Media" refers to a medium that distributes information through various platforms, such as newspapers, television, radio, and the internet.

[0274] "Network services" refer to services provided over the internet for information sharing and communication, and specifically include social media platforms.

[0275] "Automated collection" refers to the process by which a system automatically acquires and stores election-related information without human intervention.

[0276] "Natural language processing technology" refers to the technology that enables computers to understand and process human language, and in particular, it refers to methods for text analysis and semantic extraction.

[0277] "Policy information" refers to the detailed content of the policies and measures that election candidates put forward as their campaign promises.

[0278] A "user interface" refers to the screens and operating methods used by a system to exchange information with a user.

[0279] "User" refers to an individual who seeks to obtain election-related information by using this system.

[0280] "Artificial intelligence technology" refers to the technology that allows computers to mimic human intellectual tasks, particularly their ability to answer questions and generate information.

[0281] "Reliability" refers to the degree to which the information provided is accurate and free from errors and biases.

[0282] "Structured data" refers to data organized in a form that allows for efficient utilization and analysis of information.

[0283] This invention is a system for providing election-related information to eligible voters fairly and efficiently. The system is implemented through the interaction of a server, a terminal, and a user.

[0284] First, the server automatically collects information from public institutions, the media, and network services. In this process, API and web scraping technologies are used, and the Requests library in Python is used to collect information regularly and store it in a database. The server then analyzes the collected data using natural language analysis technology. Specifically, the NLTK and spaCy libraries in Python for natural language processing are used to tokenize the text data and extract policy information for each candidate. The analyzed information is structured in JSON format, enabling efficient data access.

[0285] The terminal presents the analysis results received from the server to the user via a user interface. This user interface is built with HTML / CSS and JavaScript and customizes the display content based on the user's profile information. The user can easily obtain information related to specific areas of interest using the terminal.

[0286] Furthermore, the user can input questions related to the election through the terminal. The server receives the question and generates an appropriate response using a generative AI model. For example, the GPT series of OpenAI is used as the generative AI model. An example of a prompt sentence is in the form of "I want to know more about candidate A's environmental policy." Based on this prompt, a response is generated and provided to the user.

[0287] Users can also provide feedback on the information provided. This feedback is analyzed on the server to improve the reliability of the information and to help detect and correct bias. Examples of feedback include "I was satisfied with the accuracy of the information" or "I need more details." In this way, the system provides an environment in which voters can accurately understand election-related information and use it to inform their decision-making.

[0288] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0289] Step 1:

[0290] The server automatically collects information from public institutions, media, and network services. It takes API and web data as input and periodically collects data using the Python Requests library. This data is stored in a database, enabling real-time information management. As output, unstructured raw data is stored in the database.

[0291] Step 2:

[0292] The server processes the collected data using natural language processing techniques. It uses raw data from a database as input, tokenizes the text data using Python's NLTK and spaCy, and then cleans and normalizes the data. In particular, it extracts candidate policy information through keyword extraction and contextual analysis. The output is structured policy information data in JSON format.

[0293] Step 3:

[0294] The server structures the information based on the analysis results and stores it in a database. Using the JSON data obtained in the previous step as input, it classifies the information by theme, enabling efficient access. The output is well-organized data that can be efficiently searched.

[0295] Step 4:

[0296] The terminal displays structured data received from the server in a user interface. It receives parsed data from the server as input and displays it on the screen using HTML / CSS and JavaScript. Based on the displayed information, users can view policy information tailored to their interests. The output provides a user-optimized visual interface.

[0297] Step 5:

[0298] The user enters election-related questions through a terminal. The user enters questions in free format as input, and the terminal sends these questions to the server. The user's question data is sent to the server as output.

[0299] Step 6:

[0300] The server provides user questions as prompts to a generative AI model and generates responses. It takes user questions as input and sends them to a generative AI model (e.g., GPT series). The generative AI model generates detailed answers to the questions, and the natural language response is returned to the server as output.

[0301] Step 7:

[0302] The terminal displays the user's response from the generated AI model. It receives AI-generated responses from the server as input and displays them in the user interface. The user can view the presented information and use it to aid in decision-making. As output, the information is presented on the screen in a format that is easy for the user to understand.

[0303] Step 8:

[0304] Users send feedback on the provided information via their devices. The device receives user feedback as input and sends it to the server. The feedback information is then collected on the server as output.

[0305] Step 9:

[0306] The server analyzes the collected feedback and uses it to improve the accuracy of information and correct biases. It obtains feedback data as input and evaluates the reliability of information using statistical analysis and machine learning techniques. As output, the improved-quality information is reflected back into the database again.

[0307] (Application Example 1)

[0308] 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".

[0309] Obtaining information of voters in an election is difficult due to biases, inaccurate information, and information from multiple information sources. In particular, it is an issue to fairly collect the information necessary for voters to make appropriate judgments and provide support based on individual political interests. Also, it is necessary to provide donation guidance based on highly reliable information to voters who are confused about which candidate or policy to donate to financially.

[0310] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following respective means.

[0311] In this invention, the server includes means for automatically collecting information related to the election from public institutions, news media, and social networks, means for analyzing the collected information using natural language processing technology and fairly extracting policy information for each candidate, and means for proposing donations for specific policies or candidates based on the political interests of users. Thereby, it becomes possible for voters to obtain appropriate and fair information, and it becomes possible to support highly reliable donation activities based on this information.

[0312] "Information related to the election" refers to information regarding candidates' policies and the election process obtained from public institutions, news media, and social networks.

[0313] "Natural language processing technology" is a technology that uses computers to analyze, understand, and process human language, making it possible to extract meaning and intent from large amounts of text information.

[0314] A "user interface" is a screen or means of operation through which a user interacts with a system and receives information, and it can customize and present information according to the user's interests and preferences.

[0315] "Generative artificial intelligence technology" is a technology based on artificial intelligence that automatically generates responses and information based on questions and inputs from users.

[0316] "Feedback" refers to opinions and evaluations that users provide regarding the accuracy and usefulness of the information they receive. This information is used to improve services and systems.

[0317] A "donation suggestion" refers to a proposal designed to encourage users to provide financial support to specific policies or candidates, tailored to their political interests.

[0318] The system implementing this invention consists of a cloud server and client terminals (e.g., smartphones and computers). The server automatically collects election-related data from news media, official organizations, and social networks. The collected data is obtained using web scraping techniques with Python. Next, this data is analyzed using SpaCy, a library for natural language processing, to analyze text related to policy information and candidates. The information obtained from the analysis is then filtered based on each user's profile and customized.

[0319] On the device, the application is built with Flutter and receives information pushed from the server via Firebase. The user interface visually displays information about policies and candidates of interest to the user and supports the acquisition of further detailed information. In addition, generative artificial intelligence technology (e.g., OpenAI's GPT-4) instantly generates responses to the user's questions and sends them back to the device.

[0320] Users can make donation decisions based on their interests, focusing on specific candidates or policies suggested by the system, which also provides information to support their decision-making. The collected feedback is used to further improve the accuracy and presentation of the information.

[0321] For example, a user might enter a prompt such as, "Tell me about candidates who support environmentally friendly energy policies." When this prompt is sent to the system, the server analyzes the relevant data and provides the results to the user's terminal, allowing the user to receive detailed policy information through the interface.

[0322] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0323] Step 1:

[0324] The server automatically collects election-related data from news media, official organizations, and social networks. The input is publicly available election-related information sources on the web, and the output is a collection of this data in text format. Specifically, it uses Python and scraping libraries to efficiently extract the necessary information.

[0325] Step 2:

[0326] The server analyzes the collected data using natural language processing techniques. The input is the collected text data, and the output is structured data containing policy information for each candidate. Specifically, it uses SpaCy to analyze the text and identify and tag key policies and phrases.

[0327] Step 3:

[0328] The server filters the analysis results based on each user's profile. The input consists of analyzed structured data and user profile data, while the output is customized information tailored to the user. Specifically, it extracts and efficiently organizes only the information that matches the user's interests and concerns.

[0329] Step 4:

[0330] The device displays customized information received from the server. The input is information data pushed from the server, and the output is the information displayed on the user interface. Specifically, it receives information via Firebase and displays it graphically on an app built with Flutter.

[0331] Step 5:

[0332] The user enters a specific question through the interface. A prompt (e.g., "Tell me about candidates who support environmentally friendly energy policies") is entered, and additional information is requested based on this.

[0333] Step 6:

[0334] The server generates responses using generative artificial intelligence technology in response to user prompts. The input is the user's prompt, and the output is the response. Specifically, it uses OpenAI's GPT-4 to generate the optimal answer and respond immediately to the user's questions.

[0335] Step 7:

[0336] The user makes a decision to donate to a specific candidate or policy based on the responses and information sent from the server. The input is the presented information and the user's choices, and the output is the donation decision.

[0337] Step 8:

[0338] User feedback is collected via the terminal and sent to the server. Input consists of user ratings, comments, and opinions, while output is this feedback data. The server uses this feedback to analyze and improve the accuracy of the information and the quality of the service.

[0339] 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.

[0340] This invention is a system incorporating an emotion engine to efficiently and fairly provide election-related information to users, and it functions through the interaction of a server, terminal, and user. The server first automatically collects election-related data from public institutions, news media, and social networking services. This data is analyzed using natural language processing technology, and policy information for each candidate is extracted fairly.

[0341] The analysis results are sent from the server to the terminal and presented to the user via the user interface. During this process, the emotion engine recognizes the user's emotions in real time and dynamically adjusts the information displayed. For example, if a user shows a high level of interest in a particular policy, more detailed information related to that policy will be displayed. The emotion engine analyzes the user's emotional data and optimizes the content and presentation of the information provided.

[0342] Users can input election-related questions through their devices, and the server uses generative artificial intelligence technology to generate responses to those questions and present them to the user. In this process, an emotion engine adjusts the tone and level of detail of the response based on the user's emotions. This results in more personalized answers to the specific questions voters have.

[0343] Furthermore, users send feedback to the server regarding the information provided. This feedback is used to improve the overall accuracy of the system and also helps to improve the sentiment engine's algorithms. The sentiment engine helps detect biases hidden in election information.

[0344] For example, if a user wants to research the economic policies of a candidate in a local election, the server collects and analyzes relevant information and displays it on the user's device as customized information through an emotion engine. By continuously assessing the user's interests and reactions, it becomes possible to provide more in-depth and useful information tailored to their attributes. In this way, by combining an emotion engine, it is possible to create an election information delivery environment that is tailored to each user's individual interests and emotions.

[0345] The following describes the processing flow.

[0346] Step 1:

[0347] The server automatically collects election-related data from public institutions, news media, and social networking services. This involves the use of web scraping techniques and APIs, resulting in a large amount of text data being accumulated on the server.

[0348] Step 2:

[0349] The server uses natural language processing technology to analyze the collected data. Policy information about candidates is extracted from the text, and data from different sources is integrated and organized. The bias check process also takes place here.

[0350] Step 3:

[0351] The server sends the analyzed data to the terminal. The terminal then uses a user interface to display the information to the user. During this process, the user's profile information is taken into consideration, and the information is customized according to their individual interests.

[0352] Step 4:

[0353] The device activates an emotion engine to recognize the user's emotional state in real time. The emotion engine analyzes facial expressions, tone of voice, input content, etc., to determine the user's emotions.

[0354] Step 5:

[0355] The user enters election-related questions into a terminal. The terminal sends the input and the user's emotional state to the server.

[0356] Step 6:

[0357] The server uses artificial intelligence technology to generate responses to user questions. The user's emotional state is also taken into consideration, and the responses are tailored based on their individual emotions.

[0358] Step 7:

[0359] The device receives a response from the server and displays the response through the user interface based on the analysis results of the emotion engine. For example, if the user is feeling anxious, the response will be more polite and reassuring.

[0360] Step 8:

[0361] Users submit feedback about the information through their devices. This feedback includes evaluations of the accuracy and usefulness of the information.

[0362] Step 9:

[0363] The server analyzes the feedback to improve the system's accuracy and the sentiment engine's algorithms. This results in improved performance in future information deliveries and reduces bias towards election information.

[0364] (Example 2)

[0365] 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".

[0366] Election-related information is diverse, making it difficult for users to efficiently and fairly obtain information that matches their specific areas of interest. Furthermore, information may be biased or lack the ability to cater to individual user sentiments. This makes it difficult for voters to obtain the information necessary to make informed decisions.

[0367] 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.

[0368] In this invention, the server includes means for automatically collecting election-related information from information sources, means for analyzing the collected information using natural language processing technology and fairly extracting policy information for each candidate, and means for analyzing the user's emotions in real time using emotion recognition technology and dynamically adjusting the information display. This makes it possible to provide users with efficient and personalized election information.

[0369] "Information sources" refers to all sources that provide election-related data, such as public institutions, news media, and social networking services.

[0370] "Natural language processing technology" refers to techniques that enable computers to understand and analyze human language, and includes methods for extracting useful information through the analysis of text data.

[0371] "Emotion recognition technology" refers to technology that analyzes a user's emotional state in real time from their facial expressions and voice, and adjusts the way information is presented based on that analysis.

[0372] "Generative artificial intelligence technology" is a technology that uses artificial intelligence to generate responses in natural human language, making it possible to provide appropriate answers even to complex questions.

[0373] "Feedback" refers to information that includes evaluations and opinions from users regarding the information presented, and is used as data to improve the system and enhance the accuracy of the information.

[0374] "Bias" refers to biases or skews in collected election information, and includes elements that undermine the fairness of the information.

[0375] "Optimization" refers to the process of adjusting the content and format of displayed information based on user interests and emotions to make it as useful as possible for the user.

[0376] This invention is a system that provides election-related information to users efficiently and fairly, and includes information collection, analysis, display, response generation, and collection of user feedback from diverse data sources.

[0377] Data collection and analysis

[0378] The server automatically collects election-related data from sources such as public institutions, news media, and social networking services. This process utilizes web scraping techniques and APIs, such as Python's requests and BeautifulSoup libraries. The collected data is analyzed using natural language processing techniques. Specifically, Python's NLTK and SpaCy are used to analyze text data and fairly extract policy information for each candidate.

[0379] Customized display of information

[0380] The analysis results are sent from the server to the terminal. The user sees the obtained information through the user interface on the terminal. The interface, built with HTML and CSS, visually organizes the information so that the user can easily understand it. Furthermore, the terminal is equipped with emotion recognition technology, which analyzes the user's emotions in real time via OpenCV and the Emotion API and dynamically adjusts the information display.

[0381] Question answering function

[0382] Users can input election-related questions via their terminal. For example, a possible question might be, "Who is most committed to environmental policies in the next local election?" The server uses a generative AI model (e.g., GPT-3) to generate detailed responses to the input questions and provides the appropriately edited responses to the user via their terminal.

[0383] Feedback and system accuracy improvement

[0384] Users can send feedback on the information provided to the server via their device. This feedback is used to improve the overall system performance and the emotion engine algorithm. Based on user feedback, bias in election information will be reduced, and more accurate and unbiased information will be provided.

[0385] The above describes a specific embodiment of the present invention, in which the system provides users with personalized information and responses, enabling them to access election information more effectively.

[0386] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0387] Step 1:

[0388] Data collection

[0389] The server collects election-related data from sources such as public institutions, news media, and social networking services. Specific API endpoints or web URLs are used as input, and data is retrieved based on these through web scraping or API communication. For example, the Python requests library is used to retrieve the latest information from news sites. The output is raw text data.

[0390] Step 2:

[0391] Data Analysis

[0392] The server analyzes the collected raw data using natural language processing techniques. In this step, important key phrases and policy-related information are extracted from the input data, and policy information for each candidate is compiled. Specifically, Python's NLTK and SpaCy are used to tokenize the text, perform POS tagging, and extract important information. The output is the analyzed policy information.

[0393] Step 3:

[0394] Data transmission and display

[0395] The server sends the analysis results to the terminal. The terminal displays the received data in the user interface. Analyzed policy information is received as input and displayed in a user-friendly format using HTML and CSS. Specifically, the policy information is organized in tables and lists and provided to the user in a visually clear manner. The output is the user's visual display.

[0396] Step 4:

[0397] Emotion recognition and display adjustment

[0398] The device uses emotion recognition technology to analyze the user's emotions in real time from their facial expressions and voice. Data from the camera and microphone is used as input, and analysis is performed using OpenCV and the Emotion API. Based on the user's emotions, the device dynamically adjusts the priority and level of detail of information and updates the displayed content as needed. The output is a customized information display adapted to the user's emotions.

[0399] Step 5:

[0400] Question and Answer Generation

[0401] The user enters an election-related question through the terminal. The input is provided in text format and sent to the server as a prompt. The server generates a response to the question using a generative AI model (e.g., GPT-3). The generative AI model analyzes the question, searches for relevant information, formats it, and creates a natural language answer. The output is text containing the generated answer, which is returned to the terminal and displayed to the user.

[0402] Step 6:

[0403] Feedback gathering and system improvement

[0404] Users can send feedback on the provided information and responses to the server via their terminal. Input consists of ratings and comments, which the server analyzes and uses to improve the system. Specifically, the feedback is text-mined to help fine-tune the algorithm and improve the accuracy of the information. Output consists of insights and suggestions for system improvement.

[0405] (Application Example 2)

[0406] 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 will be referred to as the "terminal."

[0407] In providing election-related information to voters fairly and efficiently, there is a need for methods that dynamically optimize information based on users' emotions and individual interests to support their decision-making process. In particular, information that users can accept is necessary regarding donations and fundraising for election campaigns.

[0408] 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.

[0409] In this invention, the server includes means for automatically collecting election-related information from information providers, news organizations, and information sharing services; means for analyzing the collected information using natural language processing technology and fairly extracting policy information for each candidate; and means for recognizing the user's emotions in real time using sentiment analysis technology and adjusting the display order and level of detail of the information. This enables the system to dynamically display detailed election-related information in the donation system based on the user's emotions and interests, thereby supporting the user's decision-making.

[0410] "Information providers" are public institutions, media outlets, and other major sources of information that provide data related to elections.

[0411] "Natural language processing technology" is a technique that mechanically analyzes text data and organizes and extracts information in a way that humans can understand.

[0412] "Emotion analysis technology" is a technology that recognizes a user's emotions in real time and adjusts the system's operation based on those emotions.

[0413] A "donation system" is a mechanism used in election campaigns to allow users to provide financial support to candidates or policies.

[0414] "Dynamic display" is a function that instantly changes the content and presentation of information based on the user's current interests and emotions.

[0415] "Supporting decision-making" refers to the act of providing information to enable users to make appropriate choices and take appropriate actions based on election-related information.

[0416] To implement this invention, a system is needed in which the server performs the following roles. First, the server automatically collects election-related data from information providers, news organizations, and information sharing services and stores it in a database. This collected data is analyzed using natural language processing technology with the Google Cloud Natural Language API to accurately extract policy information for each candidate.

[0417] Next, the analyzed information is evaluated in real time on the user's device using sentiment analysis technology with the Microsoft Azure Emotion API. The device dynamically adjusts the display order and level of detail of the information via the user interface according to this sentiment data. As a result, users can obtain a more personalized election information acquisition experience.

[0418] Users can indicate their willingness to donate to election campaigns through a smartphone application and make donation decisions after obtaining relevant policy information. Upon receiving user input, the server utilizes generative artificial intelligence technology, using Google Cloud AI to generate responses to the questions.

[0419] For example, a user might be considering donating to a particular election candidate but wants more detailed information about that candidate's economic policies. In this case, if sentiment analysis detects a high level of interest in that information, it will be provided in a detailed and easy-to-understand format.

[0420] An example of a prompt message is, "Display detailed information on Candidate A's latest economic policies, highlighting information that the user is emotionally interested in." This is expected to make the user's decision-making more confident and supportive.

[0421] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0422] Step 1:

[0423] The server collects election-related data from information providers, news organizations, and information sharing services. The input data is initially unprocessed. The server uses web scraping techniques to retrieve the necessary data and saves it to a database.

[0424] Step 2:

[0425] The server analyzes the stored data using the Google Cloud Natural Language API. Using the election-related text data obtained as input, it fairly extracts policy information for each candidate. The output is organized policy information.

[0426] Step 3:

[0427] The server utilizes the Microsoft Azure Emotion API to evaluate the user's emotions in real time. It receives the user's facial expressions and voice as input data from the device and performs emotion analysis. Based on the results, it determines the priority of information display according to the emotion.

[0428] Step 4:

[0429] The terminal receives analysis results and sentiment data, and displays the information using a user interface. Using policy information and sentiment evaluations from the server as input, it dynamically displays information tailored to the user's interests. This results in output that is easier for the user to understand.

[0430] Step 5:

[0431] Users view election campaign information and make donation decisions on a smartphone application. The application displays detailed information about candidates the user is interested in and allows them to answer additional questions as needed.

[0432] Step 6:

[0433] The server uses generative artificial intelligence technology to generate responses to user questions. It receives user questions as input and creates answers using a generative AI model. The generated answers are output and provided to the user again via the terminal.

[0434] 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.

[0435] 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.

[0436] 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.

[0437] [Third Embodiment]

[0438] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0439] 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.

[0440] 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).

[0441] 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.

[0442] 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.

[0443] 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).

[0444] 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.

[0445] 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.

[0446] 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.

[0447] 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.

[0448] 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.

[0449] 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".

[0450] This invention is a system for providing election information to voters efficiently and unbiasedly, and is primarily composed of the interaction of a server, terminals, and users. The server continuously collects election-related data from public institutions, news media, and social networking services during the election period. This data is analyzed on the server using natural language processing technology, and policy information for each candidate is fairly extracted.

[0451] The terminal presents the analysis results received from the server to the user via a user interface. The user interface can adjust the displayed content based on the user's profile, providing information tailored to their interests. This helps users quickly find information on political concerns or specific policies based on their own interests.

[0452] Furthermore, users can directly input questions about the election through their terminal. The server processes this information using artificial intelligence technology to generate responses to the user's questions. These responses provide detailed explanations on election-related topics that the user is curious about.

[0453] Furthermore, users can provide feedback on the accuracy and usefulness of the information provided through their devices. The server collects this feedback and uses it to further improve the accuracy of the information. The feedback also helps to detect potential biases in election information and improve the fairness of information provision.

[0454] As a concrete example, the server collects policy pledges of all candidates in a local election from news media and social networking services and analyzes them through natural language processing. The results of this analysis are then provided via the terminal as detailed information on policy areas of particular interest to the user (e.g., environmental policy or economic policy). The user can input questions about the main differences in each candidate's policies and receive instantly generated responses.

[0455] In this embodiment of the invention, the entire process of collecting, analyzing, presenting, and gathering feedback on election information is carried out seamlessly, enabling voters to gain an accurate and unbiased understanding of the election.

[0456] The following describes the processing flow.

[0457] Step 1:

[0458] The server automatically collects election-related data from public institutions, news media, and social networking services. It uses web scraping techniques and APIs to obtain large amounts of text data and store it on the server.

[0459] Step 2:

[0460] The server analyzes the collected data using natural language processing technology. It extracts candidate policy information from text data and integrates and organizes data from different sources. The server performs bias checks and collects additional data as needed to ensure unbiased information.

[0461] Step 3:

[0462] The server sends the analysis results to the terminal. The terminal presents the analyzed election information to the user via a user interface. Using the user profile, the information displayed is customized to each user's interests and preferences.

[0463] Step 4:

[0464] Users enter election-related questions they are interested in into the terminal. For example, they can enter questions such as, "What are the key points of candidate A's economic policies?"

[0465] Step 5:

[0466] The device sends the user's question to the server. The server generates a response to the question using generative artificial intelligence technology. The server then sends the response back to the device.

[0467] Step 6:

[0468] The terminal presents the user with the response received from the server. Users can instantly obtain detailed policy information and answers to their questions.

[0469] Step 7:

[0470] The user sends feedback to the server regarding the information provided through their device. This feedback includes evaluations of the accuracy and usefulness of the information.

[0471] Step 8:

[0472] The server aggregates user feedback and modifies the model to improve the accuracy of the information. It also uses the feedback to improve the bias detection algorithm, increasing the fairness of future information provision.

[0473] (Example 1)

[0474] 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."

[0475] Election-related information is vast and complex, making it difficult for voters to understand it accurately and without bias. Information comes from a wide range of sources, each containing different perspectives and biases, making it challenging to grasp the overall picture. Furthermore, insufficient information tailored to individual user interests and needs hinders the effective use of this information. Therefore, there is a need for a system that efficiently provides voters with the information they need to make informed decisions.

[0476] 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.

[0477] In this invention, the server includes means for automatically collecting information from public institutions, media, and network services; means for analyzing the collected information using natural language processing technology and extracting policy information for each subject; and means for generating responses using artificial intelligence technology in response to inquiries from users. This enables users to obtain election-related information fairly and accurately from diverse sources. Furthermore, by providing information tailored to the individual interests of users, it becomes possible to efficiently acquire the information necessary for decision-making.

[0478] "Information" refers to all election-related data collected from public institutions, media, and network services.

[0479] "Public institutions" refer to organizations and agencies managed and operated by the government or local authorities, and which provide official information related to elections.

[0480] "Media" refers to a medium that distributes information through various platforms, such as newspapers, television, radio, and the internet.

[0481] "Network services" refer to services provided over the internet for information sharing and communication, and specifically include social media platforms.

[0482] "Automated collection" refers to the process by which a system automatically acquires and stores election-related information without human intervention.

[0483] "Natural language processing technology" refers to the technology that enables computers to understand and process human language, and in particular, it refers to methods for text analysis and semantic extraction.

[0484] "Policy information" refers to the detailed content of the policies and measures that election candidates put forward as their campaign promises.

[0485] A "user interface" refers to the screens and operating methods used by a system to exchange information with a user.

[0486] "User" refers to an individual who seeks to obtain election-related information by using this system.

[0487] "Artificial intelligence technology" refers to the technology that allows computers to mimic human intellectual tasks, particularly their ability to answer questions and generate information.

[0488] "Reliability" refers to the degree to which the information provided is accurate and free from errors and biases.

[0489] "Structured data" refers to data that is organized in a format that allows for efficient use and analysis of information.

[0490] This invention is a system for providing election-related information to voters fairly and efficiently. The system is implemented through the interaction of a server, a terminal, and a user.

[0491] First, the server automatically collects information from public institutions, media, and network services. This process uses APIs and web scraping techniques, and periodically collects information using the Python library Requests, storing it in a database. Next, the server analyzes the collected data using natural language processing (NLTK) techniques. Specifically, it tokenizes text data using Python's natural language processing libraries NLTK and spaCy, and extracts policy information for each candidate. The analyzed information is structured in JSON format, enabling efficient data access.

[0492] The terminal presents the analysis results received from the server to the user via a user interface. This user interface is built with HTML / CSS and JavaScript and customizes the displayed content based on the user's profile information. Users can easily obtain information related to their specific areas of interest using the terminal.

[0493] Furthermore, users can input questions about the election through their terminal. The server receives these questions and generates appropriate responses using a generative AI model. For example, OpenAI's GPT series is used as a generative AI model. An example of a prompt is, "I would like to know more about candidate A's environmental policies." Based on this prompt, a response is generated and provided to the user.

[0494] Users can also provide feedback on the information provided. This feedback is analyzed on the server to improve the reliability of the information and to help detect and correct bias. Examples of feedback include "I was satisfied with the accuracy of the information" or "I need more details." In this way, the system provides an environment in which voters can accurately understand election-related information and use it to inform their decision-making.

[0495] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0496] Step 1:

[0497] The server automatically collects information from public institutions, media, and network services. It takes API and web data as input and periodically collects data using the Python Requests library. This data is stored in a database, enabling real-time information management. As output, unstructured raw data is stored in the database.

[0498] Step 2:

[0499] The server processes the collected data using natural language processing techniques. It uses raw data from a database as input, tokenizes the text data using Python's NLTK and spaCy, and then cleans and normalizes the data. In particular, it extracts candidate policy information through keyword extraction and contextual analysis. The output is structured policy information data in JSON format.

[0500] Step 3:

[0501] The server structures the information based on the analysis results and stores it in a database. Using the JSON data obtained in the previous step as input, it classifies the information by theme, enabling efficient access. The output is well-organized data that can be efficiently searched.

[0502] Step 4:

[0503] The terminal displays structured data received from the server in a user interface. It receives parsed data from the server as input and displays it on the screen using HTML / CSS and JavaScript. Based on the displayed information, users can view policy information tailored to their interests. The output provides a user-optimized visual interface.

[0504] Step 5:

[0505] The user enters election-related questions through a terminal. The user enters questions in free format as input, and the terminal sends these questions to the server. The user's question data is sent to the server as output.

[0506] Step 6:

[0507] The server provides user questions as prompts to a generative AI model and generates responses. It takes user questions as input and sends them to a generative AI model (e.g., GPT series). The generative AI model generates detailed answers to the questions, and the natural language response is returned to the server as output.

[0508] Step 7:

[0509] The terminal displays the user's response from the generated AI model. It receives AI-generated responses from the server as input and displays them in the user interface. The user can view the presented information and use it to aid in decision-making. As output, the information is presented on the screen in a format that is easy for the user to understand.

[0510] Step 8:

[0511] Users send feedback on the provided information via their devices. The device receives user feedback as input and sends it to the server. The feedback information is then collected on the server as output.

[0512] Step 9:

[0513] The server analyzes the collected feedback to improve the accuracy of the information and correct biases. It takes feedback data as input and uses statistical analysis and machine learning techniques to evaluate the reliability of the information. As output, the improved quality information is reflected back in the database.

[0514] (Application Example 1)

[0515] 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."

[0516] Obtaining information for voters during elections is difficult due to bias, inaccuracies, and information from multiple sources. In particular, the challenge lies in fairly collecting the information necessary for voters to make informed decisions and providing support based on their individual political interests. Furthermore, there is a need to provide reliable information-based guidance on donations to voters who are unsure which candidate or policy to support financially.

[0517] 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.

[0518] This invention includes a server that automatically collects election-related information from public institutions, media outlets, and social networks; a server that analyzes the collected information using natural language processing technology to fairly extract policy information for each candidate; and a server that makes suggestions for donations to specific policies or candidates based on the user's political interests. This enables voters to obtain appropriate and fair information and to support reliable donation activities based on that information.

[0519] "Election-related information" refers to information about candidates' policies and the election process obtained from public institutions, media outlets, and social networks.

[0520] "Natural language processing technology" is a technology that uses computers to analyze, understand, and process human language, making it possible to extract meaning and intent from large amounts of text information.

[0521] A "user interface" is a screen or means of operation through which a user interacts with a system and receives information, and it can customize and present information according to the user's interests and preferences.

[0522] "Generative artificial intelligence technology" is a technology based on artificial intelligence that automatically generates responses and information based on questions and inputs from users.

[0523] "Feedback" refers to opinions and evaluations that users provide regarding the accuracy and usefulness of the information they receive. This information is used to improve services and systems.

[0524] A "donation suggestion" refers to a proposal designed to encourage users to provide financial support to specific policies or candidates, tailored to their political interests.

[0525] The system implementing this invention consists of a cloud server and client terminals (e.g., smartphones and computers). The server automatically collects election-related data from news media, official organizations, and social networks. The collected data is obtained using web scraping techniques with Python. Next, this data is analyzed using SpaCy, a library for natural language processing, to analyze text related to policy information and candidates. The information obtained from the analysis is then filtered based on each user's profile and customized.

[0526] On the device, the application is built with Flutter and receives information pushed from the server via Firebase. The user interface visually displays information about policies and candidates of interest to the user and supports the acquisition of further detailed information. In addition, generative artificial intelligence technology (e.g., OpenAI's GPT-4) instantly generates responses to the user's questions and sends them back to the device.

[0527] Users can make donation decisions based on their interests, focusing on specific candidates or policies suggested by the system, which also provides information to support their decision-making. The collected feedback is used to further improve the accuracy and presentation of the information.

[0528] For example, a user might enter a prompt such as, "Tell me about candidates who support environmentally friendly energy policies." When this prompt is sent to the system, the server analyzes the relevant data and provides the results to the user's terminal, allowing the user to receive detailed policy information through the interface.

[0529] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0530] Step 1:

[0531] The server automatically collects election-related data from news media, official organizations, and social networks. The input is publicly available election-related information sources on the web, and the output is a collection of this data in text format. Specifically, it uses Python and scraping libraries to efficiently extract the necessary information.

[0532] Step 2:

[0533] The server analyzes the collected data using natural language processing techniques. The input is the collected text data, and the output is structured data containing policy information for each candidate. Specifically, it uses SpaCy to analyze the text and identify and tag key policies and phrases.

[0534] Step 3:

[0535] The server filters the analysis results based on each user's profile. The input consists of analyzed structured data and user profile data, while the output is customized information tailored to the user. Specifically, it extracts and efficiently organizes only the information that matches the user's interests and concerns.

[0536] Step 4:

[0537] The device displays customized information received from the server. The input is information data pushed from the server, and the output is the information displayed on the user interface. Specifically, it receives information via Firebase and displays it graphically on an app built with Flutter.

[0538] Step 5:

[0539] The user enters a specific question through the interface. A prompt (e.g., "Tell me about candidates who support environmentally friendly energy policies") is entered, and additional information is requested based on this.

[0540] Step 6:

[0541] The server generates responses using generative artificial intelligence technology in response to user prompts. The input is the user's prompt, and the output is the response. Specifically, it uses OpenAI's GPT-4 to generate the optimal answer and respond immediately to the user's questions.

[0542] Step 7:

[0543] The user makes a decision to donate to a specific candidate or policy based on the responses and information sent from the server. The input is the presented information and the user's choices, and the output is the donation decision.

[0544] Step 8:

[0545] User feedback is collected via the terminal and sent to the server. Input consists of user ratings, comments, and opinions, while output is this feedback data. The server uses this feedback to analyze and improve the accuracy of the information and the quality of the service.

[0546] 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.

[0547] This invention is a system incorporating an emotion engine to efficiently and fairly provide election-related information to users, and it functions through the interaction of a server, terminal, and user. The server first automatically collects election-related data from public institutions, news media, and social networking services. This data is analyzed using natural language processing technology, and policy information for each candidate is extracted fairly.

[0548] The analysis results are sent from the server to the terminal and presented to the user via the user interface. During this process, the emotion engine recognizes the user's emotions in real time and dynamically adjusts the information displayed. For example, if a user shows a high level of interest in a particular policy, more detailed information related to that policy will be displayed. The emotion engine analyzes the user's emotional data and optimizes the content and presentation of the information provided.

[0549] Users can input election-related questions through their devices, and the server uses generative artificial intelligence technology to generate responses to those questions and present them to the user. In this process, an emotion engine adjusts the tone and level of detail of the response based on the user's emotions. This results in more personalized answers to the specific questions voters have.

[0550] Furthermore, users send feedback to the server regarding the information provided. This feedback is used to improve the overall accuracy of the system and also helps to improve the sentiment engine's algorithms. The sentiment engine helps detect biases hidden in election information.

[0551] For example, if a user wants to research the economic policies of a candidate in a local election, the server collects and analyzes relevant information and displays it on the user's device as customized information through an emotion engine. By continuously assessing the user's interests and reactions, it becomes possible to provide more in-depth and useful information tailored to their attributes. In this way, by combining an emotion engine, it is possible to create an election information delivery environment that is tailored to each user's individual interests and emotions.

[0552] The following describes the processing flow.

[0553] Step 1:

[0554] The server automatically collects election-related data from public institutions, news media, and social networking services. This involves the use of web scraping techniques and APIs, resulting in a large amount of text data being accumulated on the server.

[0555] Step 2:

[0556] The server uses natural language processing technology to analyze the collected data. Policy information about candidates is extracted from the text, and data from different sources is integrated and organized. The bias check process also takes place here.

[0557] Step 3:

[0558] The server sends the analyzed data to the terminal. The terminal then uses a user interface to display the information to the user. During this process, the user's profile information is taken into consideration, and the information is customized according to their individual interests.

[0559] Step 4:

[0560] The device activates an emotion engine to recognize the user's emotional state in real time. The emotion engine analyzes facial expressions, tone of voice, input content, etc., to determine the user's emotions.

[0561] Step 5:

[0562] The user enters election-related questions into a terminal. The terminal sends the input and the user's emotional state to the server.

[0563] Step 6:

[0564] The server uses artificial intelligence technology to generate responses to user questions. The user's emotional state is also taken into consideration, and the responses are tailored based on their individual emotions.

[0565] Step 7:

[0566] The device receives a response from the server and displays the response through the user interface based on the analysis results of the emotion engine. For example, if the user is feeling anxious, the response will be more polite and reassuring.

[0567] Step 8:

[0568] Users submit feedback about the information through their devices. This feedback includes evaluations of the accuracy and usefulness of the information.

[0569] Step 9:

[0570] The server analyzes the feedback to improve the system's accuracy and the sentiment engine's algorithms. This results in improved performance in future information deliveries and reduces bias towards election information.

[0571] (Example 2)

[0572] 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."

[0573] Election-related information is diverse, making it difficult for users to efficiently and fairly obtain information that matches their specific areas of interest. Furthermore, information may be biased or lack the ability to cater to individual user sentiments. This makes it difficult for voters to obtain the information necessary to make informed decisions.

[0574] 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.

[0575] In this invention, the server includes means for automatically collecting election-related information from information sources, means for analyzing the collected information using natural language processing technology and fairly extracting policy information for each candidate, and means for analyzing the user's emotions in real time using emotion recognition technology and dynamically adjusting the information display. This makes it possible to provide users with efficient and personalized election information.

[0576] "Information sources" refers to all sources that provide election-related data, such as public institutions, news media, and social networking services.

[0577] "Natural language processing technology" refers to techniques that enable computers to understand and analyze human language, and includes methods for extracting useful information through the analysis of text data.

[0578] "Emotion recognition technology" refers to technology that analyzes a user's emotional state in real time from their facial expressions and voice, and adjusts the way information is presented based on that analysis.

[0579] "Generative artificial intelligence technology" is a technology that uses artificial intelligence to generate responses in natural human language, making it possible to provide appropriate answers even to complex questions.

[0580] "Feedback" refers to information that includes evaluations and opinions from users regarding the information presented, and is used as data to improve the system and enhance the accuracy of the information.

[0581] "Bias" refers to biases or skews in collected election information, and includes elements that undermine the fairness of the information.

[0582] "Optimization" refers to the process of adjusting the content and format of displayed information based on user interests and emotions to make it as useful as possible for the user.

[0583] This invention is a system that provides election-related information to users efficiently and fairly, and includes information collection, analysis, display, response generation, and collection of user feedback from diverse data sources.

[0584] Data collection and analysis

[0585] The server automatically collects election-related data from sources such as public institutions, news media, and social networking services. This process utilizes web scraping techniques and APIs, such as Python's requests and BeautifulSoup libraries. The collected data is analyzed using natural language processing techniques. Specifically, Python's NLTK and SpaCy are used to analyze text data and fairly extract policy information for each candidate.

[0586] Customized display of information

[0587] The analysis results are sent from the server to the terminal. The user sees the obtained information through the user interface on the terminal. The interface, built with HTML and CSS, visually organizes the information so that the user can easily understand it. Furthermore, the terminal is equipped with emotion recognition technology, which analyzes the user's emotions in real time via OpenCV and the Emotion API and dynamically adjusts the information display.

[0588] Question answering function

[0589] Users can input election-related questions via their terminal. For example, a possible question might be, "Who is most committed to environmental policies in the next local election?" The server uses a generative AI model (e.g., GPT-3) to generate detailed responses to the input questions and provides the appropriately edited responses to the user via their terminal.

[0590] Feedback and system accuracy improvement

[0591] Users can send feedback on the information provided to the server via their device. This feedback is used to improve the overall system performance and the emotion engine algorithm. Based on user feedback, bias in election information will be reduced, and more accurate and unbiased information will be provided.

[0592] The above describes a specific embodiment of the present invention, in which the system provides users with personalized information and responses, enabling them to access election information more effectively.

[0593] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0594] Step 1:

[0595] Data collection

[0596] The server collects election-related data from sources such as public institutions, news media, and social networking services. Specific API endpoints or web URLs are used as input, and data is retrieved based on these through web scraping or API communication. For example, the Python requests library is used to retrieve the latest information from news sites. The output is raw text data.

[0597] Step 2:

[0598] Data Analysis

[0599] The server analyzes the collected raw data using natural language processing techniques. In this step, important key phrases and policy-related information are extracted from the input data, and policy information for each candidate is compiled. Specifically, Python's NLTK and SpaCy are used to tokenize the text, perform POS tagging, and extract important information. The output is the analyzed policy information.

[0600] Step 3:

[0601] Data transmission and display

[0602] The server sends the analysis results to the terminal. The terminal displays the received data in the user interface. Analyzed policy information is received as input and displayed in a user-friendly format using HTML and CSS. Specifically, the policy information is organized in tables and lists and provided to the user in a visually clear manner. The output is the user's visual display.

[0603] Step 4:

[0604] Emotion recognition and display adjustment

[0605] The device uses emotion recognition technology to analyze the user's emotions in real time from their facial expressions and voice. Data from the camera and microphone is used as input, and analysis is performed using OpenCV and the Emotion API. Based on the user's emotions, the device dynamically adjusts the priority and level of detail of information and updates the displayed content as needed. The output is a customized information display adapted to the user's emotions.

[0606] Step 5:

[0607] Question and Answer Generation

[0608] The user enters an election-related question through the terminal. The input is provided in text format and sent to the server as a prompt. The server generates a response to the question using a generative AI model (e.g., GPT-3). The generative AI model analyzes the question, searches for relevant information, formats it, and creates a natural language answer. The output is text containing the generated answer, which is returned to the terminal and displayed to the user.

[0609] Step 6:

[0610] Feedback gathering and system improvement

[0611] Users can send feedback on the provided information and responses to the server via their terminal. Input consists of ratings and comments, which the server analyzes and uses to improve the system. Specifically, the feedback is text-mined to help fine-tune the algorithm and improve the accuracy of the information. Output consists of insights and suggestions for system improvement.

[0612] (Application Example 2)

[0613] 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."

[0614] In providing election-related information to voters fairly and efficiently, there is a need for methods that dynamically optimize information based on users' emotions and individual interests to support their decision-making process. In particular, information that users can accept is necessary regarding donations and fundraising for election campaigns.

[0615] 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.

[0616] In this invention, the server includes means for automatically collecting election-related information from information providers, news organizations, and information sharing services; means for analyzing the collected information using natural language processing technology and fairly extracting policy information for each candidate; and means for recognizing the user's emotions in real time using sentiment analysis technology and adjusting the display order and level of detail of the information. This enables the system to dynamically display detailed election-related information in the donation system based on the user's emotions and interests, thereby supporting the user's decision-making.

[0617] "Information providers" are public institutions, media outlets, and other major sources of information that provide data related to elections.

[0618] "Natural language processing technology" is a technique that mechanically analyzes text data and organizes and extracts information in a way that humans can understand.

[0619] "Emotion analysis technology" is a technology that recognizes a user's emotions in real time and adjusts the system's operation based on those emotions.

[0620] A "donation system" is a mechanism used in election campaigns to allow users to provide financial support to candidates or policies.

[0621] "Dynamic display" is a function that instantly changes the content and presentation of information based on the user's current interests and emotions.

[0622] "Supporting decision-making" refers to the act of providing information to enable users to make appropriate choices and take appropriate actions based on election-related information.

[0623] To implement this invention, a system is needed in which the server performs the following roles. First, the server automatically collects election-related data from information providers, news organizations, and information sharing services and stores it in a database. This collected data is analyzed using natural language processing technology with the Google Cloud Natural Language API to accurately extract policy information for each candidate.

[0624] Next, the analyzed information is evaluated in real time on the user's device using sentiment analysis technology with the Microsoft Azure Emotion API. The device dynamically adjusts the display order and level of detail of the information via the user interface according to this sentiment data. As a result, users can obtain a more personalized election information acquisition experience.

[0625] Users can indicate their willingness to donate to election campaigns through a smartphone application and make donation decisions after obtaining relevant policy information. Upon receiving user input, the server utilizes generative artificial intelligence technology, using Google Cloud AI to generate responses to the questions.

[0626] For example, a user might be considering donating to a particular election candidate but wants more detailed information about that candidate's economic policies. In this case, if sentiment analysis detects a high level of interest in that information, it will be provided in a detailed and easy-to-understand format.

[0627] An example of a prompt message is, "Display detailed information on Candidate A's latest economic policies, highlighting information that the user is emotionally interested in." This is expected to make the user's decision-making more confident and supportive.

[0628] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0629] Step 1:

[0630] The server collects election-related data from information providers, news organizations, and information sharing services. The input data is initially unprocessed. The server uses web scraping techniques to retrieve the necessary data and saves it to a database.

[0631] Step 2:

[0632] The server analyzes the stored data using the Google Cloud Natural Language API. Using the election-related text data obtained as input, it fairly extracts policy information for each candidate. The output is organized policy information.

[0633] Step 3:

[0634] The server utilizes the Microsoft Azure Emotion API to evaluate the user's emotions in real time. It receives the user's facial expressions and voice as input data from the device and performs emotion analysis. Based on the results, it determines the priority of information display according to the emotion.

[0635] Step 4:

[0636] The terminal receives analysis results and sentiment data, and displays the information using a user interface. Using policy information and sentiment evaluations from the server as input, it dynamically displays information tailored to the user's interests. This results in output that is easier for the user to understand.

[0637] Step 5:

[0638] Users view election campaign information and make donation decisions on a smartphone application. The application displays detailed information about candidates the user is interested in and allows them to answer additional questions as needed.

[0639] Step 6:

[0640] The server uses generative artificial intelligence technology to generate responses to user questions. It receives user questions as input and creates answers using a generative AI model. The generated answers are output and provided to the user again via the terminal.

[0641] 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.

[0642] 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.

[0643] 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.

[0644] [Fourth Embodiment]

[0645] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0646] 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.

[0647] 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).

[0648] 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.

[0649] 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.

[0650] 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).

[0651] 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.

[0652] 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.

[0653] 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.

[0654] 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.

[0655] 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.

[0656] 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.

[0657] 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".

[0658] This invention is a system for providing election information to voters efficiently and unbiasedly, and is primarily composed of the interaction of a server, terminals, and users. The server continuously collects election-related data from public institutions, news media, and social networking services during the election period. This data is analyzed on the server using natural language processing technology, and policy information for each candidate is fairly extracted.

[0659] The terminal presents the analysis results received from the server to the user via a user interface. The user interface can adjust the displayed content based on the user's profile, providing information tailored to their interests. This helps users quickly find information on political concerns or specific policies based on their own interests.

[0660] Furthermore, users can directly input questions about the election through their terminal. The server processes this information using artificial intelligence technology to generate responses to the user's questions. These responses provide detailed explanations on election-related topics that the user is curious about.

[0661] Furthermore, users can provide feedback on the accuracy and usefulness of the information provided through their devices. The server collects this feedback and uses it to further improve the accuracy of the information. The feedback also helps to detect potential biases in election information and improve the fairness of information provision.

[0662] As a concrete example, the server collects policy pledges of all candidates in a local election from news media and social networking services and analyzes them through natural language processing. The results of this analysis are then provided via the terminal as detailed information on policy areas of particular interest to the user (e.g., environmental policy or economic policy). The user can input questions about the main differences in each candidate's policies and receive instantly generated responses.

[0663] In this embodiment of the invention, the entire process of collecting, analyzing, presenting, and gathering feedback on election information is carried out seamlessly, enabling voters to gain an accurate and unbiased understanding of the election.

[0664] The following describes the processing flow.

[0665] Step 1:

[0666] The server automatically collects election-related data from public institutions, news media, and social networking services. It uses web scraping techniques and APIs to obtain large amounts of text data and store it on the server.

[0667] Step 2:

[0668] The server analyzes the collected data using natural language processing technology. It extracts candidate policy information from text data and integrates and organizes data from different sources. The server performs bias checks and collects additional data as needed to ensure unbiased information.

[0669] Step 3:

[0670] The server sends the analysis results to the terminal. The terminal presents the analyzed election information to the user via a user interface. Using the user profile, the information displayed is customized to each user's interests and preferences.

[0671] Step 4:

[0672] Users enter election-related questions they are interested in into the terminal. For example, they can enter questions such as, "What are the key points of candidate A's economic policies?"

[0673] Step 5:

[0674] The device sends the user's question to the server. The server generates a response to the question using generative artificial intelligence technology. The server then sends the response back to the device.

[0675] Step 6:

[0676] The terminal presents the user with the response received from the server. Users can instantly obtain detailed policy information and answers to their questions.

[0677] Step 7:

[0678] The user sends feedback to the server regarding the information provided through their device. This feedback includes evaluations of the accuracy and usefulness of the information.

[0679] Step 8:

[0680] The server aggregates user feedback and modifies the model to improve the accuracy of the information. It also uses the feedback to improve the bias detection algorithm, increasing the fairness of future information provision.

[0681] (Example 1)

[0682] 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".

[0683] Election-related information is vast and complex, making it difficult for voters to understand it accurately and without bias. Information comes from a wide range of sources, each containing different perspectives and biases, making it challenging to grasp the overall picture. Furthermore, insufficient information tailored to individual user interests and needs hinders the effective use of this information. Therefore, there is a need for a system that efficiently provides voters with the information they need to make informed decisions.

[0684] 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.

[0685] In this invention, the server includes means for automatically collecting information from public institutions, media, and network services; means for analyzing the collected information using natural language processing technology and extracting policy information for each subject; and means for generating responses using artificial intelligence technology in response to inquiries from users. This enables users to obtain election-related information fairly and accurately from diverse sources. Furthermore, by providing information tailored to the individual interests of users, it becomes possible to efficiently acquire the information necessary for decision-making.

[0686] "Information" refers to all election-related data collected from public institutions, media, and network services.

[0687] "Public institutions" refer to organizations and agencies managed and operated by the government or local authorities, and which provide official information related to elections.

[0688] "Media" refers to a medium that distributes information through various platforms, such as newspapers, television, radio, and the internet.

[0689] "Network services" refer to services provided over the internet for information sharing and communication, and specifically include social media platforms.

[0690] "Automated collection" refers to the process by which a system automatically acquires and stores election-related information without human intervention.

[0691] "Natural language processing technology" refers to the technology that enables computers to understand and process human language, and in particular, it refers to methods for text analysis and semantic extraction.

[0692] "Policy information" refers to the detailed content of the policies and measures that election candidates put forward as their campaign promises.

[0693] A "user interface" refers to the screens and operating methods used by a system to exchange information with a user.

[0694] "User" refers to an individual who seeks to obtain election-related information by using this system.

[0695] "Artificial intelligence technology" refers to the technology that allows computers to mimic human intellectual tasks, particularly their ability to answer questions and generate information.

[0696] "Reliability" refers to the degree to which the information provided is accurate and free from errors and biases.

[0697] "Structured data" refers to data that is organized in a format that allows for efficient use and analysis of information.

[0698] This invention is a system for providing election-related information to voters fairly and efficiently. The system is implemented through the interaction of a server, a terminal, and a user.

[0699] First, the server automatically collects information from public institutions, media, and network services. This process uses APIs and web scraping techniques, and periodically collects information using the Python library Requests, storing it in a database. Next, the server analyzes the collected data using natural language processing (NLTK) techniques. Specifically, it tokenizes text data using Python's natural language processing libraries NLTK and spaCy, and extracts policy information for each candidate. The analyzed information is structured in JSON format, enabling efficient data access.

[0700] The terminal presents the analysis results received from the server to the user via a user interface. This user interface is built with HTML / CSS and JavaScript and customizes the displayed content based on the user's profile information. Users can easily obtain information related to their specific areas of interest using the terminal.

[0701] Furthermore, users can input questions about the election through their terminal. The server receives these questions and generates appropriate responses using a generative AI model. For example, OpenAI's GPT series is used as a generative AI model. An example of a prompt is, "I would like to know more about candidate A's environmental policies." Based on this prompt, a response is generated and provided to the user.

[0702] Users can also provide feedback on the information provided. This feedback is analyzed on the server to improve the reliability of the information and to help detect and correct bias. Examples of feedback include "I was satisfied with the accuracy of the information" or "I need more details." In this way, the system provides an environment in which voters can accurately understand election-related information and use it to inform their decision-making.

[0703] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0704] Step 1:

[0705] The server automatically collects information from public institutions, media, and network services. It takes API and web data as input and periodically collects data using the Python Requests library. This data is stored in a database, enabling real-time information management. As output, unstructured raw data is stored in the database.

[0706] Step 2:

[0707] The server processes the collected data using natural language processing techniques. It uses raw data from a database as input, tokenizes the text data using Python's NLTK and spaCy, and then cleans and normalizes the data. In particular, it extracts candidate policy information through keyword extraction and contextual analysis. The output is structured policy information data in JSON format.

[0708] Step 3:

[0709] The server structures the information based on the analysis results and stores it in a database. Using the JSON data obtained in the previous step as input, it classifies the information by theme, enabling efficient access. The output is well-organized data that can be efficiently searched.

[0710] Step 4:

[0711] The terminal displays structured data received from the server in a user interface. It receives parsed data from the server as input and displays it on the screen using HTML / CSS and JavaScript. Based on the displayed information, users can view policy information tailored to their interests. The output provides a user-optimized visual interface.

[0712] Step 5:

[0713] The user enters election-related questions through a terminal. The user enters questions in free format as input, and the terminal sends these questions to the server. The user's question data is sent to the server as output.

[0714] Step 6:

[0715] The server provides user questions as prompts to a generative AI model and generates responses. It takes user questions as input and sends them to a generative AI model (e.g., GPT series). The generative AI model generates detailed answers to the questions, and the natural language response is returned to the server as output.

[0716] Step 7:

[0717] The terminal displays the user's response from the generated AI model. It receives AI-generated responses from the server as input and displays them in the user interface. The user can view the presented information and use it to aid in decision-making. As output, the information is presented on the screen in a format that is easy for the user to understand.

[0718] Step 8:

[0719] Users send feedback on the provided information via their devices. The device receives user feedback as input and sends it to the server. The feedback information is then collected on the server as output.

[0720] Step 9:

[0721] The server analyzes the collected feedback to improve the accuracy of the information and correct biases. It takes feedback data as input and uses statistical analysis and machine learning techniques to evaluate the reliability of the information. As output, the improved quality information is reflected back in the database.

[0722] (Application Example 1)

[0723] 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".

[0724] Obtaining information for voters during elections is difficult due to bias, inaccuracies, and information from multiple sources. In particular, the challenge lies in fairly collecting the information necessary for voters to make informed decisions and providing support based on their individual political interests. Furthermore, there is a need to provide reliable information-based guidance on donations to voters who are unsure which candidate or policy to support financially.

[0725] 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.

[0726] This invention includes a server that automatically collects election-related information from public institutions, media outlets, and social networks; a server that analyzes the collected information using natural language processing technology to fairly extract policy information for each candidate; and a server that makes suggestions for donations to specific policies or candidates based on the user's political interests. This enables voters to obtain appropriate and fair information and to support reliable donation activities based on that information.

[0727] "Election-related information" refers to information about candidates' policies and the election process obtained from public institutions, media outlets, and social networks.

[0728] "Natural language processing technology" is a technology that uses computers to analyze, understand, and process human language, making it possible to extract meaning and intent from large amounts of text information.

[0729] A "user interface" is a screen or means of operation through which a user interacts with a system and receives information, and it can customize and present information according to the user's interests and preferences.

[0730] "Generative artificial intelligence technology" is a technology based on artificial intelligence that automatically generates responses and information based on questions and inputs from users.

[0731] "Feedback" refers to opinions and evaluations that users provide regarding the accuracy and usefulness of the information they receive. This information is used to improve services and systems.

[0732] A "donation suggestion" refers to a proposal designed to encourage users to provide financial support to specific policies or candidates, tailored to their political interests.

[0733] The system implementing this invention consists of a cloud server and client terminals (e.g., smartphones and computers). The server automatically collects election-related data from news media, official organizations, and social networks. The collected data is obtained using web scraping techniques with Python. Next, this data is analyzed using SpaCy, a library for natural language processing, to analyze text related to policy information and candidates. The information obtained from the analysis is then filtered based on each user's profile and customized.

[0734] On the device, the application is built with Flutter and receives information pushed from the server via Firebase. The user interface visually displays information about policies and candidates of interest to the user and supports the acquisition of further detailed information. In addition, generative artificial intelligence technology (e.g., OpenAI's GPT-4) instantly generates responses to the user's questions and sends them back to the device.

[0735] Users can make donation decisions based on their interests, focusing on specific candidates or policies suggested by the system, which also provides information to support their decision-making. The collected feedback is used to further improve the accuracy and presentation of the information.

[0736] For example, a user might enter a prompt such as, "Tell me about candidates who support environmentally friendly energy policies." When this prompt is sent to the system, the server analyzes the relevant data and provides the results to the user's terminal, allowing the user to receive detailed policy information through the interface.

[0737] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0738] Step 1:

[0739] The server automatically collects election-related data from news media, official organizations, and social networks. The input is publicly available election-related information sources on the web, and the output is a collection of this data in text format. Specifically, it uses Python and scraping libraries to efficiently extract the necessary information.

[0740] Step 2:

[0741] The server analyzes the collected data using natural language processing techniques. The input is the collected text data, and the output is structured data containing policy information for each candidate. Specifically, it uses SpaCy to analyze the text and identify and tag key policies and phrases.

[0742] Step 3:

[0743] The server filters the analysis results based on each user's profile. The input consists of analyzed structured data and user profile data, while the output is customized information tailored to the user. Specifically, it extracts and efficiently organizes only the information that matches the user's interests and concerns.

[0744] Step 4:

[0745] The device displays customized information received from the server. The input is information data pushed from the server, and the output is the information displayed on the user interface. Specifically, it receives information via Firebase and displays it graphically on an app built with Flutter.

[0746] Step 5:

[0747] The user enters a specific question through the interface. A prompt (e.g., "Tell me about candidates who support environmentally friendly energy policies") is entered, and additional information is requested based on this.

[0748] Step 6:

[0749] The server generates responses using generative artificial intelligence technology in response to user prompts. The input is the user's prompt, and the output is the response. Specifically, it uses OpenAI's GPT-4 to generate the optimal answer and respond immediately to the user's questions.

[0750] Step 7:

[0751] The user makes a decision to donate to a specific candidate or policy based on the responses and information sent from the server. The input is the presented information and the user's choices, and the output is the donation decision.

[0752] Step 8:

[0753] User feedback is collected via the terminal and sent to the server. Input consists of user ratings, comments, and opinions, while output is this feedback data. The server uses this feedback to analyze and improve the accuracy of the information and the quality of the service.

[0754] 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.

[0755] This invention is a system incorporating an emotion engine to efficiently and fairly provide election-related information to users, and it functions through the interaction of a server, terminal, and user. The server first automatically collects election-related data from public institutions, news media, and social networking services. This data is analyzed using natural language processing technology, and policy information for each candidate is extracted fairly.

[0756] The analysis results are sent from the server to the terminal and presented to the user via the user interface. During this process, the emotion engine recognizes the user's emotions in real time and dynamically adjusts the information displayed. For example, if a user shows a high level of interest in a particular policy, more detailed information related to that policy will be displayed. The emotion engine analyzes the user's emotional data and optimizes the content and presentation of the information provided.

[0757] Users can input election-related questions through their devices, and the server uses generative artificial intelligence technology to generate responses to those questions and present them to the user. In this process, an emotion engine adjusts the tone and level of detail of the response based on the user's emotions. This results in more personalized answers to the specific questions voters have.

[0758] Furthermore, users send feedback to the server regarding the information provided. This feedback is used to improve the overall accuracy of the system and also helps to improve the sentiment engine's algorithms. The sentiment engine helps detect biases hidden in election information.

[0759] For example, if a user wants to research the economic policies of a candidate in a local election, the server collects and analyzes relevant information and displays it on the user's device as customized information through an emotion engine. By continuously assessing the user's interests and reactions, it becomes possible to provide more in-depth and useful information tailored to their attributes. In this way, by combining an emotion engine, it is possible to create an election information delivery environment that is tailored to each user's individual interests and emotions.

[0760] The following describes the processing flow.

[0761] Step 1:

[0762] The server automatically collects election-related data from public institutions, news media, and social networking services. This involves the use of web scraping techniques and APIs, resulting in a large amount of text data being accumulated on the server.

[0763] Step 2:

[0764] The server uses natural language processing technology to analyze the collected data. Policy information about candidates is extracted from the text, and data from different sources is integrated and organized. The bias check process also takes place here.

[0765] Step 3:

[0766] The server sends the analyzed data to the terminal. The terminal then uses a user interface to display the information to the user. During this process, the user's profile information is taken into consideration, and the information is customized according to their individual interests.

[0767] Step 4:

[0768] The device activates an emotion engine to recognize the user's emotional state in real time. The emotion engine analyzes facial expressions, tone of voice, input content, etc., to determine the user's emotions.

[0769] Step 5:

[0770] The user enters election-related questions into a terminal. The terminal sends the input and the user's emotional state to the server.

[0771] Step 6:

[0772] The server uses artificial intelligence technology to generate responses to user questions. The user's emotional state is also taken into consideration, and the responses are tailored based on their individual emotions.

[0773] Step 7:

[0774] The device receives a response from the server and displays the response through the user interface based on the analysis results of the emotion engine. For example, if the user is feeling anxious, the response will be more polite and reassuring.

[0775] Step 8:

[0776] Users submit feedback about the information through their devices. This feedback includes evaluations of the accuracy and usefulness of the information.

[0777] Step 9:

[0778] The server analyzes the feedback to improve the system's accuracy and the sentiment engine's algorithms. This results in improved performance in future information deliveries and reduces bias towards election information.

[0779] (Example 2)

[0780] 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".

[0781] Election-related information is diverse, making it difficult for users to efficiently and fairly obtain information that matches their specific areas of interest. Furthermore, information may be biased or lack the ability to cater to individual user sentiments. This makes it difficult for voters to obtain the information necessary to make informed decisions.

[0782] 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.

[0783] In this invention, the server includes means for automatically collecting election-related information from information sources, means for analyzing the collected information using natural language processing technology and fairly extracting policy information for each candidate, and means for analyzing the user's emotions in real time using emotion recognition technology and dynamically adjusting the information display. This makes it possible to provide users with efficient and personalized election information.

[0784] "Information sources" refers to all sources that provide election-related data, such as public institutions, news media, and social networking services.

[0785] "Natural language processing technology" refers to techniques that enable computers to understand and analyze human language, and includes methods for extracting useful information through the analysis of text data.

[0786] "Emotion recognition technology" refers to technology that analyzes a user's emotional state in real time from their facial expressions and voice, and adjusts the way information is presented based on that analysis.

[0787] "Generative artificial intelligence technology" is a technology that uses artificial intelligence to generate responses in natural human language, making it possible to provide appropriate answers even to complex questions.

[0788] "Feedback" refers to information that includes evaluations and opinions from users regarding the information presented, and is used as data to improve the system and enhance the accuracy of the information.

[0789] "Bias" refers to biases or skews in collected election information, and includes elements that undermine the fairness of the information.

[0790] "Optimization" refers to the process of adjusting the content and format of displayed information based on user interests and emotions to make it as useful as possible for the user.

[0791] This invention is a system that provides election-related information to users efficiently and fairly, and includes information collection, analysis, display, response generation, and collection of user feedback from diverse data sources.

[0792] Data collection and analysis

[0793] The server automatically collects election-related data from sources such as public institutions, news media, and social networking services. This process utilizes web scraping techniques and APIs, such as Python's requests and BeautifulSoup libraries. The collected data is analyzed using natural language processing techniques. Specifically, Python's NLTK and SpaCy are used to analyze text data and fairly extract policy information for each candidate.

[0794] Customized display of information

[0795] The analysis results are sent from the server to the terminal. The user sees the obtained information through the user interface on the terminal. The interface, built with HTML and CSS, visually organizes the information so that the user can easily understand it. Furthermore, the terminal is equipped with emotion recognition technology, which analyzes the user's emotions in real time via OpenCV and the Emotion API and dynamically adjusts the information display.

[0796] Question answering function

[0797] Users can input election-related questions via their terminal. For example, a possible question might be, "Who is most committed to environmental policies in the next local election?" The server uses a generative AI model (e.g., GPT-3) to generate detailed responses to the input questions and provides the appropriately edited responses to the user via their terminal.

[0798] Feedback and system accuracy improvement

[0799] Users can send feedback on the information provided to the server via their device. This feedback is used to improve the overall system performance and the emotion engine algorithm. Based on user feedback, bias in election information will be reduced, and more accurate and unbiased information will be provided.

[0800] The above describes a specific embodiment of the present invention, in which the system provides users with personalized information and responses, enabling them to access election information more effectively.

[0801] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0802] Step 1:

[0803] Data collection

[0804] The server collects election-related data from sources such as public institutions, news media, and social networking services. Specific API endpoints or web URLs are used as input, and data is retrieved based on these through web scraping or API communication. For example, the Python requests library is used to retrieve the latest information from news sites. The output is raw text data.

[0805] Step 2:

[0806] Data Analysis

[0807] The server analyzes the collected raw data using natural language processing techniques. In this step, important key phrases and policy-related information are extracted from the input data, and policy information for each candidate is compiled. Specifically, Python's NLTK and SpaCy are used to tokenize the text, perform POS tagging, and extract important information. The output is the analyzed policy information.

[0808] Step 3:

[0809] Data transmission and display

[0810] The server sends the analysis results to the terminal. The terminal displays the received data in the user interface. Analyzed policy information is received as input and displayed in a user-friendly format using HTML and CSS. Specifically, the policy information is organized in tables and lists and provided to the user in a visually clear manner. The output is the user's visual display.

[0811] Step 4:

[0812] Emotion recognition and display adjustment

[0813] The device uses emotion recognition technology to analyze the user's emotions in real time from their facial expressions and voice. Data from the camera and microphone is used as input, and analysis is performed using OpenCV and the Emotion API. Based on the user's emotions, the device dynamically adjusts the priority and level of detail of information and updates the displayed content as needed. The output is a customized information display adapted to the user's emotions.

[0814] Step 5:

[0815] Question and Answer Generation

[0816] The user enters an election-related question through the terminal. The input is provided in text format and sent to the server as a prompt. The server generates a response to the question using a generative AI model (e.g., GPT-3). The generative AI model analyzes the question, searches for relevant information, formats it, and creates a natural language answer. The output is text containing the generated answer, which is returned to the terminal and displayed to the user.

[0817] Step 6:

[0818] Feedback gathering and system improvement

[0819] Users can send feedback on the provided information and responses to the server via their terminal. Input consists of ratings and comments, which the server analyzes and uses to improve the system. Specifically, the feedback is text-mined to help fine-tune the algorithm and improve the accuracy of the information. Output consists of insights and suggestions for system improvement.

[0820] (Application Example 2)

[0821] 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".

[0822] In providing election-related information to voters fairly and efficiently, there is a need for methods that dynamically optimize information based on users' emotions and individual interests to support their decision-making process. In particular, information that users can accept is necessary regarding donations and fundraising for election campaigns.

[0823] 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.

[0824] In this invention, the server includes means for automatically collecting election-related information from information providers, news organizations, and information sharing services; means for analyzing the collected information using natural language processing technology and fairly extracting policy information for each candidate; and means for recognizing the user's emotions in real time using sentiment analysis technology and adjusting the display order and level of detail of the information. This enables the system to dynamically display detailed election-related information in the donation system based on the user's emotions and interests, thereby supporting the user's decision-making.

[0825] "Information providers" are public institutions, media outlets, and other major sources of information that provide data related to elections.

[0826] "Natural language processing technology" is a technique that mechanically analyzes text data and organizes and extracts information in a way that humans can understand.

[0827] "Emotion analysis technology" is a technology that recognizes a user's emotions in real time and adjusts the system's operation based on those emotions.

[0828] A "donation system" is a mechanism used in election campaigns to allow users to provide financial support to candidates or policies.

[0829] "Dynamic display" is a function that instantly changes the content and presentation of information based on the user's current interests and emotions.

[0830] "Supporting decision-making" refers to the act of providing information to enable users to make appropriate choices and take appropriate actions based on election-related information.

[0831] To implement this invention, a system is needed in which the server performs the following roles. First, the server automatically collects election-related data from information providers, news organizations, and information sharing services and stores it in a database. This collected data is analyzed using natural language processing technology with the Google Cloud Natural Language API to accurately extract policy information for each candidate.

[0832] Next, the analyzed information is evaluated in real time on the user's device using sentiment analysis technology with the Microsoft Azure Emotion API. The device dynamically adjusts the display order and level of detail of the information via the user interface according to this sentiment data. As a result, users can obtain a more personalized election information acquisition experience.

[0833] Users can indicate their willingness to donate to election campaigns through a smartphone application and make donation decisions after obtaining relevant policy information. Upon receiving user input, the server utilizes generative artificial intelligence technology, using Google Cloud AI to generate responses to the questions.

[0834] For example, a user might be considering donating to a particular election candidate but wants more detailed information about that candidate's economic policies. In this case, if sentiment analysis detects a high level of interest in that information, it will be provided in a detailed and easy-to-understand format.

[0835] An example of a prompt message is, "Display detailed information on Candidate A's latest economic policies, highlighting information that the user is emotionally interested in." This is expected to make the user's decision-making more confident and supportive.

[0836] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0837] Step 1:

[0838] The server collects election-related data from information providers, news organizations, and information sharing services. The input data is initially unprocessed. The server uses web scraping techniques to retrieve the necessary data and saves it to a database.

[0839] Step 2:

[0840] The server analyzes the stored data using the Google Cloud Natural Language API. Using the election-related text data obtained as input, it fairly extracts policy information for each candidate. The output is organized policy information.

[0841] Step 3:

[0842] The server utilizes the Microsoft Azure Emotion API to evaluate the user's emotions in real time. It receives the user's facial expressions and voice as input data from the device and performs emotion analysis. Based on the results, it determines the priority of information display according to the emotion.

[0843] Step 4:

[0844] The terminal receives analysis results and sentiment data, and displays the information using a user interface. Using policy information and sentiment evaluations from the server as input, it dynamically displays information tailored to the user's interests. This results in output that is easier for the user to understand.

[0845] Step 5:

[0846] Users view election campaign information and make donation decisions on a smartphone application. The application displays detailed information about candidates the user is interested in and allows them to answer additional questions as needed.

[0847] Step 6:

[0848] The server uses generative artificial intelligence technology to generate responses to user questions. It receives user questions as input and creates answers using a generative AI model. The generated answers are output and provided to the user again via the terminal.

[0849] 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.

[0850] 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.

[0851] 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.

[0852] 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.

[0853] 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. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, 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.

[0854] 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.

[0855] 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.

[0856] 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.

[0857] 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."

[0858] 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.

[0859] 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.

[0860] 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.

[0861] 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.

[0862] 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.

[0863] 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.

[0864] 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.

[0865] 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.

[0866] 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.

[0867] 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.

[0868] 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.

[0869] 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.

[0870] The following is further disclosed regarding the embodiments described above.

[0871] (Claim 1)

[0872] A means of automatically collecting election-related information from public institutions, news media, and social networking services,

[0873] A method for fairly extracting policy information for each candidate by analyzing information collected using natural language processing technology,

[0874] A means of displaying the analysis results to the user in a customized way via a user interface,

[0875] A means for generating responses using artificial intelligence technology in response to user questions,

[0876] Means used to receive user feedback and improve the accuracy of the information provided,

[0877] A system that includes this.

[0878] (Claim 2)

[0879] The system according to claim 1, which has a function to refer to a user profile and adjust the displayed content based on the user's interests.

[0880] (Claim 3)

[0881] The system according to claim 1, which has the function of detecting bias in election information and reducing bias by acquiring additional information.

[0882] "Example 1"

[0883] (Claim 1)

[0884] Means for automatically collecting information from public institutions, media, and network services,

[0885] A means of analyzing information collected using natural language processing technology and extracting policy information for each target,

[0886] A means of adapting and displaying analysis results to the user via a user interface,

[0887] A means of generating responses using artificial intelligence technology in response to inquiries from users,

[0888] The means used to receive feedback from users and improve the reliability of the information provided,

[0889] A means of classifying and structuring information to enable efficient access,

[0890] A system that includes this.

[0891] (Claim 2)

[0892] The system according to claim 1, which has a function to refer to user information and adjust the displayed content based on the user's interests.

[0893] (Claim 3)

[0894] The system according to claim 1, which has a function to detect bias in election-related information and to acquire additional data to reduce the bias.

[0895] "Application Example 1"

[0896] (Claim 1)

[0897] A means of automatically collecting election-related information from public institutions, media outlets, and social networks,

[0898] A method for fairly extracting policy information for each candidate by analyzing information collected using natural language processing technology,

[0899] A means of displaying customized analysis results to the user via a user interface,

[0900] A means for generating responses using artificial intelligence technology in response to questions from users,

[0901] The means used to receive feedback from users and improve the accuracy of the information provided,

[0902] A means of making donation proposals to specific policies or candidates based on the political interests of users,

[0903] A system that includes this.

[0904] (Claim 2)

[0905] The system according to claim 1, which has a function to refer to the user's profile and adjust the displayed content based on the user's interests.

[0906] (Claim 3)

[0907] The system according to claim 1, which has a function to detect bias in election information and reduce bias by acquiring additional information.

[0908] "Example 2 of combining an emotion engine"

[0909] (Claim 1)

[0910] A means of automatically collecting election-related information from various sources,

[0911] Using natural language processing technology, a means to analyze collected information and fairly extract policy information for each candidate,

[0912] A means of displaying the analysis results to the user in a customized way through a user interface,

[0913] A means of analyzing user emotions in real time using emotion recognition technology and dynamically adjusting information display,

[0914] A means for generating responses using artificial intelligence technology in response to user questions,

[0915] The means used to receive user feedback and improve the accuracy of the information provided,

[0916] A system that includes this.

[0917] (Claim 2)

[0918] The system according to claim 1, which has a function to generate a profile based on user input data and optimize the displayed content based on the user's interests.

[0919] (Claim 3)

[0920] The system according to claim 1, which has a function to detect bias in election information and reduce bias by acquiring additional relevant information.

[0921] "Application example 2 when combining with an emotional engine"

[0922] (Claim 1)

[0923] A means of automatically collecting election-related information from information providers, news organizations, and information sharing services,

[0924] A method for fairly extracting policy information for each candidate by analyzing information collected using natural language processing technology,

[0925] A means of displaying the analysis results to the user in a customized way via a user interface,

[0926] A means for generating responses using artificial intelligence technology in response to user questions,

[0927] Means used to receive user feedback and improve the accuracy of the information provided,

[0928] A means of recognizing the user's emotions in real time using emotion analysis technology and adjusting the display order and level of detail of information,

[0929] A system that includes this.

[0930] (Claim 2)

[0931] The system according to claim 1, which aggregates election-related information in a donation system and has a function to support the decision-making process.

[0932] (Claim 3)

[0933] The system according to claim 1, which has a function to analyze the user's emotions and dynamically display details of relevant election information. [Explanation of symbols]

[0934] 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. A means of automatically collecting election-related information from public institutions, news media, and social networking services, A method for fairly extracting policy information for each candidate by analyzing information collected using natural language processing technology, A means of displaying the analysis results to the user in a customized way via a user interface, A means for generating responses using artificial intelligence technology in response to user questions, Means used to receive user feedback and improve the accuracy of the information provided, A system that includes this.

2. The system according to claim 1, which has a function to refer to a user profile and adjust the displayed content based on the user's interests.

3. The system according to claim 1, which has a function to detect bias in election information and reduce bias by acquiring additional information.

Images