System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting candidate information, profiles, policies, and election-related news articles; means for summarizing the collected information using a generation AI; means for transmitting the generated summarized information to a user device; means for receiving a question input by a user; means for generating an answer to the received question using the generation AI; and means for transmitting the generated answer to the user device; and means for visualizing the analyzed result and transmitting the visualized result to the user device. AI.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In recent years, voter turnout in various elections has been declining. One of the main reasons for this is confusion caused by an overabundance of information on candidates, policies, and election-related news. This excessive amount of information makes it difficult for voters to obtain the information they need, resulting in a decline in their motivation to vote. Furthermore, with no means of quickly and accurately answering questions about elections, voters' doubts remain unresolved and they lose interest in elections. To improve this situation and increase voter turnout, there is a need to provide effective means of providing information. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for collecting candidate information, profiles, policies, and election-related news articles and summarizing them using a generation AI. It also includes a means for transmitting the generated summary information to a user terminal. Additionally, the system includes a means for receiving questions entered by a user, generating answers using a generation AI, and transmitting the generated answers to the user terminal. This provides a system that includes a means for collecting election-related data, analyzing election predictions and voting trends using a generation AI and data analysis tools, and a means for visualizing and transmitting the analysis results to the user terminal. This allows users to grasp the key points of candidate information concisely, quickly respond to user questions, and increase voters' interest in elections.

[0006] "Candidate information" refers to information about a candidate running for election, including their basic profile, background, past activities, and the electoral district in which they are running.

[0007] "Profile" refers to basic information about an individual candidate, such as name, address, educational background, work history, hobbies, etc.

[0008] "Policies" refers to the specific plans, policies, and goals that a candidate intends to implement if elected.

[0009] "Election-related news articles" refer to articles about candidates, election campaigns, poll results, etc. that are reported during the election period.

[0010] "Generative AI" refers to a system that uses artificial intelligence technology to perform natural language processing and data analysis to generate new information and insights.

[0011] "User terminal" refers to a device such as a smartphone, tablet, or PC that allows a user to use an application via communication functions.

[0012] A "database" is a structured collection of data and a system for efficiently storing, retrieving, and managing information.

[0013] A "question" refers to the text of a question or inquiry that a user enters into the system.

[0014] "Answer" refers to the text that shows the answer generated by the generation AI to the user's question.

[0015] "Election forecasting" refers to a method of estimating future election results based on past data and current trends.

[0016] "Voting trends" refers to patterns in data that indicate trends or fluctuations in voting.

[0017] "Data analysis tools" refers to a general term for software and algorithms used to collect, process, analyze, and visualize data.

[0018] "Visualization" refers to the display of data in a visual format such as a graph, chart, or diagram. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8]FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0020] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0021] First, the terms used in the following description will be explained.

[0022] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0023] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0024] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0025] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0030] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0032] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0033] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0037] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0039] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0040] The present invention aims to improve voter turnout by efficiently providing information about elections through a system equipped with the following functions.

[0041] 1. Candidate information & election news summary function

[0042] System Configuration

[0043] The server collects candidate information, profiles, policies, and election-related news articles from the Internet and specific databases.

[0044] The server preprocesses the collected information and inputs it into a generative AI to generate a summary.

[0045] The server sends the generated summary information to the terminal so that the user can check it through the app.

[0046] Specific examples

[0047] 1. The server collects candidate information and election-related news for the Tokyo City Council election.

[0048] 2. The server passes the collected information to the generation AI, which generates a summary of key policies and profiles.

[0049] 3. The server sends the generated summary information to the device so that the user can view it in the app.

[0050] 2. Information provision function in Q&A format

[0051] System Configuration

[0052] The user enters a question into the app and presses the submit button.

[0053] The terminal sends the user's question to the server.

[0054] The server inputs the question into the generation AI, which generates an appropriate answer.

[0055] The server sends the generated answer to the terminal and displays it to the user.

[0056] Specific examples

[0057] 1. A user asks, "What are Candidate A's key policies?"

[0058] 2. The device sends a question to the server.

[0059] 3. The server uses generative AI to generate answers to the questions.

[0060] 4. The server sends the generated answer to the device, where the user can view it within the app.

[0061] 3. Election prediction, trend analysis, and data visualization functions

[0062] System Configuration

[0063] The server collects election-related data (such as voter turnout, poll data, and past election results).

[0064] The server analyzes the collected data using AI generation and data analysis tools to generate election predictions and voting trends.

[0065] The server visualizes the analysis results as graphs and charts and sends them to the user's device.

[0066] Allow users to view visualized data through the app.

[0067] Specific examples

[0068] 1. The server collects voting trend data for urban and rural areas.

[0069] 2. The server uses generative AI and data analysis tools to predict the election results.

[0070] 3. The server visualizes the prediction results in graphs and charts.

[0071] 4. The server sends this visualization data to the device so that the user can view it within the app.

[0072] The system configuration described above effectively provides candidate information, answers questions, and analyzes election predictions and trends. This allows voters to easily obtain the information they need, raising their interest in elections and contributing to increased voter turnout.

[0073] The processing flow will be explained below.

[0074] 1. Candidate information & election news summary function

[0075] Program processing flow

[0076] Step 1:

[0077] The server periodically collects candidate information, profiles, policies, and election-related news articles from the Internet and specific databases.

[0078] The server retrieves the data using a web scraping tool or API.

[0079] The server stores the acquired data in temporary storage.

[0080] Step 2:

[0081] The server pre-processes and cleans the collected information.

[0082] The server removes unnecessary HTML tags and special characters and formats the text data.

[0083] The server formats the information into a uniform format.

[0084] Step 3:

[0085] The server inputs the preprocessed data into the generation AI to generate summary information.

[0086] The generative AI extracts key points from the input data and generates a summary.

[0087] Step 4:

[0088] The server stores the generated summary information in a database and transmits it to the terminal as needed.

[0089] The server stores the abstract data in the application's database.

[0090] The server transmits the summary data to the terminal in response to a request from the user.

[0091] Step 5:

[0092] The terminal displays the received summary information to the user.

[0093] The terminal displays the summary data on the screen so that the user can check it.

[0094] 2. Information provision function in Q&A format

[0095] Program processing flow

[0096] Step 1:

[0097] The user enters a question into the app and presses the submit button.

[0098] Step 2:

[0099] The terminal sends the user's question to the server.

[0100] The terminal converts the question data into an appropriate format and passes it to the server.

[0101] Step 3:

[0102] The server inputs the question data into the generation AI and begins the answer generation process.

[0103] The generative AI analyzes the question and extracts the information necessary to generate an answer.

[0104] Step 4:

[0105] The server stores the generated answer in a database and sends it to the terminal.

[0106] The server stores the generated answers in an appropriate format.

[0107] The server transmits the saved response data to the terminal.

[0108] Step 5:

[0109] The terminal displays the received answer to the user.

[0110] The terminal displays the answer data on the screen so that the user can check it.

[0111] 3. Election prediction, trend analysis, and data visualization functions

[0112] Program processing flow

[0113] Step 1:

[0114] The server periodically collects election-related data (such as voter turnout, poll data, and past election results).

[0115] The server obtains the required data from multiple data sources.

[0116] The server stores the collected data in temporary storage.

[0117] Step 2:

[0118] The server preprocesses the collected data.

[0119] The server cleans the data by imputing missing values ​​and detecting and removing outliers.

[0120] The server formats the data appropriately for analysis.

[0121] Step 3:

[0122] The server feeds the pre-processed data into generative AI and data analysis tools to generate election predictions and voting trends.

[0123] Generative AI and data analytics tools analyze data and provide predictions and trend analysis.

[0124] Step 4:

[0125] The server inputs the forecast and trend analysis results into a visualization tool to generate graphs and charts.

[0126] The server creates graphs and charts to display the prediction results in a visually easy-to-understand format.

[0127] Step 5:

[0128] The server sends the visualized data to the terminal and displays it to the user.

[0129] The server stores the visualization data in the application's database.

[0130] The server transmits the visualization data to the terminal in response to a user request.

[0131] The terminal displays graphs and charts on the screen for the user to view.

[0132] Example 1

[0133] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0134] In modern elections, voters often lack sufficient information, resulting in low voter turnout. It is difficult for voters to easily access and understand candidate information and election-related news. Even when voters ask specific questions, they often cannot receive immediate answers. Furthermore, predicting and analyzing election results and voting trends is difficult for the average voter, and the scattered nature of the information makes it difficult to make comprehensive judgments. A system that can solve these problems is needed.

[0135] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0136] In this invention, the server includes means for collecting candidate information, profiles, policies, and election-related news articles, means for preprocessing the collected information and generating summaries using a generation AI, means for transmitting the generated summaries to a user terminal, means for receiving questions entered by users, means for preprocessing the received questions and generating answers using a generation AI, means for transmitting the generated answers to the user terminal, means for collecting election-related data and analyzing election predictions and voting trends using a generation AI and a data analysis tool, means for visualizing the analysis results and transmitting them to the user terminal, and means for displaying the received information on the user terminal. This allows voters to obtain election information comprehensively and quickly, contributing to an increase in voter turnout.

[0137] "Candidate information" refers to information about the name, background, past activities, policies, etc. of a person running for election.

[0138] A "profile" is a collection of detailed information about a particular individual, including that individual's career history, educational background, work history, hobbies, etc.

[0139] "Policies" refer to the measures and promises that candidates put forward during the election, as well as the plans and guidelines that they intend to implement after the election.

[0140] "Election-related news articles" are articles containing reports or news about elections, providing information on election progress, candidate activities, election results, etc.

[0141] "Preprocessing" refers to the process of converting collected data into a format suitable for analysis or generative AI, and includes data cleaning, tokenization, normalization, etc.

[0142] "Generative AI" refers to an artificial intelligence model that learns from large amounts of data to generate text and information, and has technology specialized in natural language processing.

[0143] A "user terminal" is a device used by a user, such as a computer or smartphone, that displays information and accepts operations through applications.

[0144] "Tokenization" is the process of dividing text data into units such as words and sentences, and is performed as a preliminary step in natural language processing.

[0145] "Data analysis tools" are software and libraries used to process and analyze collected data based on statistical analysis and machine learning models.

[0146] "Visualization" refers to displaying data in a visually easy-to-understand manner, and refers to representing it as a graph or chart.

[0147] A "RESTful API" is a standardized interface for exchanging data between web services, and is based on HTTP.

[0148] "JSON" stands for JavaScript Object Notation and is a lightweight data format for structuring and representing data.

[0149] MODE FOR CARRYING OUT THE INVENTION

[0150] The present invention provides a system for efficiently providing information about elections and aiming to increase voter turnout. Detailed embodiments for realizing the following various functions are described below.

[0151] Candidate information & election news summary feature

[0152] System Configuration

[0153] The server collects candidate information, profiles, policies, and election-related news articles from the internet and specific databases using APIs and web scraping tools.

[0154] The server preprocesses the collected information, tokenizing and normalizing it using natural language processing tools such as NLTK and spaCy.

[0155] The server inputs the preprocessed information into a generative AI (e.g., GPT-4) to generate a summary.

[0156] The server sends the generated summary information to the terminal in JSON format via a RESTful API.

[0157] Users can check the summary information sent through the app. Specifically, the app parses the received JSON data and displays it on the screen.

[0158] Specific examples

[0159] A server collects candidate information and latest news about a particular city council election.

[0160] The server preprocesses the collected data and sends the generation AI a prompt: "Please summarize Candidate A's profile and key policies."

[0161] The server sends the generated summary to the user's device and displays it in the app.

[0162] Q&A format information provision function

[0163] System Configuration

[0164] The user enters a question in the app and presses the submit button, which sends the question to the server as an HTTP POST request.

[0165] The server pre-processes the received questions by tokenizing and parsing them.

[0166] The server inputs the preprocessed questions into a generative AI (e.g., GPT-4) to generate appropriate answers.

[0167] The server sends the generated response in JSON format to the terminal.

[0168] The user can check the submitted answers in the app, which parses the received JSON data and displays it on the screen.

[0169] Specific examples

[0170] A user asks, "What are Candidate A's key policies?"

[0171] The terminal sends the question to the server, and the server sends the prompt to the generation AI: "Please briefly explain Candidate A's policies."

[0172] The server sends the generated answer to the user's device and displays it in the app.

[0173] Election forecasts, trend analysis, and data visualization features

[0174] System Configuration

[0175] The server collects election-related data (such as voter turnout, poll data, and past election results) using APIs and database queries.

[0176] The server preprocesses and analyzes the collected data using data analysis tools (e.g., Pandas and NumPy).

[0177] The server then feeds the preprocessed data into generative AI (e.g., GPT-4) and machine learning models to predict election results and voting trends.

[0178] The server converts the prediction results into graphs or charts using a data visualization tool (e.g., Matplotlib or Plotly) and sends them to the terminal in JSON format.

[0179] Users can view the visualization data sent through the app, which parses the received data and displays it as an interactive graph.

[0180] Specific examples

[0181] The server collects voting trend data from urban and rural areas and uses generative AI and data analysis tools to send a prompt message: "Please predict the results of the next election."

[0182] The server visualizes the prediction results and sends them to the user's device, where they are displayed as interactive graphs in the app.

[0183] The above configuration effectively provides information on candidates, answers questions, and analyzes election predictions and trends, allowing voters to quickly and easily obtain the information they need. This is expected to increase interest in elections and contribute to an increase in voter turnout.

[0184] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0185] Candidate information & election news summary feature

[0186] Step 1: Gather information

[0187] The server collects candidate information, profiles, policies, and election-related news articles from the Internet and specific databases.

[0188] Input: Raw data obtained via API or web scraping.

[0189] Output: The raw data collected.

[0190] Specific operation: The server collects data using RESTful APIs or web scraping tools (e.g., BeautifulSoup) and stores it in an internal database.

[0191] Step 2: Preprocessing the information

[0192] The server performs pre-processing such as tokenization and normalization of the collected information.

[0193] Input: Raw data collected.

[0194] Output: Preprocessed data.

[0195] What happens: The server uses natural language processing tools (e.g., NLTK or spaCy) to cleanse the text data and remove unnecessary characters and formatting.

[0196] Step 3: Generate a summary

[0197] The server inputs the preprocessed data into a generative AI model (e.g., GPT-4) to generate a summary.

[0198] Input: Preprocessed data and a prompt to the generative AI (e.g., "Please summarize Candidate A's profile and key policies.").

[0199] Output: The generated summary.

[0200] Specific operation: The server sends the preprocessed data and prompt sentences to the generative AI model and receives the resulting summary.

[0201] Step 4: Submit summary information

[0202] The server transmits the generated summary information to the terminal.

[0203] Input: The generated summary.

[0204] Output: Summary data in JSON format sent to the user's device.

[0205] Specific operation: The server uses a RESTful API to send summary data to the user terminal.

[0206] Step 5: View summary information

[0207] The device allows the user to view summary information sent through the app.

[0208] Input: JSON data received by the user device.

[0209] Output: Summary information displayed on the screen.

[0210] Specific operation: The terminal parses the received JSON data and displays the information using a GUI.

[0211] Q&A format information provision function

[0212] Step 1: Submit your question

[0213] The user enters a question into the app and presses the submit button.

[0214] Input: The text of the question entered by the user.

[0215] Output: Send request.

[0216] What happens: The app captures user input and sends an HTTP POST request to the server.

[0217] Step 2: Ask a question

[0218] The terminal sends the user's question to the server.

[0219] Input: The outgoing request from the app.

[0220] Output: The query data received by the server.

[0221] Specific operation: The terminal sends an HTTP POST request, which is received by the server.

[0222] Step 3: Preprocessing the Question

[0223] The server preprocesses the received query.

[0224] Input: The raw query data as it arrives at the server.

[0225] Output: Preprocessed question data.

[0226] Specific operation: The server tokenizes and parses the question data into a format suitable for the generative AI.

[0227] Step 4: Generate an answer

[0228] The server inputs the preprocessed question into a generative AI model (e.g., GPT-4) to generate an answer.

[0229] Input: Preprocessed question data and prompt statement (e.g., "What are Candidate A's major policies?").

[0230] Output: The generated answer.

[0231] Specific operation: The server sends the preprocessed question data and prompt sentence to the generation AI and receives the resulting answer.

[0232] Step 5: Submit your response

[0233] The server sends the generated response to the terminal.

[0234] Input: The generated answer.

[0235] Output: JSON formatted answer data sent to the user's device.

[0236] Specific operation: The server sends the answer data to the user terminal using a RESTful API.

[0237] Step 6: View your answers

[0238] The device allows the user to check the submitted answers within the app.

[0239] Input: JSON data received by the user device.

[0240] Output: The answers displayed on the screen.

[0241] Specific operation: The terminal parses the received JSON data and displays the information using a GUI.

[0242] Election forecasts, trend analysis, and data visualization features

[0243] Step 1: Collect data

[0244] The server collects election-related data (such as voter turnout, poll data, and past election results).

[0245] Input: Raw data retrieved via API or database query.

[0246] Output: The raw data collected.

[0247] Specific operation: The server collects the necessary data through APIs and database queries and stores it in an internal database.

[0248] Step 2: Preprocessing the data

[0249] The server preprocesses the collected data using data analysis tools (e.g., Pandas and NumPy).

[0250] Input: Raw data collected.

[0251] Output: Preprocessed data.

[0252] Specific operation: The server uses Pandas and NumPy to clean the data and process it statistically.

[0253] Step 3: Generate prediction results

[0254] The server inputs the preprocessed data into generative AI (e.g., GPT-4) and machine learning models to generate predictions.

[0255] Input: Preprocessed data and a prompt (e.g., "Based on urban and rural voting trend data, please predict the outcome of the upcoming election.").

[0256] Output: The generated prediction results.

[0257] Specific operation: The server sends the preprocessed data and prompt sentences to the generation AI and receives the prediction results.

[0258] Step 4: Data visualization

[0259] The server visualizes the prediction results as graphs and charts.

[0260] Input: The generated prediction results.

[0261] Output: Visualized graphs and charts.

[0262] Specific operation: The server visualizes the data using Matplotlib or Plotly and converts it into an image file or HTML.

[0263] Step 5: Send visualization data

[0264] The server transmits the generated visualization data to the terminal.

[0265] Input: A visualized graph or chart.

[0266] Output: Visualized data sent to the user's device.

[0267] Specific operation: The server sends visualization data to the user's terminal using a RESTful API.

[0268] Step 6: Displaying the visualized data

[0269] The device allows the user to view the transmitted visualization data within the app.

[0270] Input: Visualization data received by the user terminal.

[0271] Output: Visualized graphs and charts displayed on the screen.

[0272] Specific operation: The device parses the data it receives and displays it as an interactive graph.

[0273] The above are the processing steps for carrying out the present invention, and this system allows users to obtain comprehensive and quick information about elections.

[0274] (Application example 1)

[0275] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0276] The challenge is to make it easier for users to efficiently obtain and understand election information, as well as to raise interest in elections and encourage actual voting behavior. In particular, there is a need for a method to provide election information intuitively and in real time in physical stores.

[0277] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0278] In this invention, the server includes means for collecting candidate information, profiles, policies, and election-related news articles, means for summarizing the collected information using a generation AI, means for transmitting the generated summary information to a display device, means for receiving questions entered by users, means for generating answers to the received questions using a generation AI, means for transmitting the generated answers to a display device, means for collecting election-related data and analyzing election predictions and voting trends using a generation AI and a data analysis tool, means for visualizing the analysis results and transmitting them to a display device, and means for providing the collected election information and prediction data to users in physical stores using AR technology. This allows users to intuitively obtain election information in real time even in physical stores, thereby increasing their interest in elections.

[0279] "Candidate information" refers to information about the profile, claims, background, and policies of a person running for election.

[0280] A "profile" is basic information about a person, such as background information such as date of birth, educational background, and work history.

[0281] "Policy" refers to the plans and guidelines proposed by candidates to solve public problems.

[0282] "Election-related news articles" is a general term for news and articles reported about elections.

[0283] "Collection" is the act of systematically gathering data or information.

[0284] "Generative AI" is a system that uses artificial intelligence technology to automatically generate and summarize data.

[0285] A "summary" is a concise summary of the original information.

[0286] A "display device" is a device for visually displaying information, such as smart glasses or a display.

[0287] A "question" is a question that a user enters to verify information.

[0288] An "answer" is information or a solution provided to a question.

[0289] "Election-related data" refers to data related to elections, such as voter turnout, opinion poll results, and past election results.

[0290] A "data analysis tool" is software or technology for analyzing data.

[0291] An "election forecast" is an analytical result that predicts the outcome of an election in advance.

[0292] "Voting trends" are changes in data regarding voting behavior and tendencies.

[0293] "Visualization" is a method of visually representing data.

[0294] "AR technology" stands for augmented reality technology, which is a technology that overlays digital information onto the real-world environment.

[0295] "Users in a physical store" refers to consumers or customers who visit a particular physical store.

[0296] The present invention is a system that efficiently collects and summarizes candidate information and election-related news and provides it to users. This system uses augmented reality (AR) technology to provide election information to users, particularly in brick-and-mortar stores. Specific embodiments of the system are described below.

[0297] System Configuration

[0298] The system includes a server, a display device (e.g., smart glasses or a head-mounted display), and a network within a physical store. The server operates using the following hardware and software:

[0299] Hardware: High-performance server connected to the Internet

[0300] Software: Python, Hugging Face transformers library, data analysis tools, OpenCV library

[0301] Collecting and summarizing candidate information and news

[0302] The server automatically collects election-related data from the internet and specific databases, including candidate information, profiles, key policies, and election-related news articles, and generates summaries using a generative AI model that uses Hugging Face's transformers library.

[0303] Question and Answer Function

[0304] The server receives questions from users and generates appropriate answers. At this time, the questions are input into a generative AI model, and the AI ​​generates appropriate answers and sends them to the user's display device. An example of a question a user might ask is, "What are Candidate A's main policies?"

[0305] Election predictions and trend analysis

[0306] The server collects election-related data (such as voter turnout, opinion poll data, and past election results) and uses data analysis tools to predict election results and analyze voting trends. The generated analysis results are visualized as graphs and charts and sent to a display device.

[0307] Providing information using AR technology

[0308] Users in physical stores can wear smart glasses or head-mounted displays and intuitively obtain election information on the spot through AR technology. For example, when they enter a specific election information area, candidate profiles and the latest election news are displayed in their field of vision. Furthermore, when a user asks through the smart glasses, "What are Candidate A's main policies?", the server uses generative AI to instantly provide an answer and displays it on the smart glasses.

[0309] Examples of concrete examples and prompts

[0310] For example, when a user wears smart glasses in a brick-and-mortar store and enters the election information area, the following information is displayed:

[0311] Candidate A's main policies:

[0312] education reform

[0313] environmental protection

[0314] Revitalizing the local economy

[0315] An example prompt is:

[0316] Candidate A has been a teacher for many years and has been active in educational reform. He has also proposed many policies related to environmental protection. In terms of economic policy, he places emphasis on revitalizing the local economy.

[0317] Q: What are Candidate A's key policies?

[0318] This allows users to intuitively obtain election information in real time even in physical stores, thereby increasing their interest in elections.

[0319] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0320] Step 1:

[0321] The server collects candidate information, profiles, policies, and election-related news articles from the Internet and specific databases.

[0322] Input: Election-related data from the internet and specific databases.

[0323] Output: A list of collected candidate information and news articles.

[0324] The server automatically collects election-related information through web scraping and API data acquisition, and stores the collected data for further processing.

[0325] Step 2:

[0326] The server summarizes the collected information using generative AI.

[0327] Input: Collected candidate information, profiles, policies, and election-related news articles.

[0328] Output: Candidate information and news articles summarized by generative AI.

[0329] The server uses Hugging Face's transformers library to summarize information about each candidate and news article, then converts the summarized information into a format that is easy to present to users.

[0330] Step 3:

[0331] The server transmits the generated summary information to the display device.

[0332] Input: Information summarized by the generative AI.

[0333] Output: Summary information sent to the user's display device.

[0334] The server structures the summary information and sends it in an appropriate format (e.g., JSON) to the display device (smart glasses or head-mounted display).

[0335] Step 4:

[0336] The terminal sends the question entered by the user to the server.

[0337] Input: The question entered by the user.

[0338] Output: The query data received by the server.

[0339] The user inputs a question using voice input, eye contact, etc., and the question is sent to the server. The terminal receives the user's question, formats it appropriately, and sends it to the server.

[0340] Step 5:

[0341] The server uses a generation AI to generate an answer to the received question.

[0342] Input: User question and associated election data.

[0343] Output: The answer generated by the generative AI.

[0344] The server uses a generative AI model to generate an appropriate answer to the user's question, inputs a prompt into the model, and passes the resulting answer on to the next step.

[0345] Step 6:

[0346] The server transmits the generated answer to the display device.

[0347] Input: The answer generated by the generative AI.

[0348] Output: The answer sent to the user's display device.

[0349] The server structures the generated answers and sends them to the user's display device for display.

[0350] Step 7:

[0351] The server collects election-related data and uses generative AI and data analysis tools to analyze election predictions and voting trends.

[0352] Input: Election-related data (voter turnout, poll data, past election results).

[0353] Output: Election forecasts and voting trend analysis.

[0354] The server collects election-related data and analyzes it using data analytics tools, including generative AI models, to predict election results and conduct trend analysis.

[0355] Step 8:

[0356] The server visualizes the analysis results and transmits them to a display device.

[0357] Input: Election forecasts and voting trend analysis results.

[0358] Output: Visualized graphs and charts.

[0359] The server visualizes the analysis results in graphs and charts and sends them to the user's display device, allowing the user to visually confirm the analysis results.

[0360] Step 9:

[0361] Users can obtain election information by wearing smart glasses or a head-mounted display in a physical store.

[0362] Input: Summary information, answers, and analysis results sent from the server.

[0363] Output: Visual information displayed on smart glasses or a head-mounted display.

[0364] When users enter a specific election information area, candidate information and the latest election news are displayed in their field of view using AR technology. When users enter a question, the answer is immediately displayed in their field of view.

[0365] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0366] The present invention aims to improve voter turnout by efficiently providing information about elections through a system with the following specific functions and processing flow. In particular, by combining an emotion engine, the present invention realizes dynamic information provision according to the user's emotional state.

[0367] 1. Candidate information & election news summary function

[0368] System Configuration

[0369] The server collects candidate information, profiles, policies, and election-related news articles from the Internet and specific databases.

[0370] The server preprocesses the collected information and inputs it into a generative AI to generate a summary.

[0371] The server sends the generated summary information to the terminal so that the user can view it through the app.

[0372] Specific examples

[0373] 1. The server collects candidate information and election-related news for the Tokyo City Council election.

[0374] 2. The server passes the collected information to the generation AI, which generates a summary of key policies and profiles.

[0375] 3. The server sends the generated summary information to the device so that the user can view it in the app.

[0376] 2. Information provision function in Q&A format

[0377] System Configuration

[0378] The user enters a question into the app and presses the submit button.

[0379] The terminal sends the user's question to the server.

[0380] The server inputs the question into the generation AI and starts the answer generation process.

[0381] The server stores the generated answers in a database and transmits them to the terminal.

[0382] The server activates an emotion engine based on the user's input data to recognize the user's emotion.

[0383] The server adjusts the tone and content of the response based on the emotion recognition results and sends it to the device.

[0384] The terminal displays the final adjusted answer to the user.

[0385] Specific examples

[0386] 1. A user asks, "What are Candidate A's key policies?"

[0387] 2. The device sends a question to the server.

[0388] 3. The server uses generative AI to generate answers to the questions.

[0389] 4. The server temporarily stores the generated answers and activates the emotion engine.

[0390] 5. The server uses an emotion engine to recognize emotions from the user's input data and adjust the tone and content accordingly.

[0391] 6. The server sends this finalized answer to the device, where the user can view it in the app.

[0392] 3. Election prediction, trend analysis, and data visualization functions

[0393] System Configuration

[0394] The server collects election-related data (such as voter turnout, poll data, and past election results).

[0395] The server pre-processes the collected data.

[0396] The server feeds the pre-processed data into generative AI and data analysis tools to generate election predictions and voting trends.

[0397] The server inputs the forecast and trend analysis results into a visualization tool to generate graphs and charts.

[0398] The server transmits the visualized data to the terminal and displays it to the user.

[0399] Specific examples

[0400] 1. The server collects voting trend data for urban and rural areas.

[0401] 2. The server preprocesses the data.

[0402] 3. The server uses generative AI and data analysis tools to predict the election results.

[0403] 4. The server visualizes the prediction results in graphs and charts.

[0404] 5. The server sends this visualization data to the device so that the user can view it within the app.

[0405] 4. Emotion engine integration

[0406] System Configuration

[0407] The server includes an emotion engine that recognizes emotions from user input data.

[0408] The server dynamically adjusts the tone and content of the answers and information generated by the generative AI based on the emotion recognition results.

[0409] The server analyzes the emotion recognition results and stores them in a database for future dialogue improvement.

[0410] Specific examples

[0411] 1. The server collects the questions and feedback data entered by the user.

[0412] 2. The server recognizes the user's emotional state using an emotion engine.

[0413] 3. The server adjusts the tone and content of the answers generated by the generation AI based on the emotion recognition results.

[0414] 4. The server stores the adjusted information and responses in a database for analysis.

[0415] This allows users to effectively obtain the information they need and receive personalized responses based on their own emotions, which can increase interest in elections and contribute to increasing voter turnout.

[0416] The processing flow will be explained below.

[0417] 1. Candidate information & election news summary function

[0418] Program processing flow

[0419] Step 1:

[0420] The server periodically collects candidate information, profiles, policies, and election-related news articles from the Internet and specific databases.

[0421] The server retrieves the data using a web scraping tool or API.

[0422] The server stores the acquired data in temporary storage.

[0423] Step 2:

[0424] The server pre-processes and cleans the collected information.

[0425] The server removes unnecessary HTML tags and special characters and formats the text data.

[0426] The server formats the information into a uniform format.

[0427] Step 3:

[0428] The server inputs the preprocessed data into the generation AI to generate summary information.

[0429] The generative AI extracts key points from the input data and generates a summary.

[0430] Step 4:

[0431] The server stores the generated summary information in a database and transmits it to the terminal as needed.

[0432] The server stores the abstract data in the application's database.

[0433] The server transmits the summary data to the terminal in response to a request from the user.

[0434] Step 5:

[0435] The terminal displays the received summary information to the user.

[0436] The terminal displays the summary data on the screen so that the user can check it.

[0437] 2. Information provision function in Q&A format

[0438] Program processing flow

[0439] Step 1:

[0440] The user enters a question into the app and presses the submit button.

[0441] Step 2:

[0442] The terminal sends the user's question to the server.

[0443] The terminal converts the question data into an appropriate format and passes it to the server.

[0444] Step 3:

[0445] The server inputs the question data into the generation AI and begins the answer generation process.

[0446] The generative AI analyzes the question and extracts the information necessary to generate an answer.

[0447] Step 4:

[0448] The server temporarily stores the generated answers and activates the emotion engine.

[0449] The server stores the generated answers in a database and uses them for emotion recognition processing.

[0450] Step 5:

[0451] The server uses an emotion engine to recognize emotions from the user's input data.

[0452] An emotion engine analyzes the user's input text and identifies an emotional state (e.g., happy, anger, sadness, etc.).

[0453] Step 6:

[0454] The server adjusts the tone and content of the answers generated by the generation AI based on the emotion recognition results.

[0455] The server changes the tone and expression to an appropriate one according to the user's emotional state.

[0456] Step 7:

[0457] The server sends the finalized response to the terminal.

[0458] The server makes an API request that sends the tailored response to the device.

[0459] Step 8:

[0460] The terminal displays the received answer to the user.

[0461] The terminal displays the adjusted answer on the screen so that the user can check it.

[0462] 3. Election prediction, trend analysis, and data visualization functions

[0463] Program processing flow

[0464] Step 1:

[0465] The server periodically collects election-related data (such as voter turnout, poll data, and past election results).

[0466] The server obtains the required data from multiple data sources.

[0467] The server stores the collected data in temporary storage.

[0468] Step 2:

[0469] The server preprocesses the collected data.

[0470] The server cleans the data by imputing missing values ​​and detecting and removing outliers.

[0471] The server formats the data appropriately for analysis.

[0472] Step 3:

[0473] The server feeds the pre-processed data into generative AI and data analysis tools to generate election predictions and voting trends.

[0474] Generative AI and data analytics tools analyze data and provide predictions and trend analysis.

[0475] Step 4:

[0476] The server inputs the forecast and trend analysis results into a visualization tool to generate graphs and charts.

[0477] The server creates graphs and charts to display the prediction results in a visually easy-to-understand format.

[0478] Step 5:

[0479] The server sends the visualized data to the terminal and displays it to the user.

[0480] The server stores the visualization data in the application's database.

[0481] The server transmits the visualization data to the terminal in response to a user request.

[0482] The terminal displays graphs and charts on the screen for the user to view.

[0483] 4. Emotion engine integration

[0484] Program processing flow

[0485] Step 1:

[0486] The server collects user-entered questions and feedback data.

[0487] The server stores the user's input in a database and uses it for subsequent processing.

[0488] Step 2:

[0489] The server uses an emotion engine to recognize emotions from the user's input data.

[0490] An emotion engine analyzes the input text and identifies the user's emotional state.

[0491] Step 3:

[0492] Based on the emotion recognition results, the server dynamically adjusts the tone and content of the answers and information generated by the generation AI.

[0493] Generative AI generates responses that use appropriate expressions and tones depending on the recognized emotion.

[0494] Step 4:

[0495] The server stores the adjusted information and responses in a database for later analysis and improvement.

[0496] The server stores the emotion recognition results in a database and uses them for future improvements and analysis of the dialogue system.

[0497] This allows users to effectively obtain the information they need and receive personalized responses based on their own emotions, which can increase interest in elections and contribute to increasing voter turnout.

[0498] Example 2

[0499] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0500] Conventional election information systems have had difficulty processing large amounts of information appropriately and providing it to users in an easy-to-understand format. Furthermore, while it is essential to provide not only appropriate answers to users' questions but also personalized responses that reflect the user's emotions, there has been a lack of means to achieve this. Furthermore, displaying election predictions and voting trend analysis results in a visually understandable manner has also been a challenge.

[0501] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting candidate information, profiles, policies, and election-related news articles; means for summarizing the collected information using a generative model; means for transmitting the generated summary information to a user terminal; means for receiving questions entered by a user; means for generating answers to the received questions using a generative model; means for transmitting the generated answers to the user terminal; means for recognizing an emotional state from user input data; means for dynamically adjusting the tone and content of the answers based on the emotion recognition results; means for collecting election-related data and analyzing election predictions and voting trends using a generative model and a data analysis tool; and means for visualizing and transmitting the analysis results to the user terminal. This enables efficient provision of information about elections and dynamic provision of information according to the user's emotional state. Furthermore, visually displaying the analysis results of election predictions and voting trends makes it easier for users to understand.

[0502] "Candidate information" refers to basic data about individual candidates running in an election, including their name, background, political party affiliation, contact information, etc.

[0503] A "profile" is a record of a candidate's personal information, past career history, achievements, activities, etc.

[0504] "Policies" refer to the specific plans and proposals that candidates advocate during the election period, including promises related to society, the economy, education, healthcare, etc.

[0505] "Election-related news articles" refers to news articles and news content related to elections, and refers to information disseminated by media and news organizations.

[0506] "Means of collection" refers to the functions and methods for automatically obtaining the necessary data from sources such as the Internet and databases.

[0507] A "generative model" refers to an artificial intelligence model that is trained to generate output based on input data for a specific purpose.

[0508] A "summary" is a concise summary of the main points extracted from collected information.

[0509] A "user terminal" is an electronic device that can receive and display information provided by the system, and includes smartphones, tablets, personal computers, etc.

[0510] The "means for receiving a question" refers to a function or method by which the system receives a question or inquiry sent by a user.

[0511] "Answer generation means" refers to the generative model or algorithm used to generate appropriate answers to user questions.

[0512] "Means for recognizing emotional states" refers to techniques and methods for analyzing user input data to identify the emotions behind it.

[0513] "Dynamic adjustment means" refers to functions or methods for automatically changing the content or tone of information based on emotion recognition results.

[0514] "Data Analysis Tools" means software or platforms used to analyze collected data and generate statistical trends and predictions.

[0515] "Election forecasting" refers to analysis that predicts future election outcomes based on collected data.

[0516] "Voting trend analysis" refers to the analysis of past and current voting data to identify patterns and trends in voting behavior.

[0517] "Visualization" refers to the visual representation of analytical results, using graphs and charts to display data in an easy-to-understand manner.

[0518] This invention is a system that efficiently provides information about elections and aims to increase voter turnout. Specifically, it collects information from the internet and specific databases, generates summaries and answers using a generative AI model, and provides dynamic information based on the user's emotional state. It also analyzes election predictions and voting trends, and visualizes the results to provide to users.

[0519] 1. Candidate information & election news summary function

[0520] In this system, the server first collects candidate information, profiles, policies, and election-related news articles from the internet or specific databases. The collected information is then preprocessed and input into a generative AI model (e.g., a GPT-based model) to generate a summary. The generated summary information is then sent from the server to the user's device, where the user can view it through an app. This series of processes allows users to easily grasp key information related to the election.

[0521] Specific examples

[0522] 1. The server collects candidate information and election-related news for city elections.

[0523] 2. The server passes the collected information to the generation AI, which generates a summary of key policies and profiles.

[0524] 3. The server sends the generated summary information to the device so that the user can view it in the app.

[0525] Prompt Sentence Examples

[0526] "Please create a profile and a summary of key policies for Candidate A in the Tokyo Metropolitan Assembly election."

[0527] 2. Information provision function in Q&A format

[0528] When a user enters and submits a question on the app, the device sends the question to the server. The server uses a generative AI model to generate an answer to the question and an emotion engine to recognize emotions from the user's input data. The server then adjusts the tone and content of the answer based on the emotion recognition results and sends the final answer to the user's device, allowing the user to receive appropriate information.

[0529] Specific examples

[0530] 1. A user asks, "What are Candidate A's key policies?"

[0531] 2. The device sends a question to the server.

[0532] 3. The server uses generative AI to generate answers to the questions.

[0533] 4. The server temporarily stores the generated answers and activates the emotion engine.

[0534] 5. The server uses an emotion engine to recognize emotions from the user's input data and adjust the tone and content accordingly.

[0535] 6. The server sends this finalized answer to the device, where the user can view it in the app.

[0536] Prompt Sentence Examples

[0537] "Please tell me about Candidate A's major policies."

[0538] 3. Election prediction, trend analysis, and data visualization functions

[0539] The system's server collects and preprocesses election-related data (such as voter turnout, opinion poll data, and past election results). The preprocessed data is then input into a generative AI model and data analysis tools to analyze election predictions and voting trends. The results of the prediction and trend analysis are converted into graphs and charts using visualization tools and sent to user devices. This allows users to visually understand election trends.

[0540] Specific examples

[0541] 1. The server collects voting trend data for urban and rural areas.

[0542] 2. The server preprocesses the data.

[0543] 3. The server uses generative AI and data analysis tools to predict the election results.

[0544] 4. The server visualizes the prediction results in graphs and charts.

[0545] 5. The server sends this visualization data to the device so that the user can view it within the app.

[0546] Prompt Sentence Examples

[0547] "Predict the outcome of the next election based on urban and rural voting trends."

[0548] 4. Emotion engine integration

[0549] The server is equipped with an emotion engine that recognizes emotions from user input data. Based on the emotion recognition results, the generative AI model dynamically adjusts the tone and content of the responses and information it generates. This adjusted data is stored in a database and used to improve future interactions.

[0550] Specific examples

[0551] 1. The server collects the questions and feedback data entered by the user.

[0552] 2. The server recognizes the user's emotional state using an emotion engine.

[0553] 3. The server adjusts the tone and content of the answers generated by the generation AI based on the emotion recognition results.

[0554] 4. The server stores the adjusted information and responses in a database for analysis.

[0555] This allows users to effectively obtain the information they need and receive personalized responses based on their own emotions, which can increase interest in elections and contribute to increasing voter turnout.

[0556] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0557] Candidate information & election news summary feature

[0558] Step 1: Gather information

[0559] The server collects candidate information, profiles, policies, and election-related news articles from the Internet and specific databases.

[0560] Input: Raw data from the internet or databases.

[0561] Output: Raw information about each candidate.

[0562] Specific operation: The server uses a web crawler to retrieve text data from major news sites and official databases.

[0563] Step 2: Information preprocessing

[0564] The server preprocesses the collected information and formats it for input into the generative AI.

[0565] Input: Raw data (noisy).

[0566] Output: Preprocessed structured data.

[0567] What it does: The server uses text analysis and natural language processing (NLP) techniques to filter out noise, extract the necessary information, and convert it into structured data.

[0568] Step 3: Summary generation

[0569] The server inputs the preprocessed data into a generative AI model to generate a summary.

[0570] Input: Preprocessed structured data.

[0571] Output: Candidate information and policy summary.

[0572] How it works: The server passes the data prompt to a generative AI model (e.g., a GPT-based model) and generates a summary containing key information for each candidate.

[0573] Step 4: Submit summary information

[0574] The server transmits the generated summary information to the terminal.

[0575] Input: Abstract text.

[0576] Output: Summary sent to the user's terminal.

[0577] Specific operation: The server uses the API to send data to display the generated summary on the user's device in real time.

[0578] Q&A format information provision function

[0579] Step 1: Enter your question

[0580] The user enters a question into the app and presses the submit button.

[0581] Input: The user's question text.

[0582] Output: The question sent to the terminal.

[0583] Specific action: The user types a question into the input form and presses the "Submit" button.

[0584] Step 2: Submit your question

[0585] The terminal sends the user's question to the server.

[0586] Input: The question received from the user.

[0587] Output: The question data passed to the server.

[0588] Specific operation: The device sends the user's input to the server via the API.

[0589] Step 3: Question processing and answer generation

[0590] The server inputs the question into the generative AI model and starts the answer generation process.

[0591] Input: User question data.

[0592] Output: The generated answer.

[0593] What happens: The server passes the prompt to the generative AI model, which generates an appropriate answer.

[0594] Step 4: Save your answers

[0595] The server stores the generated answers in a database.

[0596] Input: The generated answer.

[0597] Output: Answers stored in a database.

[0598] Specific operation: The server temporarily stores the generated answer in a database.

[0599] Step 5: Emotion Recognition

[0600] The server activates an emotion engine based on the user's input data to recognize emotions.

[0601] Input: User question data.

[0602] Output: Emotion recognition results.

[0603] What it does: The emotion engine extracts and tags emotion data from the user's text.

[0604] Step 6: Adjust your answers

[0605] The server adjusts the tone and content of the response based on the emotion recognition results.

[0606] Input: Emotion recognition results and generated answers.

[0607] Output: The final adjusted answer.

[0608] What happens: The server uses the tone adjustment module to personalize the answer and generate the adjusted answer.

[0609] Step 7: Submit and view your responses

[0610] The server sends this finalized answer to the terminal and displays it to the user.

[0611] Input: Final adjusted answer.

[0612] Output: The answer displayed on the terminal.

[0613] Specific operation: The terminal displays the received response on the user interface.

[0614] Election forecasts, trend analysis, and data visualization features

[0615] Step 1: Data collection

[0616] The server collects election-related data (such as voter turnout, poll data, and past election results).

[0617] Input: Various election-related data.

[0618] Output: The raw data collected.

[0619] What happens: The server retrieves the necessary data from data sources (public government data, pollster reports, etc.).

[0620] Step 2: Data Preprocessing

[0621] The server pre-processes the collected data.

[0622] Input: Raw data.

[0623] Output: Preprocessed data.

[0624] Specific operation: The server performs data cleaning and format conversion.

[0625] Step 3: Election predictions

[0626] The server feeds the pre-processed data into generative AI models and data analysis tools to generate election predictions and voting trends.

[0627] Input: Preprocessed data.

[0628] Output: Forecast and trend analysis results.

[0629] What it does: Uses machine learning models to predict poll results and trends.

[0630] Step 4: Data visualization

[0631] The server inputs the forecast and trend analysis results into a visualization tool to generate graphs and charts.

[0632] Input: Forecast and trend analysis results.

[0633] Output: Visualized data in the form of graphs and charts.

[0634] Specific Actions: Use visualization tools (e.g., Tableau, Power BI) to visually display analysis results.

[0635] Step 5: Send visualization data

[0636] The server transmits the visualized data to the terminal and displays it to the user.

[0637] Input: Visualization data in the form of graphs and charts.

[0638] Output: Graphs and charts displayed on the terminal.

[0639] Specific operation: Visualization data is sent from the server to the terminal and displayed on the user interface.

[0640] Emotion engine integration

[0641] Step 1: Collecting Emotional Data

[0642] The server collects the user's input data.

[0643] Input: User questions and feedback data.

[0644] Output: The raw data collected.

[0645] Specific operation: The server passes the user's input text (question, feedback, etc.) to the text analysis module.

[0646] Step 2: Emotion Recognition

[0647] The server uses an emotion engine to recognize the user's emotional state.

[0648] Input: The raw data collected.

[0649] Output: Emotion recognition results.

[0650] What it does: An emotion recognition engine classifies the sentiment of the text (e.g., positive, negative, neutral).

[0651] Step 3: Adjust and save

[0652] The server adjusts the tone and content of the response based on the emotion recognition results and stores them in a database.

[0653] Input: Emotion recognition results and generated answers.

[0654] Output: Tailored information or answers.

[0655] Specific actions: The adjusted information is stored in a database and used to improve services in the future.

[0656] This allows users to effectively obtain the information they need and receive personalized responses that reflect their own emotions.

[0657] (Application example 2)

[0658] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0659] Existing election information systems are limited to providing static information, making it difficult to provide dynamic information tailored to individual users' emotional states and interests. Furthermore, there is a lack of mechanisms for improving the user experience in election-related donations and campaign fund management. The present invention aims to solve these problems and increase voter turnout by motivating users to vote.

[0660] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0661] In this invention, the server includes: means for collecting candidate information, profiles, policies, and election-related news articles; means for summarizing the collected information using a generation AI; means for transmitting the generated summary information to a user terminal; means for receiving questions entered by a user; means for generating answers to the received questions using a generation AI; means for transmitting the generated answers to the user terminal; means for collecting election-related data and analyzing election predictions and voting trends using a generation AI and a data analysis tool; means for visualizing and transmitting the analysis results to the user terminal; means for recognizing the emotional state of the user from the input data; means for dynamically adjusting the tone and content of the answers and information generated by the generation AI based on the emotion recognition results; an electronic payment function for election donations; and means for analyzing the emotion recognition results and storing them in a database for future dialogue improvement. This enables dynamic provision of information according to the user's emotional state and an improved user experience in election donations and campaign management.

[0662] Below are definitions of important words:

[0663] "Candidate information" refers to detailed information such as the name, background, political party affiliation, and policies of a person running for election.

[0664] A "profile" is detailed information including basic information about the candidate, past work history, educational background, etc.

[0665] "Policies" refer to the content of the promises and specific measures that candidates put forward during the election.

[0666] "Election news articles" are articles that summarize the latest events and reports related to elections.

[0667] "Generative AI" is a type of artificial intelligence that performs natural language processing and data generation, summarizing information and generating answers.

[0668] A "user terminal" is a device such as a smartphone, tablet, or PC that a user uses to connect to the Internet and obtain information.

[0669] An "emotional state" is an emotional state (e.g., joy, sadness, anger) recognized from the data and behavior entered by the user.

[0670] "Dynamic adjustment means" refers to a method of changing the tone and content of the answers and information generated by the generative AI in real time based on the emotion recognition results.

[0671] "Electronic payment function" is a technology for conducting monetary transactions via the Internet.

[0672] This invention is a system that aims to increase voter turnout by efficiently providing information about elections. By combining this system with an emotion engine, it is possible to dynamically provide information according to the user's emotional state. This system has the following specific configuration and processing procedures.

[0673] Candidate information & election news summary feature

[0674] System Configuration

[0675] The server collects candidate information, profiles, policies, and election-related news articles from the Internet and specific databases.

[0676] The server preprocesses the collected information and inputs it into a generative AI model to generate a summary.

[0677] The server transmits the generated summary information to the user terminal so that the user can check it through the app.

[0678] Specific examples

[0679] 1. The server collects candidate information and election-related news for city elections.

[0680] 2. The server passes the collected information to a generative AI model to generate summaries of key policies and profiles.

[0681] 3. The server sends the generated summary information to the user's device so that the user can view it in the app.

[0682] Q&A format information provision function

[0683] System Configuration

[0684] The user enters a question into the app and presses the submit button.

[0685] The terminal sends the user's question to the server.

[0686] The server inputs the question into the generative AI model and starts the answer generation process.

[0687] The server stores the generated answers in a database and transmits them to the terminal.

[0688] The server activates an emotion engine based on the user's input data to recognize the user's emotion.

[0689] The server adjusts the tone and content of the response based on the emotion recognition results and sends it to the device.

[0690] The terminal displays the final adjusted answer to the user.

[0691] Specific examples

[0692] 1. A user asks, "What are the candidates' key policies?"

[0693] 2. The device sends a question to the server.

[0694] 3. The server generates an answer to the question using a generative AI model.

[0695] 4. The server temporarily stores the generated answers and activates the emotion engine.

[0696] 5. The server uses an emotion engine to recognize emotions from the user's input data and adjust the tone and content accordingly.

[0697] 6. The server sends this finalized answer to the device, where the user can view it in the app.

[0698] Election forecasts, trend analysis, and data visualization features

[0699] System Configuration

[0700] The server collects election-related data (such as voter turnout, poll data, and past election results).

[0701] The server pre-processes the collected data.

[0702] The server feeds the pre-processed data into generative AI models and data analysis tools to generate election predictions and voting trends.

[0703] The server inputs the forecast and trend analysis results into a visualization tool to generate graphs and charts.

[0704] The server transmits the visualized data to the user terminal and displays it to the user.

[0705] Specific examples

[0706] 1. The server collects voting trend data for urban and rural areas.

[0707] 2. The server preprocesses the data.

[0708] 3. The server uses generative AI models and data analysis tools to predict election outcomes.

[0709] 4. The server visualizes the prediction results in graphs and charts.

[0710] 5. The server sends this visualization data to the user's device so that the user can view it within the app.

[0711] Emotion engine integration

[0712] System Configuration

[0713] The server includes an emotion engine that recognizes emotions from user input data.

[0714] The server dynamically adjusts the tone and content of the answers and information generated by the generative AI model based on the emotion recognition results.

[0715] The server analyzes the emotion recognition results and stores them in a database for future dialogue improvement.

[0716] Specific examples

[0717] 1. The server collects the questions and feedback data entered by the user.

[0718] 2. The server recognizes the user's emotional state using an emotion engine.

[0719] 3. The server adjusts the tone and content of the answers generated by the generative AI model based on the emotion recognition results.

[0720] 4. The server stores the adjusted information and responses in a database for analysis.

[0721] 5. This allows users to effectively obtain the information they need and receive personalized responses based on their emotions.

[0722] Election Contributions and Campaign Management

[0723] As part of this invention, an electronic payment function for campaign donations is built in. Users can make donations through the app, and the results of their donations are updated in real time.

[0724] Prompt Sentence Examples

[0725] "What are the main policies of this candidate?"

[0726] "I want to donate to this candidate, how do I do that?"

[0727] "Predict the results of the next election."

[0728] The server dynamically generates answers to these questions, tailoring responses to the user's emotional state, allowing users to easily and effectively obtain information about the election and make better decisions.

[0729] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0730] Step 1:

[0731] The server collects candidate information, profiles, policies, and election-related news articles from the internet and specific databases. It receives election-related information from external databases and APIs as input and stores the collected data in an internal database. Specific operations include sending HTTP requests and making API calls to retrieve data.

[0732] Step 2:

[0733] The server preprocesses the collected information and converts it into data to be input into the generative AI model. It receives raw data as input, converts character encoding, removes unnecessary information, and converts it into a structured data format. Specific operations include data cleansing and data formatting.

[0734] Step 3:

[0735] The server passes the preprocessed data to a generative AI model to generate summaries of key policies and profiles. It receives structured election-related data as input and outputs text summarized by the model. Specifically, it invokes a natural language processing model and performs the summary generation process.

[0736] Step 4:

[0737] The server sends the generated summary information to the user's device so that the user can view it through the app. The server receives the summary information as input, sends it to the user's device, and displays it. Specifically, data is transferred using a data transmission protocol.

[0738] Step 5:

[0739] The user enters a question into the app and presses the send button. The device receives the text entered by the user as input and sends it to the server. Specifically, the text input and button press events are processed via the user interface.

[0740] Step 6:

[0741] The server receives the user's question, inputs it into the generative AI model, and performs the answer generation process. It receives the user's question text as input and generates the answer text using the generative AI model. Specific operations include analyzing the question text and generating the answer.

[0742] Step 7:

[0743] The server stores the generated answer in a database and sends it to the terminal. The server receives the generated answer text as input, stores it in a database, and sends it to the user's terminal. Specific operations include database operations and the use of data transfer protocols.

[0744] Step 8:

[0745] The server analyzes the user's input data and activates the emotion engine to recognize the user's emotion. It receives the user's question text as input and sends it to the emotion engine cluster to output the emotional state. Specific operations include running the text emotion analysis algorithm.

[0746] Step 9:

[0747] The server adjusts the tone and content of the response based on the emotion recognition results. It receives the recognized emotional state and the generated response text as input, modifies the content and tone, and generates the final response. Specific operations include adjusting the text tone and reframing the content.

[0748] Step 10:

[0749] The server sends the final adjusted answer to the device so that the user can view it within the app. It receives the final adjusted answer as input, sends it to the user's device, and displays it. Specific operations include using a data transmission protocol and displaying it in the user interface.

[0750] Step 11:

[0751] The server collects election-related data and uses generative AI models and data analysis tools to analyze election predictions and voting trends. It receives election data from a database as input, analyzes and predicts, and stores the results internally. Specific operations include running data analysis algorithms and applying predictive models.

[0752] Step 12:

[0753] The server converts the analysis results obtained into graphs and charts using a visualization tool and sends them to the user's device. The server receives the analysis result data as input, converts it into a visual format, and sends it to the user's device. Specific operations include using the data visualization tool and creating graphs.

[0754] Step 13:

[0755] When a user makes a donation through the app, the device uses the electronic payment function to send donation information to the server, receives the donation amount as input, and completes the electronic payment procedure. Specific operations include executing the payment process and recording the transaction.

[0756] Example prompt sentence:

[0757] "What are the main policies of this candidate?"

[0758] "I want to donate to this candidate, how do I do that?"

[0759] "Predict the results of the next election."

[0760] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0761] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0762] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0763] [Second embodiment]

[0764] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0765] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0766] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0767] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0768] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0769] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0770] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0771] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0772] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0773] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0774] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0775] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0776] The present invention aims to improve voter turnout by efficiently providing information about elections through a system equipped with the following functions.

[0777] 1. Candidate information & election news summary function

[0778] System Configuration

[0779] The server collects candidate information, profiles, policies, and election-related news articles from the Internet and specific databases.

[0780] The server preprocesses the collected information and inputs it into a generative AI to generate a summary.

[0781] The server sends the generated summary information to the terminal so that the user can check it through the app.

[0782] Specific examples

[0783] 1. The server collects candidate information and election-related news for the Tokyo City Council election.

[0784] 2. The server passes the collected information to the generation AI, which generates a summary of key policies and profiles.

[0785] 3. The server sends the generated summary information to the device so that the user can view it in the app.

[0786] 2. Information provision function in Q&A format

[0787] System Configuration

[0788] The user enters a question into the app and presses the submit button.

[0789] The terminal sends the user's question to the server.

[0790] The server inputs the question into the generation AI, which generates an appropriate answer.

[0791] The server sends the generated answer to the terminal and displays it to the user.

[0792] Specific examples

[0793] 1. A user asks, "What are Candidate A's key policies?"

[0794] 2. The device sends a question to the server.

[0795] 3. The server uses generative AI to generate answers to the questions.

[0796] 4. The server sends the generated answer to the device, where the user can view it within the app.

[0797] 3. Election prediction, trend analysis, and data visualization functions

[0798] System Configuration

[0799] The server collects election-related data (such as voter turnout, poll data, and past election results).

[0800] The server analyzes the collected data using AI generation and data analysis tools to generate election predictions and voting trends.

[0801] The server visualizes the analysis results as graphs and charts and sends them to the user's device.

[0802] Allow users to view visualized data through the app.

[0803] Specific examples

[0804] 1. The server collects voting trend data for urban and rural areas.

[0805] 2. The server uses generative AI and data analysis tools to predict the election results.

[0806] 3. The server visualizes the prediction results in graphs and charts.

[0807] 4. The server sends this visualization data to the device so that the user can view it within the app.

[0808] The system configuration described above effectively provides candidate information, answers questions, and analyzes election predictions and trends. This allows voters to easily obtain the information they need, raising their interest in elections and contributing to increased voter turnout.

[0809] The processing flow will be explained below.

[0810] 1. Candidate information & election news summary function

[0811] Program processing flow

[0812] Step 1:

[0813] The server periodically collects candidate information, profiles, policies, and election-related news articles from the Internet and specific databases.

[0814] The server retrieves the data using a web scraping tool or API.

[0815] The server stores the acquired data in temporary storage.

[0816] Step 2:

[0817] The server pre-processes and cleans the collected information.

[0818] The server removes unnecessary HTML tags and special characters and formats the text data.

[0819] The server formats the information into a uniform format.

[0820] Step 3:

[0821] The server inputs the preprocessed data into the generation AI to generate summary information.

[0822] The generative AI extracts key points from the input data and generates a summary.

[0823] Step 4:

[0824] The server stores the generated summary information in a database and transmits it to the terminal as needed.

[0825] The server stores the abstract data in the application's database.

[0826] The server transmits the summary data to the terminal in response to a request from the user.

[0827] Step 5:

[0828] The terminal displays the received summary information to the user.

[0829] The terminal displays the summary data on the screen so that the user can check it.

[0830] 2. Information provision function in Q&A format

[0831] Program processing flow

[0832] Step 1:

[0833] The user enters a question into the app and presses the submit button.

[0834] Step 2:

[0835] The terminal sends the user's question to the server.

[0836] The terminal converts the question data into an appropriate format and passes it to the server.

[0837] Step 3:

[0838] The server inputs the question data into the generation AI and begins the answer generation process.

[0839] The generative AI analyzes the question and extracts the information necessary to generate an answer.

[0840] Step 4:

[0841] The server stores the generated answer in a database and sends it to the terminal.

[0842] The server stores the generated answers in an appropriate format.

[0843] The server transmits the saved response data to the terminal.

[0844] Step 5:

[0845] The terminal displays the received answer to the user.

[0846] The terminal displays the answer data on the screen so that the user can check it.

[0847] 3. Election prediction, trend analysis, and data visualization functions

[0848] Program processing flow

[0849] Step 1:

[0850] The server periodically collects election-related data (such as voter turnout, poll data, and past election results).

[0851] The server obtains the required data from multiple data sources.

[0852] The server stores the collected data in temporary storage.

[0853] Step 2:

[0854] The server preprocesses the collected data.

[0855] The server cleans the data by imputing missing values ​​and detecting and removing outliers.

[0856] The server formats the data appropriately for analysis.

[0857] Step 3:

[0858] The server feeds the pre-processed data into generative AI and data analysis tools to generate election predictions and voting trends.

[0859] Generative AI and data analytics tools analyze data and provide predictions and trend analysis.

[0860] Step 4:

[0861] The server inputs the forecast and trend analysis results into a visualization tool to generate graphs and charts.

[0862] The server creates graphs and charts to display the prediction results in a visually easy-to-understand format.

[0863] Step 5:

[0864] The server sends the visualized data to the terminal and displays it to the user.

[0865] The server stores the visualization data in the application's database.

[0866] The server transmits the visualization data to the terminal in response to a user request.

[0867] The terminal displays graphs and charts on the screen for the user to view.

[0868] Example 1

[0869] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0870] In modern elections, voters often lack sufficient information, resulting in low voter turnout. It is difficult for voters to easily access and understand candidate information and election-related news. Even when voters ask specific questions, they often cannot receive immediate answers. Furthermore, predicting and analyzing election results and voting trends is difficult for the average voter, and the scattered nature of the information makes it difficult to make comprehensive judgments. A system that can solve these problems is needed.

[0871] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0872] In this invention, the server includes means for collecting candidate information, profiles, policies, and election-related news articles, means for preprocessing the collected information and generating summaries using a generation AI, means for transmitting the generated summaries to a user terminal, means for receiving questions entered by users, means for preprocessing the received questions and generating answers using a generation AI, means for transmitting the generated answers to the user terminal, means for collecting election-related data and analyzing election predictions and voting trends using a generation AI and a data analysis tool, means for visualizing the analysis results and transmitting them to the user terminal, and means for displaying the received information on the user terminal. This allows voters to obtain election information comprehensively and quickly, contributing to an increase in voter turnout.

[0873] "Candidate information" refers to information about the name, background, past activities, policies, etc. of a person running for election.

[0874] A "profile" is a collection of detailed information about a particular individual, including that individual's career history, educational background, work history, hobbies, etc.

[0875] "Policies" refer to the measures and promises that candidates put forward during the election, as well as the plans and guidelines that they intend to implement after the election.

[0876] "Election-related news articles" are articles containing reports or news about elections, providing information on election progress, candidate activities, election results, etc.

[0877] "Preprocessing" refers to the process of converting collected data into a format suitable for analysis or generative AI, and includes data cleaning, tokenization, normalization, etc.

[0878] "Generative AI" refers to an artificial intelligence model that learns from large amounts of data to generate text and information, and has technology specialized in natural language processing.

[0879] A "user terminal" is a device used by a user, such as a computer or smartphone, that displays information and accepts operations through applications.

[0880] "Tokenization" is the process of dividing text data into units such as words and sentences, and is performed as a preliminary step in natural language processing.

[0881] "Data analysis tools" are software and libraries used to process and analyze collected data based on statistical analysis and machine learning models.

[0882] "Visualization" refers to displaying data in a visually easy-to-understand manner, and refers to representing it as a graph or chart.

[0883] A "RESTful API" is a standardized interface for exchanging data between web services, and is based on HTTP.

[0884] "JSON" stands for JavaScript Object Notation and is a lightweight data format for structuring and representing data.

[0885] MODE FOR CARRYING OUT THE INVENTION

[0886] The present invention provides a system for efficiently providing information about elections and aiming to increase voter turnout. Detailed embodiments for realizing the following various functions are described below.

[0887] Candidate information & election news summary feature

[0888] System Configuration

[0889] The server collects candidate information, profiles, policies, and election-related news articles from the internet and specific databases using APIs and web scraping tools.

[0890] The server preprocesses the collected information, tokenizing and normalizing it using natural language processing tools such as NLTK and spaCy.

[0891] The server inputs the preprocessed information into a generative AI (e.g., GPT-4) to generate a summary.

[0892] The server sends the generated summary information to the terminal in JSON format via a RESTful API.

[0893] Users can check the summary information sent through the app. Specifically, the app parses the received JSON data and displays it on the screen.

[0894] Specific examples

[0895] A server collects candidate information and latest news about a particular city council election.

[0896] The server preprocesses the collected data and sends the generation AI a prompt: "Please summarize Candidate A's profile and key policies."

[0897] The server sends the generated summary to the user's device and displays it in the app.

[0898] Q&A format information provision function

[0899] System Configuration

[0900] The user enters a question in the app and presses the submit button, which sends the question to the server as an HTTP POST request.

[0901] The server pre-processes the received questions by tokenizing and parsing them.

[0902] The server inputs the preprocessed questions into a generative AI (e.g., GPT-4) to generate appropriate answers.

[0903] The server sends the generated response in JSON format to the terminal.

[0904] The user can check the submitted answers in the app, which parses the received JSON data and displays it on the screen.

[0905] Specific examples

[0906] A user asks, "What are Candidate A's key policies?"

[0907] The terminal sends the question to the server, and the server sends the prompt to the generation AI: "Please briefly explain Candidate A's policies."

[0908] The server sends the generated answer to the user's device and displays it in the app.

[0909] Election forecasts, trend analysis, and data visualization features

[0910] System Configuration

[0911] The server collects election-related data (such as voter turnout, poll data, and past election results) using APIs and database queries.

[0912] The server preprocesses and analyzes the collected data using data analysis tools (e.g., Pandas and NumPy).

[0913] The server then feeds the preprocessed data into generative AI (e.g., GPT-4) and machine learning models to predict election results and voting trends.

[0914] The server converts the prediction results into graphs or charts using a data visualization tool (e.g., Matplotlib or Plotly) and sends them to the terminal in JSON format.

[0915] Users can view the visualization data sent through the app, which parses the received data and displays it as an interactive graph.

[0916] Specific examples

[0917] The server collects voting trend data from urban and rural areas and uses generative AI and data analysis tools to send a prompt message: "Please predict the results of the next election."

[0918] The server visualizes the prediction results and sends them to the user's device, where they are displayed as interactive graphs in the app.

[0919] The above configuration effectively provides information on candidates, answers questions, and analyzes election predictions and trends, allowing voters to quickly and easily obtain the information they need. This is expected to increase interest in elections and contribute to an increase in voter turnout.

[0920] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0921] Candidate information & election news summary feature

[0922] Step 1: Gather information

[0923] The server collects candidate information, profiles, policies, and election-related news articles from the Internet and specific databases.

[0924] Input: Raw data obtained via API or web scraping.

[0925] Output: The raw data collected.

[0926] Specific operation: The server collects data using RESTful APIs or web scraping tools (e.g., BeautifulSoup) and stores it in an internal database.

[0927] Step 2: Preprocessing the information

[0928] The server performs pre-processing such as tokenization and normalization of the collected information.

[0929] Input: Raw data collected.

[0930] Output: Preprocessed data.

[0931] What happens: The server uses natural language processing tools (e.g., NLTK or spaCy) to cleanse the text data and remove unnecessary characters and formatting.

[0932] Step 3: Generate a summary

[0933] The server inputs the preprocessed data into a generative AI model (e.g., GPT-4) to generate a summary.

[0934] Input: Preprocessed data and a prompt to the generative AI (e.g., "Please summarize Candidate A's profile and key policies.").

[0935] Output: The generated summary.

[0936] Specific operation: The server sends the preprocessed data and prompt sentences to the generative AI model and receives the resulting summary.

[0937] Step 4: Submit summary information

[0938] The server transmits the generated summary information to the terminal.

[0939] Input: The generated summary.

[0940] Output: Summary data in JSON format sent to the user's device.

[0941] Specific operation: The server uses a RESTful API to send summary data to the user terminal.

[0942] Step 5: View summary information

[0943] The device allows the user to view summary information sent through the app.

[0944] Input: JSON data received by the user device.

[0945] Output: Summary information displayed on the screen.

[0946] Specific operation: The terminal parses the received JSON data and displays the information using a GUI.

[0947] Q&A format information provision function

[0948] Step 1: Submit your question

[0949] The user enters a question into the app and presses the submit button.

[0950] Input: The text of the question entered by the user.

[0951] Output: Send request.

[0952] What happens: The app captures user input and sends an HTTP POST request to the server.

[0953] Step 2: Ask a question

[0954] The terminal sends the user's question to the server.

[0955] Input: The outgoing request from the app.

[0956] Output: The query data received by the server.

[0957] Specific operation: The terminal sends an HTTP POST request, which is received by the server.

[0958] Step 3: Preprocessing the Question

[0959] The server preprocesses the received query.

[0960] Input: The raw query data as it arrives at the server.

[0961] Output: Preprocessed question data.

[0962] Specific operation: The server tokenizes and parses the question data into a format suitable for the generative AI.

[0963] Step 4: Generate an answer

[0964] The server inputs the preprocessed question into a generative AI model (e.g., GPT-4) to generate an answer.

[0965] Input: Preprocessed question data and prompt statement (e.g., "What are Candidate A's major policies?").

[0966] Output: The generated answer.

[0967] Specific operation: The server sends the preprocessed question data and prompt sentence to the generation AI and receives the resulting answer.

[0968] Step 5: Submit your response

[0969] The server sends the generated response to the terminal.

[0970] Input: The generated answer.

[0971] Output: JSON formatted answer data sent to the user's device.

[0972] Specific operation: The server sends the answer data to the user terminal using a RESTful API.

[0973] Step 6: View your answers

[0974] The device allows the user to check the submitted answers within the app.

[0975] Input: JSON data received by the user device.

[0976] Output: The answers displayed on the screen.

[0977] Specific operation: The terminal parses the received JSON data and displays the information using a GUI.

[0978] Election forecasts, trend analysis, and data visualization features

[0979] Step 1: Collect data

[0980] The server collects election-related data (such as voter turnout, poll data, and past election results).

[0981] Input: Raw data retrieved via API or database query.

[0982] Output: The raw data collected.

[0983] Specific operation: The server collects the necessary data through APIs and database queries and stores it in an internal database.

[0984] Step 2: Preprocessing the data

[0985] The server preprocesses the collected data using data analysis tools (e.g., Pandas and NumPy).

[0986] Input: Raw data collected.

[0987] Output: Preprocessed data.

[0988] Specific operation: The server uses Pandas and NumPy to clean the data and process it statistically.

[0989] Step 3: Generate prediction results

[0990] The server inputs the preprocessed data into generative AI (e.g., GPT-4) and machine learning models to generate predictions.

[0991] Input: Preprocessed data and a prompt (e.g., "Based on urban and rural voting trend data, please predict the outcome of the upcoming election.").

[0992] Output: The generated prediction results.

[0993] Specific operation: The server sends the preprocessed data and prompt sentences to the generation AI and receives the prediction results.

[0994] Step 4: Data visualization

[0995] The server visualizes the prediction results as graphs and charts.

[0996] Input: The generated prediction results.

[0997] Output: Visualized graphs and charts.

[0998] Specific operation: The server visualizes the data using Matplotlib or Plotly and converts it into an image file or HTML.

[0999] Step 5: Send visualization data

[1000] The server transmits the generated visualization data to the terminal.

[1001] Input: A visualized graph or chart.

[1002] Output: Visualized data sent to the user's device.

[1003] Specific operation: The server sends visualization data to the user's terminal using a RESTful API.

[1004] Step 6: Displaying the visualized data

[1005] The device allows the user to view the transmitted visualization data within the app.

[1006] Input: Visualization data received by the user terminal.

[1007] Output: Visualized graphs and charts displayed on the screen.

[1008] Specific operation: The device parses the data it receives and displays it as an interactive graph.

[1009] The above are the processing steps for carrying out the present invention, and this system allows users to obtain comprehensive and quick information about elections.

[1010] (Application example 1)

[1011] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1012] The challenge is to make it easier for users to efficiently obtain and understand election information, as well as to raise interest in elections and encourage actual voting behavior. In particular, there is a need for a method to provide election information intuitively and in real time in physical stores.

[1013] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1014] In this invention, the server includes means for collecting candidate information, profiles, policies, and election-related news articles, means for summarizing the collected information using a generation AI, means for transmitting the generated summary information to a display device, means for receiving questions entered by users, means for generating answers to the received questions using a generation AI, means for transmitting the generated answers to a display device, means for collecting election-related data and analyzing election predictions and voting trends using a generation AI and a data analysis tool, means for visualizing the analysis results and transmitting them to a display device, and means for providing the collected election information and prediction data to users in physical stores using AR technology. This allows users to intuitively obtain election information in real time even in physical stores, thereby increasing their interest in elections.

[1015] "Candidate information" refers to information about the profile, claims, background, and policies of a person running for election.

[1016] A "profile" is basic information about a person, such as background information such as date of birth, educational background, and work history.

[1017] "Policy" refers to the plans and guidelines proposed by candidates to solve public problems.

[1018] "Election-related news articles" is a general term for news and articles reported about elections.

[1019] "Collection" is the act of systematically gathering data or information.

[1020] "Generative AI" is a system that uses artificial intelligence technology to automatically generate and summarize data.

[1021] A "summary" is a concise summary of the original information.

[1022] A "display device" is a device for visually displaying information, such as smart glasses or a display.

[1023] A "question" is a question that a user enters to verify information.

[1024] An "answer" is information or a solution provided to a question.

[1025] "Election-related data" refers to data related to elections, such as voter turnout, opinion poll results, and past election results.

[1026] A "data analysis tool" is software or technology for analyzing data.

[1027] An "election forecast" is an analytical result that predicts the outcome of an election in advance.

[1028] "Voting trends" are changes in data regarding voting behavior and tendencies.

[1029] "Visualization" is a method of visually representing data.

[1030] "AR technology" stands for augmented reality technology, which is a technology that overlays digital information onto the real-world environment.

[1031] "Users in a physical store" refers to consumers or customers who visit a particular physical store.

[1032] The present invention is a system that efficiently collects and summarizes candidate information and election-related news and provides it to users. This system uses augmented reality (AR) technology to provide election information to users, particularly in brick-and-mortar stores. Specific embodiments of the system are described below.

[1033] System Configuration

[1034] The system includes a server, a display device (e.g., smart glasses or a head-mounted display), and a network within a physical store. The server operates using the following hardware and software:

[1035] Hardware: High-performance server connected to the Internet

[1036] Software: Python, Hugging Face transformers library, data analysis tools, OpenCV library

[1037] Collecting and summarizing candidate information and news

[1038] The server automatically collects election-related data from the internet and specific databases, including candidate information, profiles, key policies, and election-related news articles, and generates summaries using a generative AI model that uses Hugging Face's transformers library.

[1039] Question and Answer Function

[1040] The server receives questions from users and generates appropriate answers. At this time, the questions are input into a generative AI model, and the AI ​​generates appropriate answers and sends them to the user's display device. An example of a question a user might ask is, "What are Candidate A's main policies?"

[1041] Election predictions and trend analysis

[1042] The server collects election-related data (such as voter turnout, opinion poll data, and past election results) and uses data analysis tools to predict election results and analyze voting trends. The generated analysis results are visualized as graphs and charts and sent to a display device.

[1043] Providing information using AR technology

[1044] Users in physical stores can wear smart glasses or head-mounted displays and intuitively obtain election information on the spot through AR technology. For example, when they enter a specific election information area, candidate profiles and the latest election news are displayed in their field of vision. Furthermore, when a user asks through the smart glasses, "What are Candidate A's main policies?", the server uses generative AI to instantly provide an answer and displays it on the smart glasses.

[1045] Examples of concrete examples and prompts

[1046] For example, when a user wears smart glasses in a brick-and-mortar store and enters the election information area, the following information is displayed:

[1047] Candidate A's main policies:

[1048] education reform

[1049] environmental protection

[1050] Revitalizing the local economy

[1051] An example prompt is:

[1052] Candidate A has been a teacher for many years and has been active in educational reform. He has also proposed many policies related to environmental protection. In terms of economic policy, he places emphasis on revitalizing the local economy.

[1053] Q: What are Candidate A's key policies?

[1054] This allows users to intuitively obtain election information in real time even in physical stores, thereby increasing their interest in elections.

[1055] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1056] Step 1:

[1057] The server collects candidate information, profiles, policies, and election-related news articles from the Internet and specific databases.

[1058] Input: Election-related data from the internet and specific databases.

[1059] Output: A list of collected candidate information and news articles.

[1060] The server automatically collects election-related information through web scraping and API data acquisition, and stores the collected data for further processing.

[1061] Step 2:

[1062] The server summarizes the collected information using generative AI.

[1063] Input: Collected candidate information, profiles, policies, and election-related news articles.

[1064] Output: Candidate information and news articles summarized by generative AI.

[1065] The server uses Hugging Face's transformers library to summarize information about each candidate and news article, then converts the summarized information into a format that is easy to present to users.

[1066] Step 3:

[1067] The server transmits the generated summary information to the display device.

[1068] Input: Information summarized by the generative AI.

[1069] Output: Summary information sent to the user's display device.

[1070] The server structures the summary information and sends it in an appropriate format (e.g., JSON) to the display device (smart glasses or head-mounted display).

[1071] Step 4:

[1072] The terminal sends the question entered by the user to the server.

[1073] Input: The question entered by the user.

[1074] Output: The query data received by the server.

[1075] The user inputs a question using voice input, eye contact, etc., and the question is sent to the server. The terminal receives the user's question, formats it appropriately, and sends it to the server.

[1076] Step 5:

[1077] The server uses a generation AI to generate an answer to the received question.

[1078] Input: User question and associated election data.

[1079] Output: The answer generated by the generative AI.

[1080] The server uses a generative AI model to generate an appropriate answer to the user's question, inputs a prompt into the model, and passes the resulting answer on to the next step.

[1081] Step 6:

[1082] The server transmits the generated answer to the display device.

[1083] Input: The answer generated by the generative AI.

[1084] Output: The answer sent to the user's display device.

[1085] The server structures the generated answers and sends them to the user's display device for display.

[1086] Step 7:

[1087] The server collects election-related data and uses generative AI and data analysis tools to analyze election predictions and voting trends.

[1088] Input: Election-related data (voter turnout, poll data, past election results).

[1089] Output: Election forecasts and voting trend analysis.

[1090] The server collects election-related data and analyzes it using data analytics tools, including generative AI models, to predict election results and conduct trend analysis.

[1091] Step 8:

[1092] The server visualizes the analysis results and transmits them to a display device.

[1093] Input: Election forecasts and voting trend analysis results.

[1094] Output: Visualized graphs and charts.

[1095] The server visualizes the analysis results in graphs and charts and sends them to the user's display device, allowing the user to visually confirm the analysis results.

[1096] Step 9:

[1097] Users can obtain election information by wearing smart glasses or a head-mounted display in a physical store.

[1098] Input: Summary information, answers, and analysis results sent from the server.

[1099] Output: Visual information displayed on smart glasses or a head-mounted display.

[1100] When users enter a specific election information area, candidate information and the latest election news are displayed in their field of view using AR technology. When users enter a question, the answer is immediately displayed in their field of view.

[1101] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1102] The present invention aims to improve voter turnout by efficiently providing information about elections through a system with the following specific functions and processing flow. In particular, by combining an emotion engine, the present invention realizes dynamic information provision according to the user's emotional state.

[1103] 1. Candidate information & election news summary function

[1104] System Configuration

[1105] The server collects candidate information, profiles, policies, and election-related news articles from the Internet and specific databases.

[1106] The server preprocesses the collected information and inputs it into a generative AI to generate a summary.

[1107] The server sends the generated summary information to the terminal so that the user can view it through the app.

[1108] Specific examples

[1109] 1. The server collects candidate information and election-related news for the Tokyo City Council election.

[1110] 2. The server passes the collected information to the generation AI, which generates a summary of key policies and profiles.

[1111] 3. The server sends the generated summary information to the device so that the user can view it in the app.

[1112] 2. Information provision function in Q&A format

[1113] System Configuration

[1114] The user enters a question into the app and presses the submit button.

[1115] The terminal sends the user's question to the server.

[1116] The server inputs the question into the generation AI and starts the answer generation process.

[1117] The server stores the generated answers in a database and transmits them to the terminal.

[1118] The server activates an emotion engine based on the user's input data to recognize the user's emotion.

[1119] The server adjusts the tone and content of the response based on the emotion recognition results and sends it to the device.

[1120] The terminal displays the final adjusted answer to the user.

[1121] Specific examples

[1122] 1. A user asks, "What are Candidate A's key policies?"

[1123] 2. The device sends a question to the server.

[1124] 3. The server uses generative AI to generate answers to the questions.

[1125] 4. The server temporarily stores the generated answers and activates the emotion engine.

[1126] 5. The server uses an emotion engine to recognize emotions from the user's input data and adjust the tone and content accordingly.

[1127] 6. The server sends this finalized answer to the device, where the user can view it in the app.

[1128] 3. Election prediction, trend analysis, and data visualization functions

[1129] System Configuration

[1130] The server collects election-related data (such as voter turnout, poll data, and past election results).

[1131] The server pre-processes the collected data.

[1132] The server feeds the pre-processed data into generative AI and data analysis tools to generate election predictions and voting trends.

[1133] The server inputs the forecast and trend analysis results into a visualization tool to generate graphs and charts.

[1134] The server transmits the visualized data to the terminal and displays it to the user.

[1135] Specific examples

[1136] 1. The server collects voting trend data for urban and rural areas.

[1137] 2. The server preprocesses the data.

[1138] 3. The server uses generative AI and data analysis tools to predict the election results.

[1139] 4. The server visualizes the prediction results in graphs and charts.

[1140] 5. The server sends this visualization data to the device so that the user can view it within the app.

[1141] 4. Emotion engine integration

[1142] System Configuration

[1143] The server includes an emotion engine that recognizes emotions from user input data.

[1144] The server dynamically adjusts the tone and content of the answers and information generated by the generative AI based on the emotion recognition results.

[1145] The server analyzes the emotion recognition results and stores them in a database for future dialogue improvement.

[1146] Specific examples

[1147] 1. The server collects the questions and feedback data entered by the user.

[1148] 2. The server recognizes the user's emotional state using an emotion engine.

[1149] 3. The server adjusts the tone and content of the answers generated by the generation AI based on the emotion recognition results.

[1150] 4. The server stores the adjusted information and responses in a database for analysis.

[1151] This allows users to effectively obtain the information they need and receive personalized responses based on their own emotions, which can increase interest in elections and contribute to increasing voter turnout.

[1152] The processing flow will be explained below.

[1153] 1. Candidate information & election news summary function

[1154] Program processing flow

[1155] Step 1:

[1156] The server periodically collects candidate information, profiles, policies, and election-related news articles from the Internet and specific databases.

[1157] The server retrieves the data using a web scraping tool or API.

[1158] The server stores the acquired data in temporary storage.

[1159] Step 2:

[1160] The server pre-processes and cleans the collected information.

[1161] The server removes unnecessary HTML tags and special characters and formats the text data.

[1162] The server formats the information into a uniform format.

[1163] Step 3:

[1164] The server inputs the preprocessed data into the generation AI to generate summary information.

[1165] The generative AI extracts key points from the input data and generates a summary.

[1166] Step 4:

[1167] The server stores the generated summary information in a database and transmits it to the terminal as needed.

[1168] The server stores the abstract data in the application's database.

[1169] The server transmits the summary data to the terminal in response to a request from the user.

[1170] Step 5:

[1171] The terminal displays the received summary information to the user.

[1172] The terminal displays the summary data on the screen so that the user can check it.

[1173] 2. Information provision function in Q&A format

[1174] Program processing flow

[1175] Step 1:

[1176] The user enters a question into the app and presses the submit button.

[1177] Step 2:

[1178] The terminal sends the user's question to the server.

[1179] The terminal converts the question data into an appropriate format and passes it to the server.

[1180] Step 3:

[1181] The server inputs the question data into the generation AI and begins the answer generation process.

[1182] The generative AI analyzes the question and extracts the information necessary to generate an answer.

[1183] Step 4:

[1184] The server temporarily stores the generated answers and activates the emotion engine.

[1185] The server stores the generated answers in a database and uses them for emotion recognition processing.

[1186] Step 5:

[1187] The server uses an emotion engine to recognize emotions from the user's input data.

[1188] An emotion engine analyzes the user's input text and identifies an emotional state (e.g., happy, anger, sadness, etc.).

[1189] Step 6:

[1190] The server adjusts the tone and content of the answers generated by the generation AI based on the emotion recognition results.

[1191] The server changes the tone and expression to an appropriate one according to the user's emotional state.

[1192] Step 7:

[1193] The server sends the finalized response to the terminal.

[1194] The server makes an API request that sends the tailored response to the device.

[1195] Step 8:

[1196] The terminal displays the received answer to the user.

[1197] The terminal displays the adjusted answer on the screen so that the user can check it.

[1198] 3. Election prediction, trend analysis, and data visualization functions

[1199] Program processing flow

[1200] Step 1:

[1201] The server periodically collects election-related data (such as voter turnout, poll data, and past election results).

[1202] The server obtains the required data from multiple data sources.

[1203] The server stores the collected data in temporary storage.

[1204] Step 2:

[1205] The server preprocesses the collected data.

[1206] The server cleans the data by imputing missing values ​​and detecting and removing outliers.

[1207] The server formats the data appropriately for analysis.

[1208] Step 3:

[1209] The server feeds the pre-processed data into generative AI and data analysis tools to generate election predictions and voting trends.

[1210] Generative AI and data analytics tools analyze data and provide predictions and trend analysis.

[1211] Step 4:

[1212] The server inputs the forecast and trend analysis results into a visualization tool to generate graphs and charts.

[1213] The server creates graphs and charts to display the prediction results in a visually easy-to-understand format.

[1214] Step 5:

[1215] The server sends the visualized data to the terminal and displays it to the user.

[1216] The server stores the visualization data in the application's database.

[1217] The server transmits the visualization data to the terminal in response to a user request.

[1218] The terminal displays graphs and charts on the screen for the user to view.

[1219] 4. Emotion engine integration

[1220] Program processing flow

[1221] Step 1:

[1222] The server collects user-entered questions and feedback data.

[1223] The server stores the user's input in a database and uses it for subsequent processing.

[1224] Step 2:

[1225] The server uses an emotion engine to recognize emotions from the user's input data.

[1226] An emotion engine analyzes the input text and identifies the user's emotional state.

[1227] Step 3:

[1228] Based on the emotion recognition results, the server dynamically adjusts the tone and content of the answers and information generated by the generation AI.

[1229] Generative AI generates responses that use appropriate expressions and tones depending on the recognized emotion.

[1230] Step 4:

[1231] The server stores the adjusted information and responses in a database for later analysis and improvement.

[1232] The server stores the emotion recognition results in a database and uses them for future improvements and analysis of the dialogue system.

[1233] This allows users to effectively obtain the information they need and receive personalized responses based on their own emotions, which can increase interest in elections and contribute to increasing voter turnout.

[1234] Example 2

[1235] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1236] Conventional election information systems have had difficulty processing large amounts of information appropriately and providing it to users in an easy-to-understand format. Furthermore, while it is essential to provide not only appropriate answers to users' questions but also personalized responses that reflect the user's emotions, there has been a lack of means to achieve this. Furthermore, displaying election predictions and voting trend analysis results in a visually understandable manner has also been a challenge.

[1237] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting candidate information, profiles, policies, and election-related news articles; means for summarizing the collected information using a generative model; means for transmitting the generated summary information to a user terminal; means for receiving questions entered by a user; means for generating answers to the received questions using a generative model; means for transmitting the generated answers to the user terminal; means for recognizing an emotional state from user input data; means for dynamically adjusting the tone and content of the answers based on the emotion recognition results; means for collecting election-related data and analyzing election predictions and voting trends using a generative model and a data analysis tool; and means for visualizing and transmitting the analysis results to the user terminal. This enables efficient provision of information about elections and dynamic provision of information according to the user's emotional state. Furthermore, visually displaying the analysis results of election predictions and voting trends makes it easier for users to understand.

[1238] "Candidate information" refers to basic data about individual candidates running in an election, including their name, background, political party affiliation, contact information, etc.

[1239] A "profile" is a record of a candidate's personal information, past career history, achievements, activities, etc.

[1240] "Policies" refer to the specific plans and proposals that candidates advocate during the election period, including promises related to society, the economy, education, healthcare, etc.

[1241] "Election-related news articles" refers to news articles and news content related to elections, and refers to information disseminated by media and news organizations.

[1242] "Means of collection" refers to the functions and methods for automatically obtaining the necessary data from sources such as the Internet and databases.

[1243] A "generative model" refers to an artificial intelligence model that is trained to generate output based on input data for a specific purpose.

[1244] A "summary" is a concise summary of the main points extracted from collected information.

[1245] A "user terminal" is an electronic device that can receive and display information provided by the system, and includes smartphones, tablets, personal computers, etc.

[1246] The "means for receiving a question" refers to a function or method by which the system receives a question or inquiry sent by a user.

[1247] "Answer generation means" refers to the generative model or algorithm used to generate appropriate answers to user questions.

[1248] "Means for recognizing emotional states" refers to techniques and methods for analyzing user input data to identify the emotions behind it.

[1249] "Dynamic adjustment means" refers to functions or methods for automatically changing the content or tone of information based on emotion recognition results.

[1250] "Data Analysis Tools" means software or platforms used to analyze collected data and generate statistical trends and predictions.

[1251] "Election forecasting" refers to analysis that predicts future election outcomes based on collected data.

[1252] "Voting trend analysis" refers to the analysis of past and current voting data to identify patterns and trends in voting behavior.

[1253] "Visualization" refers to the visual representation of analytical results, using graphs and charts to display data in an easy-to-understand manner.

[1254] This invention is a system that efficiently provides information about elections and aims to increase voter turnout. Specifically, it collects information from the internet and specific databases, generates summaries and answers using a generative AI model, and provides dynamic information based on the user's emotional state. It also analyzes election predictions and voting trends, and visualizes the results to provide to users.

[1255] 1. Candidate information & election news summary function

[1256] In this system, the server first collects candidate information, profiles, policies, and election-related news articles from the internet or specific databases. The collected information is then preprocessed and input into a generative AI model (e.g., a GPT-based model) to generate a summary. The generated summary information is then sent from the server to the user's device, where the user can view it through an app. This series of processes allows users to easily grasp key information related to the election.

[1257] Specific examples

[1258] 1. The server collects candidate information and election-related news for city elections.

[1259] 2. The server passes the collected information to the generation AI, which generates a summary of key policies and profiles.

[1260] 3. The server sends the generated summary information to the device so that the user can view it in the app.

[1261] Prompt Sentence Examples

[1262] "Please create a profile and a summary of key policies for Candidate A in the Tokyo Metropolitan Assembly election."

[1263] 2. Information provision function in Q&A format

[1264] When a user enters and submits a question on the app, the device sends the question to the server. The server uses a generative AI model to generate an answer to the question and an emotion engine to recognize emotions from the user's input data. The server then adjusts the tone and content of the answer based on the emotion recognition results and sends the final answer to the user's device, allowing the user to receive appropriate information.

[1265] Specific examples

[1266] 1. A user asks, "What are Candidate A's key policies?"

[1267] 2. The device sends a question to the server.

[1268] 3. The server uses generative AI to generate answers to the questions.

[1269] 4. The server temporarily stores the generated answers and activates the emotion engine.

[1270] 5. The server uses an emotion engine to recognize emotions from the user's input data and adjust the tone and content accordingly.

[1271] 6. The server sends this finalized answer to the device, where the user can view it in the app.

[1272] Prompt Sentence Examples

[1273] "Please tell me about Candidate A's major policies."

[1274] 3. Election prediction, trend analysis, and data visualization functions

[1275] The system's server collects and preprocesses election-related data (such as voter turnout, opinion poll data, and past election results). The preprocessed data is then input into a generative AI model and data analysis tools to analyze election predictions and voting trends. The results of the prediction and trend analysis are converted into graphs and charts using visualization tools and sent to user devices. This allows users to visually understand election trends.

[1276] Specific examples

[1277] 1. The server collects voting trend data for urban and rural areas.

[1278] 2. The server preprocesses the data.

[1279] 3. The server uses generative AI and data analysis tools to predict the election results.

[1280] 4. The server visualizes the prediction results in graphs and charts.

[1281] 5. The server sends this visualization data to the device so that the user can view it within the app.

[1282] Prompt Sentence Examples

[1283] "Predict the outcome of the next election based on urban and rural voting trends."

[1284] 4. Emotion engine integration

[1285] The server is equipped with an emotion engine that recognizes emotions from user input data. Based on the emotion recognition results, the generative AI model dynamically adjusts the tone and content of the responses and information it generates. This adjusted data is stored in a database and used to improve future interactions.

[1286] Specific examples

[1287] 1. The server collects the questions and feedback data entered by the user.

[1288] 2. The server recognizes the user's emotional state using an emotion engine.

[1289] 3. The server adjusts the tone and content of the answers generated by the generation AI based on the emotion recognition results.

[1290] 4. The server stores the adjusted information and responses in a database for analysis.

[1291] This allows users to effectively obtain the information they need and receive personalized responses based on their own emotions, which can increase interest in elections and contribute to increasing voter turnout.

[1292] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1293] Candidate information & election news summary feature

[1294] Step 1: Gather information

[1295] The server collects candidate information, profiles, policies, and election-related news articles from the Internet and specific databases.

[1296] Input: Raw data from the internet or databases.

[1297] Output: Raw information about each candidate.

[1298] Specific operation: The server uses a web crawler to retrieve text data from major news sites and official databases.

[1299] Step 2: Information preprocessing

[1300] The server preprocesses the collected information and formats it for input into the generative AI.

[1301] Input: Raw data (noisy).

[1302] Output: Preprocessed structured data.

[1303] What it does: The server uses text analysis and natural language processing (NLP) techniques to filter out noise, extract the necessary information, and convert it into structured data.

[1304] Step 3: Summary generation

[1305] The server inputs the preprocessed data into a generative AI model to generate a summary.

[1306] Input: Preprocessed structured data.

[1307] Output: Candidate information and policy summary.

[1308] How it works: The server passes the data prompt to a generative AI model (e.g., a GPT-based model) and generates a summary containing key information for each candidate.

[1309] Step 4: Submit summary information

[1310] The server transmits the generated summary information to the terminal.

[1311] Input: Abstract text.

[1312] Output: Summary sent to the user's terminal.

[1313] Specific operation: The server uses the API to send data to display the generated summary on the user's device in real time.

[1314] Q&A format information provision function

[1315] Step 1: Enter your question

[1316] The user enters a question into the app and presses the submit button.

[1317] Input: The user's question text.

[1318] Output: The question sent to the terminal.

[1319] Specific action: The user types a question into the input form and presses the "Submit" button.

[1320] Step 2: Submit your question

[1321] The terminal sends the user's question to the server.

[1322] Input: The question received from the user.

[1323] Output: The question data passed to the server.

[1324] Specific operation: The device sends the user's input to the server via the API.

[1325] Step 3: Question processing and answer generation

[1326] The server inputs the question into the generative AI model and starts the answer generation process.

[1327] Input: User question data.

[1328] Output: The generated answer.

[1329] What happens: The server passes the prompt to the generative AI model, which generates an appropriate answer.

[1330] Step 4: Save your answers

[1331] The server stores the generated answers in a database.

[1332] Input: The generated answer.

[1333] Output: Answers stored in a database.

[1334] Specific operation: The server temporarily stores the generated answer in a database.

[1335] Step 5: Emotion Recognition

[1336] The server activates an emotion engine based on the user's input data to recognize emotions.

[1337] Input: User question data.

[1338] Output: Emotion recognition results.

[1339] What it does: The emotion engine extracts and tags emotion data from the user's text.

[1340] Step 6: Adjust your answers

[1341] The server adjusts the tone and content of the response based on the emotion recognition results.

[1342] Input: Emotion recognition results and generated answers.

[1343] Output: The final adjusted answer.

[1344] What happens: The server uses the tone adjustment module to personalize the answer and generate the adjusted answer.

[1345] Step 7: Submit and view your responses

[1346] The server sends this finalized answer to the terminal and displays it to the user.

[1347] Input: Final adjusted answer.

[1348] Output: The answer displayed on the terminal.

[1349] Specific operation: The terminal displays the received response on the user interface.

[1350] Election forecasts, trend analysis, and data visualization features

[1351] Step 1: Data collection

[1352] The server collects election-related data (such as voter turnout, poll data, and past election results).

[1353] Input: Various election-related data.

[1354] Output: The raw data collected.

[1355] What happens: The server retrieves the necessary data from data sources (public government data, pollster reports, etc.).

[1356] Step 2: Data Preprocessing

[1357] The server pre-processes the collected data.

[1358] Input: Raw data.

[1359] Output: Preprocessed data.

[1360] Specific operation: The server performs data cleaning and format conversion.

[1361] Step 3: Election predictions

[1362] The server feeds the pre-processed data into generative AI models and data analysis tools to generate election predictions and voting trends.

[1363] Input: Preprocessed data.

[1364] Output: Forecast and trend analysis results.

[1365] What it does: Uses machine learning models to predict poll results and trends.

[1366] Step 4: Data visualization

[1367] The server inputs the forecast and trend analysis results into a visualization tool to generate graphs and charts.

[1368] Input: Forecast and trend analysis results.

[1369] Output: Visualized data in the form of graphs and charts.

[1370] Specific Actions: Use visualization tools (e.g., Tableau, Power BI) to visually display analysis results.

[1371] Step 5: Send visualization data

[1372] The server transmits the visualized data to the terminal and displays it to the user.

[1373] Input: Visualization data in the form of graphs and charts.

[1374] Output: Graphs and charts displayed on the terminal.

[1375] Specific operation: Visualization data is sent from the server to the terminal and displayed on the user interface.

[1376] Emotion engine integration

[1377] Step 1: Collecting Emotional Data

[1378] The server collects the user's input data.

[1379] Input: User questions and feedback data.

[1380] Output: The raw data collected.

[1381] Specific operation: The server passes the user's input text (question, feedback, etc.) to the text analysis module.

[1382] Step 2: Emotion Recognition

[1383] The server uses an emotion engine to recognize the user's emotional state.

[1384] Input: The raw data collected.

[1385] Output: Emotion recognition results.

[1386] What it does: An emotion recognition engine classifies the sentiment of the text (e.g., positive, negative, neutral).

[1387] Step 3: Adjust and save

[1388] The server adjusts the tone and content of the response based on the emotion recognition results and stores them in a database.

[1389] Input: Emotion recognition results and generated answers.

[1390] Output: Tailored information or answers.

[1391] Specific actions: The adjusted information is stored in a database and used to improve services in the future.

[1392] This allows users to effectively obtain the information they need and receive personalized responses that reflect their own emotions.

[1393] (Application example 2)

[1394] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1395] Existing election information systems are limited to providing static information, making it difficult to provide dynamic information tailored to individual users' emotional states and interests. Furthermore, there is a lack of mechanisms for improving the user experience in election-related donations and campaign fund management. The present invention aims to solve these problems and increase voter turnout by motivating users to vote.

[1396] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1397] In this invention, the server includes: means for collecting candidate information, profiles, policies, and election-related news articles; means for summarizing the collected information using a generation AI; means for transmitting the generated summary information to a user terminal; means for receiving questions entered by a user; means for generating answers to the received questions using a generation AI; means for transmitting the generated answers to the user terminal; means for collecting election-related data and analyzing election predictions and voting trends using a generation AI and a data analysis tool; means for visualizing and transmitting the analysis results to the user terminal; means for recognizing the emotional state of the user from the input data; means for dynamically adjusting the tone and content of the answers and information generated by the generation AI based on the emotion recognition results; an electronic payment function for election donations; and means for analyzing the emotion recognition results and storing them in a database for future dialogue improvement. This enables dynamic provision of information according to the user's emotional state and an improved user experience in election donations and campaign management.

[1398] Below are definitions of important words:

[1399] "Candidate information" refers to detailed information such as the name, background, political party affiliation, and policies of a person running for election.

[1400] A "profile" is detailed information including basic information about the candidate, past work history, educational background, etc.

[1401] "Policies" refer to the content of the promises and specific measures that candidates put forward during the election.

[1402] "Election news articles" are articles that summarize the latest events and reports related to elections.

[1403] "Generative AI" is a type of artificial intelligence that performs natural language processing and data generation, summarizing information and generating answers.

[1404] A "user terminal" is a device such as a smartphone, tablet, or PC that a user uses to connect to the Internet and obtain information.

[1405] An "emotional state" is an emotional state (e.g., joy, sadness, anger) recognized from the data and behavior entered by the user.

[1406] "Dynamic adjustment means" refers to a method of changing the tone and content of the answers and information generated by the generative AI in real time based on the emotion recognition results.

[1407] "Electronic payment function" is a technology for conducting monetary transactions via the Internet.

[1408] This invention is a system that aims to increase voter turnout by efficiently providing information about elections. By combining this system with an emotion engine, it is possible to dynamically provide information according to the user's emotional state. This system has the following specific configuration and processing procedures.

[1409] Candidate information & election news summary feature

[1410] System Configuration

[1411] The server collects candidate information, profiles, policies, and election-related news articles from the Internet and specific databases.

[1412] The server preprocesses the collected information and inputs it into a generative AI model to generate a summary.

[1413] The server transmits the generated summary information to the user terminal so that the user can check it through the app.

[1414] Specific examples

[1415] 1. The server collects candidate information and election-related news for city elections.

[1416] 2. The server passes the collected information to a generative AI model to generate summaries of key policies and profiles.

[1417] 3. The server sends the generated summary information to the user's device so that the user can view it in the app.

[1418] Q&A format information provision function

[1419] System Configuration

[1420] The user enters a question into the app and presses the submit button.

[1421] The terminal sends the user's question to the server.

[1422] The server inputs the question into the generative AI model and starts the answer generation process.

[1423] The server stores the generated answers in a database and transmits them to the terminal.

[1424] The server activates an emotion engine based on the user's input data to recognize the user's emotion.

[1425] The server adjusts the tone and content of the response based on the emotion recognition results and sends it to the device.

[1426] The terminal displays the final adjusted answer to the user.

[1427] Specific examples

[1428] 1. A user asks, "What are the candidates' key policies?"

[1429] 2. The device sends a question to the server.

[1430] 3. The server generates an answer to the question using a generative AI model.

[1431] 4. The server temporarily stores the generated answers and activates the emotion engine.

[1432] 5. The server uses an emotion engine to recognize emotions from the user's input data and adjust the tone and content accordingly.

[1433] 6. The server sends this finalized answer to the device, where the user can view it in the app.

[1434] Election forecasts, trend analysis, and data visualization features

[1435] System Configuration

[1436] The server collects election-related data (such as voter turnout, poll data, and past election results).

[1437] The server pre-processes the collected data.

[1438] The server feeds the pre-processed data into generative AI models and data analysis tools to generate election predictions and voting trends.

[1439] The server inputs the forecast and trend analysis results into a visualization tool to generate graphs and charts.

[1440] The server transmits the visualized data to the user terminal and displays it to the user.

[1441] Specific examples

[1442] 1. The server collects voting trend data for urban and rural areas.

[1443] 2. The server preprocesses the data.

[1444] 3. The server uses generative AI models and data analysis tools to predict election outcomes.

[1445] 4. The server visualizes the prediction results in graphs and charts.

[1446] 5. The server sends this visualization data to the user's device so that the user can view it within the app.

[1447] Emotion engine integration

[1448] System Configuration

[1449] The server includes an emotion engine that recognizes emotions from user input data.

[1450] The server dynamically adjusts the tone and content of the answers and information generated by the generative AI model based on the emotion recognition results.

[1451] The server analyzes the emotion recognition results and stores them in a database for future dialogue improvement.

[1452] Specific examples

[1453] 1. The server collects the questions and feedback data entered by the user.

[1454] 2. The server recognizes the user's emotional state using an emotion engine.

[1455] 3. The server adjusts the tone and content of the answers generated by the generative AI model based on the emotion recognition results.

[1456] 4. The server stores the adjusted information and responses in a database for analysis.

[1457] 5. This allows users to effectively obtain the information they need and receive personalized responses based on their emotions.

[1458] Election Contributions and Campaign Management

[1459] As part of this invention, an electronic payment function for campaign donations is built in. Users can make donations through the app, and the results of their donations are updated in real time.

[1460] Prompt Sentence Examples

[1461] "What are the main policies of this candidate?"

[1462] "I want to donate to this candidate, how do I do that?"

[1463] "Predict the results of the next election."

[1464] The server dynamically generates answers to these questions, tailoring responses to the user's emotional state, allowing users to easily and effectively obtain information about the election and make better decisions.

[1465] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1466] Step 1:

[1467] The server collects candidate information, profiles, policies, and election-related news articles from the internet and specific databases. It receives election-related information from external databases and APIs as input and stores the collected data in an internal database. Specific operations include sending HTTP requests and making API calls to retrieve data.

[1468] Step 2:

[1469] The server preprocesses the collected information and converts it into data to be input into the generative AI model. It receives raw data as input, converts character encoding, removes unnecessary information, and converts it into a structured data format. Specific operations include data cleansing and data formatting.

[1470] Step 3:

[1471] The server passes the preprocessed data to a generative AI model to generate summaries of key policies and profiles. It receives structured election-related data as input and outputs text summarized by the model. Specifically, it invokes a natural language processing model and performs the summary generation process.

[1472] Step 4:

[1473] The server sends the generated summary information to the user's device so that the user can view it through the app. The server receives the summary information as input, sends it to the user's device, and displays it. Specifically, data is transferred using a data transmission protocol.

[1474] Step 5:

[1475] The user enters a question into the app and presses the send button. The device receives the text entered by the user as input and sends it to the server. Specifically, the text input and button press events are processed via the user interface.

[1476] Step 6:

[1477] The server receives the user's question, inputs it into the generative AI model, and performs the answer generation process. It receives the user's question text as input and generates the answer text using the generative AI model. Specific operations include analyzing the question text and generating the answer.

[1478] Step 7:

[1479] The server stores the generated answer in a database and sends it to the terminal. The server receives the generated answer text as input, stores it in a database, and sends it to the user's terminal. Specific operations include database operations and the use of data transfer protocols.

[1480] Step 8:

[1481] The server analyzes the user's input data and activates the emotion engine to recognize the user's emotion. It receives the user's question text as input and sends it to the emotion engine cluster to output the emotional state. Specific operations include running the text emotion analysis algorithm.

[1482] Step 9:

[1483] The server adjusts the tone and content of the response based on the emotion recognition results. It receives the recognized emotional state and the generated response text as input, modifies the content and tone, and generates the final response. Specific operations include adjusting the text tone and reframing the content.

[1484] Step 10:

[1485] The server sends the final adjusted answer to the device so that the user can view it within the app. It receives the final adjusted answer as input, sends it to the user's device, and displays it. Specific operations include using a data transmission protocol and displaying it in the user interface.

[1486] Step 11:

[1487] The server collects election-related data and uses generative AI models and data analysis tools to analyze election predictions and voting trends. It receives election data from a database as input, analyzes and predicts, and stores the results internally. Specific operations include running data analysis algorithms and applying predictive models.

[1488] Step 12:

[1489] The server converts the analysis results obtained into graphs and charts using a visualization tool and sends them to the user's device. The server receives the analysis result data as input, converts it into a visual format, and sends it to the user's device. Specific operations include using the data visualization tool and creating graphs.

[1490] Step 13:

[1491] When a user makes a donation through the app, the device uses the electronic payment function to send donation information to the server, receives the donation amount as input, and completes the electronic payment procedure. Specific operations include executing the payment process and recording the transaction.

[1492] Example prompt sentence:

[1493] "What are the main policies of this candidate?"

[1494] "I want to donate to this candidate, how do I do that?"

[1495] "Predict the results of the next election."

[1496] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1497] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1498] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1499] [Third embodiment]

[1500] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1501] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1502] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1503] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1504] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1505] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1506] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1507] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1508] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1509] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1510] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1511] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1512] The present invention aims to improve voter turnout by efficiently providing information about elections through a system equipped with the following functions.

[1513] 1. Candidate information & election news summary function

[1514] System Configuration

[1515] The server collects candidate information, profiles, policies, and election-related news articles from the Internet and specific databases.

[1516] The server preprocesses the collected information and inputs it into a generative AI to generate a summary.

[1517] The server sends the generated summary information to the terminal so that the user can check it through the app.

[1518] Specific examples

[1519] 1. The server collects candidate information and election-related news for the Tokyo City Council election.

[1520] 2. The server passes the collected information to the generation AI, which generates a summary of key policies and profiles.

[1521] 3. The server sends the generated summary information to the device so that the user can view it in the app.

[1522] 2. Information provision function in Q&A format

[1523] System Configuration

[1524] The user enters a question into the app and presses the submit button.

[1525] The terminal sends the user's question to the server.

[1526] The server inputs the question into the generation AI, which generates an appropriate answer.

[1527] The server sends the generated answer to the terminal and displays it to the user.

[1528] Specific examples

[1529] 1. A user asks, "What are Candidate A's key policies?"

[1530] 2. The device sends a question to the server.

[1531] 3. The server uses generative AI to generate answers to the questions.

[1532] 4. The server sends the generated answer to the device, where the user can view it within the app.

[1533] 3. Election prediction, trend analysis, and data visualization functions

[1534] System Configuration

[1535] The server collects election-related data (such as voter turnout, poll data, and past election results).

[1536] The server analyzes the collected data using AI generation and data analysis tools to generate election predictions and voting trends.

[1537] The server visualizes the analysis results as graphs and charts and sends them to the user's device.

[1538] Allow users to view visualized data through the app.

[1539] Specific examples

[1540] 1. The server collects voting trend data for urban and rural areas.

[1541] 2. The server uses generative AI and data analysis tools to predict the election results.

[1542] 3. The server visualizes the prediction results in graphs and charts.

[1543] 4. The server sends this visualization data to the device so that the user can view it within the app.

[1544] The system configuration described above effectively provides candidate information, answers questions, and analyzes election predictions and trends. This allows voters to easily obtain the information they need, raising their interest in elections and contributing to increased voter turnout.

[1545] The processing flow will be explained below.

[1546] 1. Candidate information & election news summary function

[1547] Program processing flow

[1548] Step 1:

[1549] The server periodically collects candidate information, profiles, policies, and election-related news articles from the Internet and specific databases.

[1550] The server retrieves the data using a web scraping tool or API.

[1551] The server stores the acquired data in temporary storage.

[1552] Step 2:

[1553] The server pre-processes and cleans the collected information.

[1554] The server removes unnecessary HTML tags and special characters and formats the text data.

[1555] The server formats the information into a uniform format.

[1556] Step 3:

[1557] The server inputs the preprocessed data into the generation AI to generate summary information.

[1558] The generative AI extracts key points from the input data and generates a summary.

[1559] Step 4:

[1560] The server stores the generated summary information in a database and transmits it to the terminal as needed.

[1561] The server stores the abstract data in the application's database.

[1562] The server transmits the summary data to the terminal in response to a request from the user.

[1563] Step 5:

[1564] The terminal displays the received summary information to the user.

[1565] The terminal displays the summary data on the screen so that the user can check it.

[1566] 2. Information provision function in Q&A format

[1567] Program processing flow

[1568] Step 1:

[1569] The user enters a question into the app and presses the submit button.

[1570] Step 2:

[1571] The terminal sends the user's question to the server.

[1572] The terminal converts the question data into an appropriate format and passes it to the server.

[1573] Step 3:

[1574] The server inputs the question data into the generation AI and begins the answer generation process.

[1575] The generative AI analyzes the question and extracts the information necessary to generate an answer.

[1576] Step 4:

[1577] The server stores the generated answer in a database and sends it to the terminal.

[1578] The server stores the generated answers in an appropriate format.

[1579] The server transmits the saved response data to the terminal.

[1580] Step 5:

[1581] The terminal displays the received answer to the user.

[1582] The terminal displays the answer data on the screen so that the user can check it.

[1583] 3. Election prediction, trend analysis, and data visualization functions

[1584] Program processing flow

[1585] Step 1:

[1586] The server periodically collects election-related data (such as voter turnout, poll data, and past election results).

[1587] The server obtains the required data from multiple data sources.

[1588] The server stores the collected data in temporary storage.

[1589] Step 2:

[1590] The server preprocesses the collected data.

[1591] The server cleans the data by imputing missing values ​​and detecting and removing outliers.

[1592] The server formats the data appropriately for analysis.

[1593] Step 3:

[1594] The server feeds the pre-processed data into generative AI and data analysis tools to generate election predictions and voting trends.

[1595] Generative AI and data analytics tools analyze data and provide predictions and trend analysis.

[1596] Step 4:

[1597] The server inputs the forecast and trend analysis results into a visualization tool to generate graphs and charts.

[1598] The server creates graphs and charts to display the prediction results in a visually easy-to-understand format.

[1599] Step 5:

[1600] The server sends the visualized data to the terminal and displays it to the user.

[1601] The server stores the visualization data in the application's database.

[1602] The server transmits the visualization data to the terminal in response to a user request.

[1603] The terminal displays graphs and charts on the screen for the user to view.

[1604] Example 1

[1605] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1606] In modern elections, voters often lack sufficient information, resulting in low voter turnout. It is difficult for voters to easily access and understand candidate information and election-related news. Even when voters ask specific questions, they often cannot receive immediate answers. Furthermore, predicting and analyzing election results and voting trends is difficult for the average voter, and the scattered nature of the information makes it difficult to make comprehensive judgments. A system that can solve these problems is needed.

[1607] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1608] In this invention, the server includes means for collecting candidate information, profiles, policies, and election-related news articles, means for preprocessing the collected information and generating summaries using a generation AI, means for transmitting the generated summaries to a user terminal, means for receiving questions entered by users, means for preprocessing the received questions and generating answers using a generation AI, means for transmitting the generated answers to the user terminal, means for collecting election-related data and analyzing election predictions and voting trends using a generation AI and a data analysis tool, means for visualizing the analysis results and transmitting them to the user terminal, and means for displaying the received information on the user terminal. This allows voters to obtain election information comprehensively and quickly, contributing to an increase in voter turnout.

[1609] "Candidate information" refers to information about the name, background, past activities, policies, etc. of a person running for election.

[1610] A "profile" is a collection of detailed information about a particular individual, including that individual's career history, educational background, work history, hobbies, etc.

[1611] "Policies" refer to the measures and promises that candidates put forward during the election, as well as the plans and guidelines that they intend to implement after the election.

[1612] "Election-related news articles" are articles containing reports or news about elections, providing information on election progress, candidate activities, election results, etc.

[1613] "Preprocessing" refers to the process of converting collected data into a format suitable for analysis or generative AI, and includes data cleaning, tokenization, normalization, etc.

[1614] "Generative AI" refers to an artificial intelligence model that learns from large amounts of data to generate text and information, and has technology specialized in natural language processing.

[1615] A "user terminal" is a device used by a user, such as a computer or smartphone, that displays information and accepts operations through applications.

[1616] "Tokenization" is the process of dividing text data into units such as words and sentences, and is performed as a preliminary step in natural language processing.

[1617] "Data analysis tools" are software and libraries used to process and analyze collected data based on statistical analysis and machine learning models.

[1618] "Visualization" refers to displaying data in a visually easy-to-understand manner, and refers to representing it as a graph or chart.

[1619] A "RESTful API" is a standardized interface for exchanging data between web services, and is based on HTTP.

[1620] "JSON" stands for JavaScript Object Notation and is a lightweight data format for structuring and representing data.

[1621] MODE FOR CARRYING OUT THE INVENTION

[1622] The present invention provides a system for efficiently providing information about elections and aiming to increase voter turnout. Detailed embodiments for realizing the following various functions are described below.

[1623] Candidate information & election news summary feature

[1624] System Configuration

[1625] The server collects candidate information, profiles, policies, and election-related news articles from the internet and specific databases using APIs and web scraping tools.

[1626] The server preprocesses the collected information, tokenizing and normalizing it using natural language processing tools such as NLTK and spaCy.

[1627] The server inputs the preprocessed information into a generative AI (e.g., GPT-4) to generate a summary.

[1628] The server sends the generated summary information to the terminal in JSON format via a RESTful API.

[1629] Users can check the summary information sent through the app. Specifically, the app parses the received JSON data and displays it on the screen.

[1630] Specific examples

[1631] A server collects candidate information and latest news about a particular city council election.

[1632] The server preprocesses the collected data and sends the generation AI a prompt: "Please summarize Candidate A's profile and key policies."

[1633] The server sends the generated summary to the user's device and displays it in the app.

[1634] Q&A format information provision function

[1635] System Configuration

[1636] The user enters a question in the app and presses the submit button, which sends the question to the server as an HTTP POST request.

[1637] The server pre-processes the received questions by tokenizing and parsing them.

[1638] The server inputs the preprocessed questions into a generative AI (e.g., GPT-4) to generate appropriate answers.

[1639] The server sends the generated response in JSON format to the terminal.

[1640] The user can check the submitted answers in the app, which parses the received JSON data and displays it on the screen.

[1641] Specific examples

[1642] A user asks, "What are Candidate A's key policies?"

[1643] The terminal sends the question to the server, and the server sends the prompt to the generation AI: "Please briefly explain Candidate A's policies."

[1644] The server sends the generated answer to the user's device and displays it in the app.

[1645] Election forecasts, trend analysis, and data visualization features

[1646] System Configuration

[1647] The server collects election-related data (such as voter turnout, poll data, and past election results) using APIs and database queries.

[1648] The server preprocesses and analyzes the collected data using data analysis tools (e.g., Pandas and NumPy).

[1649] The server then feeds the preprocessed data into generative AI (e.g., GPT-4) and machine learning models to predict election results and voting trends.

[1650] The server converts the prediction results into graphs or charts using a data visualization tool (e.g., Matplotlib or Plotly) and sends them to the terminal in JSON format.

[1651] Users can view the visualization data sent through the app, which parses the received data and displays it as an interactive graph.

[1652] Specific examples

[1653] The server collects voting trend data from urban and rural areas and uses generative AI and data analysis tools to send a prompt message: "Please predict the results of the next election."

[1654] The server visualizes the prediction results and sends them to the user's device, where they are displayed as interactive graphs in the app.

[1655] The above configuration effectively provides information on candidates, answers questions, and analyzes election predictions and trends, allowing voters to quickly and easily obtain the information they need. This is expected to increase interest in elections and contribute to an increase in voter turnout.

[1656] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1657] Candidate information & election news summary feature

[1658] Step 1: Gather information

[1659] The server collects candidate information, profiles, policies, and election-related news articles from the Internet and specific databases.

[1660] Input: Raw data obtained via API or web scraping.

[1661] Output: The raw data collected.

[1662] Specific operation: The server collects data using RESTful APIs or web scraping tools (e.g., BeautifulSoup) and stores it in an internal database.

[1663] Step 2: Preprocessing the information

[1664] The server performs pre-processing such as tokenization and normalization of the collected information.

[1665] Input: Raw data collected.

[1666] Output: Preprocessed data.

[1667] What happens: The server uses natural language processing tools (e.g., NLTK or spaCy) to cleanse the text data and remove unnecessary characters and formatting.

[1668] Step 3: Generate a summary

[1669] The server inputs the preprocessed data into a generative AI model (e.g., GPT-4) to generate a summary.

[1670] Input: Preprocessed data and a prompt to the generative AI (e.g., "Please summarize Candidate A's profile and key policies.").

[1671] Output: The generated summary.

[1672] Specific operation: The server sends the preprocessed data and prompt sentences to the generative AI model and receives the resulting summary.

[1673] Step 4: Submit summary information

[1674] The server transmits the generated summary information to the terminal.

[1675] Input: The generated summary.

[1676] Output: Summary data in JSON format sent to the user's device.

[1677] Specific operation: The server uses a RESTful API to send summary data to the user terminal.

[1678] Step 5: View summary information

[1679] The device allows the user to view summary information sent through the app.

[1680] Input: JSON data received by the user device.

[1681] Output: Summary information displayed on the screen.

[1682] Specific operation: The terminal parses the received JSON data and displays the information using a GUI.

[1683] Q&A format information provision function

[1684] Step 1: Submit your question

[1685] The user enters a question into the app and presses the submit button.

[1686] Input: The text of the question entered by the user.

[1687] Output: Send request.

[1688] What happens: The app captures user input and sends an HTTP POST request to the server.

[1689] Step 2: Ask a question

[1690] The terminal sends the user's question to the server.

[1691] Input: The outgoing request from the app.

[1692] Output: The query data received by the server.

[1693] Specific operation: The terminal sends an HTTP POST request, which is received by the server.

[1694] Step 3: Preprocessing the Question

[1695] The server preprocesses the received query.

[1696] Input: The raw query data as it arrives at the server.

[1697] Output: Preprocessed question data.

[1698] Specific operation: The server tokenizes and parses the question data into a format suitable for the generative AI.

[1699] Step 4: Generate an answer

[1700] The server inputs the preprocessed question into a generative AI model (e.g., GPT-4) to generate an answer.

[1701] Input: Preprocessed question data and prompt statement (e.g., "What are Candidate A's major policies?").

[1702] Output: The generated answer.

[1703] Specific operation: The server sends the preprocessed question data and prompt sentence to the generation AI and receives the resulting answer.

[1704] Step 5: Submit your response

[1705] The server sends the generated response to the terminal.

[1706] Input: The generated answer.

[1707] Output: JSON formatted answer data sent to the user's device.

[1708] Specific operation: The server sends the answer data to the user terminal using a RESTful API.

[1709] Step 6: View your answers

[1710] The device allows the user to check the submitted answers within the app.

[1711] Input: JSON data received by the user device.

[1712] Output: The answers displayed on the screen.

[1713] Specific operation: The terminal parses the received JSON data and displays the information using a GUI.

[1714] Election forecasts, trend analysis, and data visualization features

[1715] Step 1: Collect data

[1716] The server collects election-related data (such as voter turnout, poll data, and past election results).

[1717] Input: Raw data retrieved via API or database query.

[1718] Output: The raw data collected.

[1719] Specific operation: The server collects the necessary data through APIs and database queries and stores it in an internal database.

[1720] Step 2: Preprocessing the data

[1721] The server preprocesses the collected data using data analysis tools (e.g., Pandas and NumPy).

[1722] Input: Raw data collected.

[1723] Output: Preprocessed data.

[1724] Specific operation: The server uses Pandas and NumPy to clean the data and process it statistically.

[1725] Step 3: Generate prediction results

[1726] The server inputs the preprocessed data into generative AI (e.g., GPT-4) and machine learning models to generate predictions.

[1727] Input: Preprocessed data and a prompt (e.g., "Based on urban and rural voting trend data, please predict the outcome of the upcoming election.").

[1728] Output: The generated prediction results.

[1729] Specific operation: The server sends the preprocessed data and prompt sentences to the generation AI and receives the prediction results.

[1730] Step 4: Data visualization

[1731] The server visualizes the prediction results as graphs and charts.

[1732] Input: The generated prediction results.

[1733] Output: Visualized graphs and charts.

[1734] Specific operation: The server visualizes the data using Matplotlib or Plotly and converts it into an image file or HTML.

[1735] Step 5: Send visualization data

[1736] The server transmits the generated visualization data to the terminal.

[1737] Input: A visualized graph or chart.

[1738] Output: Visualized data sent to the user's device.

[1739] Specific operation: The server sends visualization data to the user's terminal using a RESTful API.

[1740] Step 6: Displaying the visualized data

[1741] The device allows the user to view the transmitted visualization data within the app.

[1742] Input: Visualization data received by the user terminal.

[1743] Output: Visualized graphs and charts displayed on the screen.

[1744] Specific operation: The device parses the data it receives and displays it as an interactive graph.

[1745] The above are the processing steps for carrying out the present invention, and this system allows users to obtain comprehensive and quick information about elections.

[1746] (Application example 1)

[1747] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1748] The challenge is to make it easier for users to efficiently obtain and understand election information, as well as to raise interest in elections and encourage actual voting behavior. In particular, there is a need for a method to provide election information intuitively and in real time in physical stores.

[1749] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1750] In this invention, the server includes means for collecting candidate information, profiles, policies, and election-related news articles, means for summarizing the collected information using a generation AI, means for transmitting the generated summary information to a display device, means for receiving questions entered by users, means for generating answers to the received questions using a generation AI, means for transmitting the generated answers to a display device, means for collecting election-related data and analyzing election predictions and voting trends using a generation AI and a data analysis tool, means for visualizing the analysis results and transmitting them to a display device, and means for providing the collected election information and prediction data to users in physical stores using AR technology. This allows users to intuitively obtain election information in real time even in physical stores, thereby increasing their interest in elections.

[1751] "Candidate information" refers to information about the profile, claims, background, and policies of a person running for election.

[1752] A "profile" is basic information about a person, such as background information such as date of birth, educational background, and work history.

[1753] "Policy" refers to the plans and guidelines proposed by candidates to solve public problems.

[1754] "Election-related news articles" is a general term for news and articles reported about elections.

[1755] "Collection" is the act of systematically gathering data or information.

[1756] "Generative AI" is a system that uses artificial intelligence technology to automatically generate and summarize data.

[1757] A "summary" is a concise summary of the original information.

[1758] A "display device" is a device for visually displaying information, such as smart glasses or a display.

[1759] A "question" is a question that a user enters to verify information.

[1760] An "answer" is information or a solution provided to a question.

[1761] "Election-related data" refers to data related to elections, such as voter turnout, opinion poll results, and past election results.

[1762] A "data analysis tool" is software or technology for analyzing data.

[1763] An "election forecast" is an analytical result that predicts the outcome of an election in advance.

[1764] "Voting trends" are changes in data regarding voting behavior and tendencies.

[1765] "Visualization" is a method of visually representing data.

[1766] "AR technology" stands for augmented reality technology, which is a technology that overlays digital information onto the real-world environment.

[1767] "Users in a physical store" refers to consumers or customers who visit a particular physical store.

[1768] The present invention is a system that efficiently collects and summarizes candidate information and election-related news and provides it to users. This system uses augmented reality (AR) technology to provide election information to users, particularly in brick-and-mortar stores. Specific embodiments of the system are described below.

[1769] System Configuration

[1770] The system includes a server, a display device (e.g., smart glasses or a head-mounted display), and a network within a physical store. The server operates using the following hardware and software:

[1771] Hardware: High-performance server connected to the Internet

[1772] Software: Python, Hugging Face transformers library, data analysis tools, OpenCV library

[1773] Collecting and summarizing candidate information and news

[1774] The server automatically collects election-related data from the internet and specific databases, including candidate information, profiles, key policies, and election-related news articles, and generates summaries using a generative AI model that uses Hugging Face's transformers library.

[1775] Question and Answer Function

[1776] The server receives questions from users and generates appropriate answers. At this time, the questions are input into a generative AI model, and the AI ​​generates appropriate answers and sends them to the user's display device. An example of a question a user might ask is, "What are Candidate A's main policies?"

[1777] Election predictions and trend analysis

[1778] The server collects election-related data (such as voter turnout, opinion poll data, and past election results) and uses data analysis tools to predict election results and analyze voting trends. The generated analysis results are visualized as graphs and charts and sent to a display device.

[1779] Providing information using AR technology

[1780] Users in physical stores can wear smart glasses or head-mounted displays and intuitively obtain election information on the spot through AR technology. For example, when they enter a specific election information area, candidate profiles and the latest election news are displayed in their field of vision. Furthermore, when a user asks through the smart glasses, "What are Candidate A's main policies?", the server uses generative AI to instantly provide an answer and displays it on the smart glasses.

[1781] Examples of concrete examples and prompts

[1782] For example, when a user wears smart glasses in a brick-and-mortar store and enters the election information area, the following information is displayed:

[1783] Candidate A's main policies:

[1784] education reform

[1785] environmental protection

[1786] Revitalizing the local economy

[1787] An example prompt is:

[1788] Candidate A has been a teacher for many years and has been active in educational reform. He has also proposed many policies related to environmental protection. In terms of economic policy, he places emphasis on revitalizing the local economy.

[1789] Q: What are Candidate A's key policies?

[1790] This allows users to intuitively obtain election information in real time even in physical stores, thereby increasing their interest in elections.

[1791] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1792] Step 1:

[1793] The server collects candidate information, profiles, policies, and election-related news articles from the Internet and specific databases.

[1794] Input: Election-related data from the internet and specific databases.

[1795] Output: A list of collected candidate information and news articles.

[1796] The server automatically collects election-related information through web scraping and API data acquisition, and stores the collected data for further processing.

[1797] Step 2:

[1798] The server summarizes the collected information using generative AI.

[1799] Input: Collected candidate information, profiles, policies, and election-related news articles.

[1800] Output: Candidate information and news articles summarized by generative AI.

[1801] The server uses Hugging Face's transformers library to summarize information about each candidate and news article, then converts the summarized information into a format that is easy to present to users.

[1802] Step 3:

[1803] The server transmits the generated summary information to the display device.

[1804] Input: Information summarized by the generative AI.

[1805] Output: Summary information sent to the user's display device.

[1806] The server structures the summary information and sends it in an appropriate format (e.g., JSON) to the display device (smart glasses or head-mounted display).

[1807] Step 4:

[1808] The terminal sends the question entered by the user to the server.

[1809] Input: The question entered by the user.

[1810] Output: The query data received by the server.

[1811] The user inputs a question using voice input, eye contact, etc., and the question is sent to the server. The terminal receives the user's question, formats it appropriately, and sends it to the server.

[1812] Step 5:

[1813] The server uses a generation AI to generate an answer to the received question.

[1814] Input: User question and associated election data.

[1815] Output: The answer generated by the generative AI.

[1816] The server uses a generative AI model to generate an appropriate answer to the user's question, inputs a prompt into the model, and passes the resulting answer on to the next step.

[1817] Step 6:

[1818] The server transmits the generated answer to the display device.

[1819] Input: The answer generated by the generative AI.

[1820] Output: The answer sent to the user's display device.

[1821] The server structures the generated answers and sends them to the user's display device for display.

[1822] Step 7:

[1823] The server collects election-related data and uses generative AI and data analysis tools to analyze election predictions and voting trends.

[1824] Input: Election-related data (voter turnout, poll data, past election results).

[1825] Output: Election forecasts and voting trend analysis.

[1826] The server collects election-related data and analyzes it using data analytics tools, including generative AI models, to predict election results and conduct trend analysis.

[1827] Step 8:

[1828] The server visualizes the analysis results and transmits them to a display device.

[1829] Input: Election forecasts and voting trend analysis results.

[1830] Output: Visualized graphs and charts.

[1831] The server visualizes the analysis results in graphs and charts and sends them to the user's display device, allowing the user to visually confirm the analysis results.

[1832] Step 9:

[1833] Users can obtain election information by wearing smart glasses or a head-mounted display in a physical store.

[1834] Input: Summary information, answers, and analysis results sent from the server.

[1835] Output: Visual information displayed on smart glasses or a head-mounted display.

[1836] When users enter a specific election information area, candidate information and the latest election news are displayed in their field of view using AR technology. When users enter a question, the answer is immediately displayed in their field of view.

[1837] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1838] The present invention aims to improve voter turnout by efficiently providing information about elections through a system with the following specific functions and processing flow. In particular, by combining an emotion engine, the present invention realizes dynamic information provision according to the user's emotional state.

[1839] 1. Candidate information & election news summary function

[1840] System Configuration

[1841] The server collects candidate information, profiles, policies, and election-related news articles from the Internet and specific databases.

[1842] The server preprocesses the collected information and inputs it into a generative AI to generate a summary.

[1843] The server sends the generated summary information to the terminal so that the user can view it through the app.

[1844] Specific examples

[1845] 1. The server collects candidate information and election-related news for the Tokyo City Council election.

[1846] 2. The server passes the collected information to the generation AI, which generates a summary of key policies and profiles.

[1847] 3. The server sends the generated summary information to the device so that the user can view it in the app.

[1848] 2. Information provision function in Q&A format

[1849] System Configuration

[1850] The user enters a question into the app and presses the submit button.

[1851] The terminal sends the user's question to the server.

[1852] The server inputs the question into the generation AI and starts the answer generation process.

[1853] The server stores the generated answers in a database and transmits them to the terminal.

[1854] The server activates an emotion engine based on the user's input data to recognize the user's emotion.

[1855] The server adjusts the tone and content of the response based on the emotion recognition results and sends it to the device.

[1856] The terminal displays the final adjusted answer to the user.

[1857] Specific examples

[1858] 1. A user asks, "What are Candidate A's key policies?"

[1859] 2. The device sends a question to the server.

[1860] 3. The server uses generative AI to generate answers to the questions.

[1861] 4. The server temporarily stores the generated answers and activates the emotion engine.

[1862] 5. The server uses an emotion engine to recognize emotions from the user's input data and adjust the tone and content accordingly.

[1863] 6. The server sends this finalized answer to the device, where the user can view it in the app.

[1864] 3. Election prediction, trend analysis, and data visualization functions

[1865] System Configuration

[1866] The server collects election-related data (such as voter turnout, poll data, and past election results).

[1867] The server pre-processes the collected data.

[1868] The server feeds the pre-processed data into generative AI and data analysis tools to generate election predictions and voting trends.

[1869] The server inputs the forecast and trend analysis results into a visualization tool to generate graphs and charts.

[1870] The server transmits the visualized data to the terminal and displays it to the user.

[1871] Specific examples

[1872] 1. The server collects voting trend data for urban and rural areas.

[1873] 2. The server preprocesses the data.

[1874] 3. The server uses generative AI and data analysis tools to predict the election results.

[1875] 4. The server visualizes the prediction results in graphs and charts.

[1876] 5. The server sends this visualization data to the device so that the user can view it within the app.

[1877] 4. Emotion engine integration

[1878] System Configuration

[1879] The server includes an emotion engine that recognizes emotions from user input data.

[1880] The server dynamically adjusts the tone and content of the answers and information generated by the generative AI based on the emotion recognition results.

[1881] The server analyzes the emotion recognition results and stores them in a database for future dialogue improvement.

[1882] Specific examples

[1883] 1. The server collects the questions and feedback data entered by the user.

[1884] 2. The server recognizes the user's emotional state using an emotion engine.

[1885] 3. The server adjusts the tone and content of the answers generated by the generation AI based on the emotion recognition results.

[1886] 4. The server stores the adjusted information and responses in a database for analysis.

[1887] This allows users to effectively obtain the information they need and receive personalized responses based on their own emotions, which can increase interest in elections and contribute to increasing voter turnout.

[1888] The processing flow will be explained below.

[1889] 1. Candidate information & election news summary function

[1890] Program processing flow

[1891] Step 1:

[1892] The server periodically collects candidate information, profiles, policies, and election-related news articles from the Internet and specific databases.

[1893] The server retrieves the data using a web scraping tool or API.

[1894] The server stores the acquired data in temporary storage.

[1895] Step 2:

[1896] The server pre-processes and cleans the collected information.

[1897] The server removes unnecessary HTML tags and special characters and formats the text data.

[1898] The server formats the information into a uniform format.

[1899] Step 3:

[1900] The server inputs the preprocessed data into the generation AI to generate summary information.

[1901] The generative AI extracts key points from the input data and generates a summary.

[1902] Step 4:

[1903] The server stores the generated summary information in a database and transmits it to the terminal as needed.

[1904] The server stores the abstract data in the application's database.

[1905] The server transmits the summary data to the terminal in response to a request from the user.

[1906] Step 5:

[1907] The terminal displays the received summary information to the user.

[1908] The terminal displays the summary data on the screen so that the user can check it.

[1909] 2. Information provision function in Q&A format

[1910] Program processing flow

[1911] Step 1:

[1912] The user enters a question into the app and presses the submit button.

[1913] Step 2:

[1914] The terminal sends the user's question to the server.

[1915] The terminal converts the question data into an appropriate format and passes it to the server.

[1916] Step 3:

[1917] The server inputs the question data into the generation AI and begins the answer generation process.

[1918] The generative AI analyzes the question and extracts the information necessary to generate an answer.

[1919] Step 4:

[1920] The server temporarily stores the generated answers and activates the emotion engine.

[1921] The server stores the generated answers in a database and uses them for emotion recognition processing.

[1922] Step 5:

[1923] The server uses an emotion engine to recognize emotions from the user's input data.

[1924] An emotion engine analyzes the user's input text and identifies an emotional state (e.g., happy, anger, sadness, etc.).

[1925] Step 6:

[1926] The server adjusts the tone and content of the answers generated by the generation AI based on the emotion recognition results.

[1927] The server changes the tone and expression to an appropriate one according to the user's emotional state.

[1928] Step 7:

[1929] The server sends the finalized response to the terminal.

[1930] The server makes an API request that sends the tailored response to the device.

[1931] Step 8:

[1932] The terminal displays the received answer to the user.

[1933] The terminal displays the adjusted answer on the screen so that the user can check it.

[1934] 3. Election prediction, trend analysis, and data visualization functions

[1935] Program processing flow

[1936] Step 1:

[1937] The server periodically collects election-related data (such as voter turnout, poll data, and past election results).

[1938] The server obtains the required data from multiple data sources.

[1939] The server stores the collected data in temporary storage.

[1940] Step 2:

[1941] The server preprocesses the collected data.

[1942] The server cleans the data by imputing missing values ​​and detecting and removing outliers.

[1943] The server formats the data appropriately for analysis.

[1944] Step 3:

[1945] The server feeds the pre-processed data into generative AI and data analysis tools to generate election predictions and voting trends.

[1946] Generative AI and data analytics tools analyze data and provide predictions and trend analysis.

[1947] Step 4:

[1948] The server inputs the forecast and trend analysis results into a visualization tool to generate graphs and charts.

[1949] The server creates graphs and charts to display the prediction results in a visually easy-to-understand format.

[1950] Step 5:

[1951] The server sends the visualized data to the terminal and displays it to the user.

[1952] The server stores the visualization data in the application's database.

[1953] The server transmits the visualization data to the terminal in response to a user request.

[1954] The terminal displays graphs and charts on the screen for the user to view.

[1955] 4. Emotion engine integration

[1956] Program processing flow

[1957] Step 1:

[1958] The server collects user-entered questions and feedback data.

[1959] The server stores the user's input in a database and uses it for subsequent processing.

[1960] Step 2:

[1961] The server uses an emotion engine to recognize emotions from the user's input data.

[1962] An emotion engine analyzes the input text and identifies the user's emotional state.

[1963] Step 3:

[1964] Based on the emotion recognition results, the server dynamically adjusts the tone and content of the answers and information generated by the generation AI.

[1965] Generative AI generates responses that use appropriate expressions and tones depending on the recognized emotion.

[1966] Step 4:

[1967] The server stores the adjusted information and responses in a database for later analysis and improvement.

[1968] The server stores the emotion recognition results in a database and uses them for future improvements and analysis of the dialogue system.

[1969] This allows users to effectively obtain the information they need and receive personalized responses based on their own emotions, which can increase interest in elections and contribute to increasing voter turnout.

[1970] Example 2

[1971] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1972] Conventional election information systems have had difficulty processing large amounts of information appropriately and providing it to users in an easy-to-understand format. Furthermore, while it is essential to provide not only appropriate answers to users' questions but also personalized responses that reflect the user's emotions, there has been a lack of means to achieve this. Furthermore, displaying election predictions and voting trend analysis results in a visually understandable manner has also been a challenge.

[1973] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting candidate information, profiles, policies, and election-related news articles; means for summarizing the collected information using a generative model; means for transmitting the generated summary information to a user terminal; means for receiving questions entered by a user; means for generating answers to the received questions using a generative model; means for transmitting the generated answers to the user terminal; means for recognizing an emotional state from user input data; means for dynamically adjusting the tone and content of the answers based on the emotion recognition results; means for collecting election-related data and analyzing election predictions and voting trends using a generative model and a data analysis tool; and means for visualizing and transmitting the analysis results to the user terminal. This enables efficient provision of information about elections and dynamic provision of information according to the user's emotional state. Furthermore, visually displaying the analysis results of election predictions and voting trends makes it easier for users to understand.

[1974] "Candidate information" refers to basic data about individual candidates running in an election, including their name, background, political party affiliation, contact information, etc.

[1975] A "profile" is a record of a candidate's personal information, past career history, achievements, activities, etc.

[1976] "Policies" refer to the specific plans and proposals that candidates advocate during the election period, including promises related to society, the economy, education, healthcare, etc.

[1977] "Election-related news articles" refers to news articles and news content related to elections, and refers to information disseminated by media and news organizations.

[1978] "Means of collection" refers to the functions and methods for automatically obtaining the necessary data from sources such as the Internet and databases.

[1979] A "generative model" refers to an artificial intelligence model that is trained to generate output based on input data for a specific purpose.

[1980] A "summary" is a concise summary of the main points extracted from collected information.

[1981] A "user terminal" is an electronic device that can receive and display information provided by the system, and includes smartphones, tablets, personal computers, etc.

[1982] The "means for receiving a question" refers to a function or method by which the system receives a question or inquiry sent by a user.

[1983] "Answer generation means" refers to the generative model or algorithm used to generate appropriate answers to user questions.

[1984] "Means for recognizing emotional states" refers to techniques and methods for analyzing user input data to identify the emotions behind it.

[1985] "Dynamic adjustment means" refers to functions or methods for automatically changing the content or tone of information based on emotion recognition results.

[1986] "Data Analysis Tools" means software or platforms used to analyze collected data and generate statistical trends and predictions.

[1987] "Election forecasting" refers to analysis that predicts future election outcomes based on collected data.

[1988] "Voting trend analysis" refers to the analysis of past and current voting data to identify patterns and trends in voting behavior.

[1989] "Visualization" refers to the visual representation of analytical results, using graphs and charts to display data in an easy-to-understand manner.

[1990] This invention is a system that efficiently provides information about elections and aims to increase voter turnout. Specifically, it collects information from the internet and specific databases, generates summaries and answers using a generative AI model, and provides dynamic information based on the user's emotional state. It also analyzes election predictions and voting trends, and visualizes the results to provide to users.

[1991] 1. Candidate information & election news summary function

[1992] In this system, the server first collects candidate information, profiles, policies, and election-related news articles from the internet or specific databases. The collected information is then preprocessed and input into a generative AI model (e.g., a GPT-based model) to generate a summary. The generated summary information is then sent from the server to the user's device, where the user can view it through an app. This series of processes allows users to easily grasp key information related to the election.

[1993] Specific examples

[1994] 1. The server collects candidate information and election-related news for city elections.

[1995] 2. The server passes the collected information to the generation AI, which generates a summary of key policies and profiles.

[1996] 3. The server sends the generated summary information to the device so that the user can view it in the app.

[1997] Prompt Sentence Examples

[1998] "Please create a profile and a summary of key policies for Candidate A in the Tokyo Metropolitan Assembly election."

[1999] 2. Information provision function in Q&A format

[2000] When a user enters and submits a question on the app, the device sends the question to the server. The server uses a generative AI model to generate an answer to the question and an emotion engine to recognize emotions from the user's input data. The server then adjusts the tone and content of the answer based on the emotion recognition results and sends the final answer to the user's device, allowing the user to receive appropriate information.

[2001] Specific examples

[2002] 1. A user asks, "What are Candidate A's key policies?"

[2003] 2. The device sends a question to the server.

[2004] 3. The server uses generative AI to generate answers to the questions.

[2005] 4. The server temporarily stores the generated answers and activates the emotion engine.

[2006] 5. The server uses an emotion engine to recognize emotions from the user's input data and adjust the tone and content accordingly.

[2007] 6. The server sends this finalized answer to the device, where the user can view it in the app.

[2008] Prompt Sentence Examples

[2009] "Please tell me about Candidate A's major policies."

[2010] 3. Election prediction, trend analysis, and data visualization functions

[2011] The system's server collects and preprocesses election-related data (such as voter turnout, opinion poll data, and past election results). The preprocessed data is then input into a generative AI model and data analysis tools to analyze election predictions and voting trends. The results of the prediction and trend analysis are converted into graphs and charts using visualization tools and sent to user devices. This allows users to visually understand election trends.

[2012] Specific examples

[2013] 1. The server collects voting trend data for urban and rural areas.

[2014] 2. The server preprocesses the data.

[2015] 3. The server uses generative AI and data analysis tools to predict the election results.

[2016] 4. The server visualizes the prediction results in graphs and charts.

[2017] 5. The server sends this visualization data to the device so that the user can view it within the app.

[2018] Prompt Sentence Examples

[2019] "Predict the outcome of the next election based on urban and rural voting trends."

[2020] 4. Emotion engine integration

[2021] The server is equipped with an emotion engine that recognizes emotions from user input data. Based on the emotion recognition results, the generative AI model dynamically adjusts the tone and content of the responses and information it generates. This adjusted data is stored in a database and used to improve future interactions.

[2022] Specific examples

[2023] 1. The server collects the questions and feedback data entered by the user.

[2024] 2. The server recognizes the user's emotional state using an emotion engine.

[2025] 3. The server adjusts the tone and content of the answers generated by the generation AI based on the emotion recognition results.

[2026] 4. The server stores the adjusted information and responses in a database for analysis.

[2027] This allows users to effectively obtain the information they need and receive personalized responses based on their own emotions, which can increase interest in elections and contribute to increasing voter turnout.

[2028] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2029] Candidate information & election news summary feature

[2030] Step 1: Gather information

[2031] The server collects candidate information, profiles, policies, and election-related news articles from the Internet and specific databases.

[2032] Input: Raw data from the internet or databases.

[2033] Output: Raw information about each candidate.

[2034] Specific operation: The server uses a web crawler to retrieve text data from major news sites and official databases.

[2035] Step 2: Information preprocessing

[2036] The server preprocesses the collected information and formats it for input into the generative AI.

[2037] Input: Raw data (noisy).

[2038] Output: Preprocessed structured data.

[2039] What it does: The server uses text analysis and natural language processing (NLP) techniques to filter out noise, extract the necessary information, and convert it into structured data.

[2040] Step 3: Summary generation

[2041] The server inputs the preprocessed data into a generative AI model to generate a summary.

[2042] Input: Preprocessed structured data.

[2043] Output: Candidate information and policy summary.

[2044] How it works: The server passes the data prompt to a generative AI model (e.g., a GPT-based model) and generates a summary containing key information for each candidate.

[2045] Step 4: Submit summary information

[2046] The server transmits the generated summary information to the terminal.

[2047] Input: Abstract text.

[2048] Output: Summary sent to the user's terminal.

[2049] Specific operation: The server uses the API to send data to display the generated summary on the user's device in real time.

[2050] Q&A format information provision function

[2051] Step 1: Enter your question

[2052] The user enters a question into the app and presses the submit button.

[2053] Input: The user's question text.

[2054] Output: The question sent to the terminal.

[2055] Specific action: The user types a question into the input form and presses the "Submit" button.

[2056] Step 2: Submit your question

[2057] The terminal sends the user's question to the server.

[2058] Input: The question received from the user.

[2059] Output: The question data passed to the server.

[2060] Specific operation: The device sends the user's input to the server via the API.

[2061] Step 3: Question processing and answer generation

[2062] The server inputs the question into the generative AI model and starts the answer generation process.

[2063] Input: User question data.

[2064] Output: The generated answer.

[2065] What happens: The server passes the prompt to the generative AI model, which generates an appropriate answer.

[2066] Step 4: Save your answers

[2067] The server stores the generated answers in a database.

[2068] Input: The generated answer.

[2069] Output: Answers stored in a database.

[2070] Specific operation: The server temporarily stores the generated answer in a database.

[2071] Step 5: Emotion Recognition

[2072] The server activates an emotion engine based on the user's input data to recognize emotions.

[2073] Input: User question data.

[2074] Output: Emotion recognition results.

[2075] What it does: The emotion engine extracts and tags emotion data from the user's text.

[2076] Step 6: Adjust your answers

[2077] The server adjusts the tone and content of the response based on the emotion recognition results.

[2078] Input: Emotion recognition results and generated answers.

[2079] Output: The final adjusted answer.

[2080] What happens: The server uses the tone adjustment module to personalize the answer and generate the adjusted answer.

[2081] Step 7: Submit and view your responses

[2082] The server sends this finalized answer to the terminal and displays it to the user.

[2083] Input: Final adjusted answer.

[2084] Output: The answer displayed on the terminal.

[2085] Specific operation: The terminal displays the received response on the user interface.

[2086] Election forecasts, trend analysis, and data visualization features

[2087] Step 1: Data collection

[2088] The server collects election-related data (such as voter turnout, poll data, and past election results).

[2089] Input: Various election-related data.

[2090] Output: The raw data collected.

[2091] What happens: The server retrieves the necessary data from data sources (public government data, pollster reports, etc.).

[2092] Step 2: Data Preprocessing

[2093] The server pre-processes the collected data.

[2094] Input: Raw data.

[2095] Output: Preprocessed data.

[2096] Specific operation: The server performs data cleaning and format conversion.

[2097] Step 3: Election predictions

[2098] The server feeds the pre-processed data into generative AI models and data analysis tools to generate election predictions and voting trends.

[2099] Input: Preprocessed data.

[2100] Output: Forecast and trend analysis results.

[2101] What it does: Uses machine learning models to predict poll results and trends.

[2102] Step 4: Data visualization

[2103] The server inputs the forecast and trend analysis results into a visualization tool to generate graphs and charts.

[2104] Input: Forecast and trend analysis results.

[2105] Output: Visualized data in the form of graphs and charts.

[2106] Specific Actions: Use visualization tools (e.g., Tableau, Power BI) to visually display analysis results.

[2107] Step 5: Send visualization data

[2108] The server transmits the visualized data to the terminal and displays it to the user.

[2109] Input: Visualization data in the form of graphs and charts.

[2110] Output: Graphs and charts displayed on the terminal.

[2111] Specific operation: Visualization data is sent from the server to the terminal and displayed on the user interface.

[2112] Emotion engine integration

[2113] Step 1: Collecting Emotional Data

[2114] The server collects the user's input data.

[2115] Input: User questions and feedback data.

[2116] Output: The raw data collected.

[2117] Specific operation: The server passes the user's input text (question, feedback, etc.) to the text analysis module.

[2118] Step 2: Emotion Recognition

[2119] The server uses an emotion engine to recognize the user's emotional state.

[2120] Input: The raw data collected.

[2121] Output: Emotion recognition results.

[2122] What it does: An emotion recognition engine classifies the sentiment of the text (e.g., positive, negative, neutral).

[2123] Step 3: Adjust and save

[2124] The server adjusts the tone and content of the response based on the emotion recognition results and stores them in a database.

[2125] Input: Emotion recognition results and generated answers.

[2126] Output: Tailored information or answers.

[2127] Specific actions: The adjusted information is stored in a database and used to improve services in the future.

[2128] This allows users to effectively obtain the information they need and receive personalized responses that reflect their own emotions.

[2129] (Application example 2)

[2130] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[2131] Existing election information systems are limited to providing static information, making it difficult to provide dynamic information tailored to individual users' emotional states and interests. Furthermore, there is a lack of mechanisms for improving the user experience in election-related donations and campaign fund management. The present invention aims to solve these problems and increase voter turnout by motivating users to vote.

[2132] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2133] In this invention, the server includes: means for collecting candidate information, profiles, policies, and election-related news articles; means for summarizing the collected information using a generation AI; means for transmitting the generated summary information to a user terminal; means for receiving questions entered by a user; means for generating answers to the received questions using a generation AI; means for transmitting the generated answers to the user terminal; means for collecting election-related data and analyzing election predictions and voting trends using a generation AI and a data analysis tool; means for visualizing and transmitting the analysis results to the user terminal; means for recognizing the emotional state of the user from the input data; means for dynamically adjusting the tone and content of the answers and information generated by the generation AI based on the emotion recognition results; an electronic payment function for election donations; and means for analyzing the emotion recognition results and storing them in a database for future dialogue improvement. This enables dynamic provision of information according to the user's emotional state and an improved user experience in election donations and campaign management.

[2134] Below are definitions of important words:

[2135] "Candidate information" refers to detailed information such as the name, background, political party affiliation, and policies of a person running for election.

[2136] A "profile" is detailed information including basic information about the candidate, past work history, educational background, etc.

[2137] "Policies" refer to the content of the promises and specific measures that candidates put forward during the election.

[2138] "Election news articles" are articles that summarize the latest events and reports related to elections.

[2139] "Generative AI" is a type of artificial intelligence that performs natural language processing and data generation, summarizing information and generating answers.

[2140] A "user terminal" is a device such as a smartphone, tablet, or PC that a user uses to connect to the Internet and obtain information.

[2141] An "emotional state" is an emotional state (e.g., joy, sadness, anger) recognized from the data and behavior entered by the user.

[2142] "Dynamic adjustment means" refers to a method of changing the tone and content of the answers and information generated by the generative AI in real time based on the emotion recognition results.

[2143] "Electronic payment function" is a technology for conducting monetary transactions via the Internet.

[2144] This invention is a system that aims to increase voter turnout by efficiently providing information about elections. By combining this system with an emotion engine, it is possible to dynamically provide information according to the user's emotional state. This system has the following specific configuration and processing procedures.

[2145] Candidate information & election news summary feature

[2146] System Configuration

[2147] The server collects candidate information, profiles, policies, and election-related news articles from the Internet and specific databases.

[2148] The server preprocesses the collected information and inputs it into a generative AI model to generate a summary.

[2149] The server transmits the generated summary information to the user terminal so that the user can check it through the app.

[2150] Specific examples

[2151] 1. The server collects candidate information and election-related news for city elections.

[2152] 2. The server passes the collected information to a generative AI model to generate summaries of key policies and profiles.

[2153] 3. The server sends the generated summary information to the user's device so that the user can view it in the app.

[2154] Q&A format information provision function

[2155] System Configuration

[2156] The user enters a question into the app and presses the submit button.

[2157] The terminal sends the user's question to the server.

[2158] The server inputs the question into the generative AI model and starts the answer generation process.

[2159] The server stores the generated answers in a database and transmits them to the terminal.

[2160] The server activates an emotion engine based on the user's input data to recognize the user's emotion.

[2161] The server adjusts the tone and content of the response based on the emotion recognition results and sends it to the device.

[2162] The terminal displays the final adjusted answer to the user.

[2163] Specific examples

[2164] 1. A user asks, "What are the candidates' key policies?"

[2165] 2. The device sends a question to the server.

[2166] 3. The server generates an answer to the question using a generative AI model.

[2167] 4. The server temporarily stores the generated answers and activates the emotion engine.

[2168] 5. The server uses an emotion engine to recognize emotions from the user's input data and adjust the tone and content accordingly.

[2169] 6. The server sends this finalized answer to the device, where the user can view it in the app.

[2170] Election forecasts, trend analysis, and data visualization features

[2171] System Configuration

[2172] The server collects election-related data (such as voter turnout, poll data, and past election results).

[2173] The server pre-processes the collected data.

[2174] The server feeds the pre-processed data into generative AI models and data analysis tools to generate election predictions and voting trends.

[2175] The server inputs the forecast and trend analysis results into a visualization tool to generate graphs and charts.

[2176] The server transmits the visualized data to the user terminal and displays it to the user.

[2177] Specific examples

[2178] 1. The server collects voting trend data for urban and rural areas.

[2179] 2. The server preprocesses the data.

[2180] 3. The server uses generative AI models and data analysis tools to predict election outcomes.

[2181] 4. The server visualizes the prediction results in graphs and charts.

[2182] 5. The server sends this visualization data to the user's device so that the user can view it within the app.

[2183] Emotion engine integration

[2184] System Configuration

[2185] The server includes an emotion engine that recognizes emotions from user input data.

[2186] The server dynamically adjusts the tone and content of the answers and information generated by the generative AI model based on the emotion recognition results.

[2187] The server analyzes the emotion recognition results and stores them in a database for future dialogue improvement.

[2188] Specific examples

[2189] 1. The server collects the questions and feedback data entered by the user.

[2190] 2. The server recognizes the user's emotional state using an emotion engine.

[2191] 3. The server adjusts the tone and content of the answers generated by the generative AI model based on the emotion recognition results.

[2192] 4. The server stores the adjusted information and responses in a database for analysis.

[2193] 5. This allows users to effectively obtain the information they need and receive personalized responses based on their emotions.

[2194] Election Contributions and Campaign Management

[2195] As part of this invention, an electronic payment function for campaign donations is built in. Users can make donations through the app, and the results of their donations are updated in real time.

[2196] Prompt Sentence Examples

[2197] "What are the main policies of this candidate?"

[2198] "I want to donate to this candidate, how do I do that?"

[2199] "Predict the results of the next election."

[2200] The server dynamically generates answers to these questions, tailoring responses to the user's emotional state, allowing users to easily and effectively obtain information about the election and make better decisions.

[2201] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2202] Step 1:

[2203] The server collects candidate information, profiles, policies, and election-related news articles from the internet and specific databases. It receives election-related information from external databases and APIs as input and stores the collected data in an internal database. Specific operations include sending HTTP requests and making API calls to retrieve data.

[2204] Step 2:

[2205] The server preprocesses the collected information and converts it into data to be input into the generative AI model. It receives raw data as input, converts character encoding, removes unnecessary information, and converts it into a structured data format. Specific operations include data cleansing and data formatting.

[2206] Step 3:

[2207] The server passes the preprocessed data to a generative AI model to generate summaries of key policies and profiles. It receives structured election-related data as input and outputs text summarized by the model. Specifically, it invokes a natural language processing model and performs the summary generation process.

[2208] Step 4:

[2209] The server sends the generated summary information to the user's device so that the user can view it through the app. The server receives the summary information as input, sends it to the user's device, and displays it. Specifically, data is transferred using a data transmission protocol.

[2210] Step 5:

[2211] The user enters a question into the app and presses the send button. The device receives the text entered by the user as input and sends it to the server. Specifically, the text input and button press events are processed via the user interface.

[2212] Step 6:

[2213] The server receives the user's question, inputs it into the generative AI model, and performs the answer generation process. It receives the user's question text as input and generates the answer text using the generative AI model. Specific operations include analyzing the question text and generating the answer.

[2214] Step 7:

[2215] The server stores the generated answer in a database and sends it to the terminal. The server receives the generated answer text as input, stores it in a database, and sends it to the user's terminal. Specific operations include database operations and the use of data transfer protocols.

[2216] Step 8:

[2217] The server analyzes the user's input data and activates the emotion engine to recognize the user's emotion. It receives the user's question text as input and sends it to the emotion engine cluster to output the emotional state. Specific operations include running the text emotion analysis algorithm.

[2218] Step 9:

[2219] The server adjusts the tone and content of the response based on the emotion recognition results. It receives the recognized emotional state and the generated response text as input, modifies the content and tone, and generates the final response. Specific operations include adjusting the text tone and reframing the content.

[2220] Step 10:

[2221] The server sends the final adjusted answer to the device so that the user can view it within the app. It receives the final adjusted answer as input, sends it to the user's device, and displays it. Specific operations include using a data transmission protocol and displaying it in the user interface.

[2222] Step 11:

[2223] The server collects election-related data and uses generative AI models and data analysis tools to analyze election predictions and voting trends. It receives election data from a database as input, analyzes and predicts, and stores the results internally. Specific operations include running data analysis algorithms and applying predictive models.

[2224] Step 12:

[2225] The server converts the analysis results obtained into graphs and charts using a visualization tool and sends them to the user's device. The server receives the analysis result data as input, converts it into a visual format, and sends it to the user's device. Specific operations include using the data visualization tool and creating graphs.

[2226] Step 13:

[2227] When a user makes a donation through the app, the device uses the electronic payment function to send donation information to the server, receives the donation amount as input, and completes the electronic payment procedure. Specific operations include executing the payment process and recording the transaction.

[2228] Example prompt sentence:

[2229] "What are the main policies of this candidate?"

[2230] "I want to donate to this candidate, how do I do that?"

[2231] "Predict the results of the next election."

[2232] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[2233] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2234] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[2235] [Fourth embodiment]

[2236] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[2237] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[2238] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[2239] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[2240] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[2241] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[2242] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[2243] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[2244] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[2245] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[2246] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[2247] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[2248] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2249] The present invention aims to improve voter turnout by efficiently providing information about elections through a system equipped with the following functions.

[2250] 1. Candidate information & election news summary function

[2251] System Configuration

[2252] The server collects candidate information, profiles, policies, and election-related news articles from the Internet and specific databases.

[2253] The server preprocesses the collected information and inputs it into a generative AI to generate a summary.

[2254] The server sends the generated summary information to the terminal so that the user can check it through the app.

[2255] Specific examples

[2256] 1. The server collects candidate information and election-related news for the Tokyo City Council election.

[2257] 2. The server passes the collected information to the generation AI, which generates a summary of key policies and profiles.

[2258] 3. The server sends the generated summary information to the device so that the user can view it in the app.

[2259] 2. Information provision function in Q&A format

[2260] System Configuration

[2261] The user enters a question into the app and presses the submit button.

[2262] The terminal sends the user's question to the server.

[2263] The server inputs the question into the generation AI, which generates an appropriate answer.

[2264] The server sends the generated answer to the terminal and displays it to the user.

[2265] Specific examples

[2266] 1. A user asks, "What are Candidate A's key policies?"

[2267] 2. The device sends a question to the server.

[2268] 3. The server uses generative AI to generate answers to the questions.

[2269] 4. The server sends the generated answer to the device, where the user can view it within the app.

[2270] 3. Election prediction, trend analysis, and data visualization functions

[2271] System Configuration

[2272] The server collects election-related data (such as voter turnout, poll data, and past election results).

[2273] The server analyzes the collected data using AI generation and data analysis tools to generate election predictions and voting trends.

[2274] The server visualizes the analysis results as graphs and charts and sends them to the user's device.

[2275] Allow users to view visualized data through the app.

[2276] Specific examples

[2277] 1. The server collects voting trend data for urban and rural areas.

[2278] 2. The server uses generative AI and data analysis tools to predict the election results.

[2279] 3. The server visualizes the prediction results in graphs and charts.

[2280] 4. The server sends this visualization data to the device so that the user can view it within the app.

[2281] The system configuration described above effectively provides candidate information, answers questions, and analyzes election predictions and trends. This allows voters to easily obtain the information they need, raising their interest in elections and contributing to increased voter turnout.

[2282] The processing flow will be explained below.

[2283] 1. Candidate information & election news summary function

[2284] Program processing flow

[2285] Step 1:

[2286] The server periodically collects candidate information, profiles, policies, and election-related news articles from the Internet and specific databases.

[2287] The server retrieves the data using a web scraping tool or API.

[2288] The server stores the acquired data in temporary storage.

[2289] Step 2:

[2290] The server pre-processes and cleans the collected information.

[2291] The server removes unnecessary HTML tags and special characters and formats the text data.

[2292] The server formats the information into a uniform format.

[2293] Step 3:

[2294] The server inputs the preprocessed data into the generation AI to generate summary information.

[2295] The generative AI extracts key points from the input data and generates a summary.

[2296] Step 4:

[2297] The server stores the generated summary information in a database and transmits it to the terminal as needed.

[2298] The server stores the abstract data in the application's database.

[2299] The server transmits the summary data to the terminal in response to a request from the user.

[2300] Step 5:

[2301] The terminal displays the received summary information to the user.

[2302] The terminal displays the summary data on the screen so that the user can check it.

[2303] 2. Information provision function in Q&A format

[2304] Program processing flow

[2305] Step 1:

[2306] The user enters a question into the app and presses the submit button.

[2307] Step 2:

[2308] The terminal sends the user's question to the server.

[2309] The terminal converts the question data into an appropriate format and passes it to the server.

[2310] Step 3:

[2311] The server inputs the question data into the generation AI and begins the answer generation process.

[2312] The generative AI analyzes the question and extracts the information necessary to generate an answer.

[2313] Step 4:

[2314] The server stores the generated answer in a database and sends it to the terminal.

[2315] The server stores the generated answers in an appropriate format.

[2316] The server transmits the saved response data to the terminal.

[2317] Step 5:

[2318] The terminal displays the received answer to the user.

[2319] The terminal displays the answer data on the screen so that the user can check it.

[2320] 3. Election prediction, trend analysis, and data visualization functions

[2321] Program processing flow

[2322] Step 1:

[2323] The server periodically collects election-related data (such as voter turnout, poll data, and past election results).

[2324] The server obtains the required data from multiple data sources.

[2325] The server stores the collected data in temporary storage.

[2326] Step 2:

[2327] The server preprocesses the collected data.

[2328] The server cleans the data by imputing missing values ​​and detecting and removing outliers.

[2329] The server formats the data appropriately for analysis.

[2330] Step 3:

[2331] The server feeds the pre-processed data into generative AI and data analysis tools to generate election predictions and voting trends.

[2332] Generative AI and data analytics tools analyze data and provide predictions and trend analysis.

[2333] Step 4:

[2334] The server inputs the forecast and trend analysis results into a visualization tool to generate graphs and charts.

[2335] The server creates graphs and charts to display the prediction results in a visually easy-to-understand format.

[2336] Step 5:

[2337] The server sends the visualized data to the terminal and displays it to the user.

[2338] The server stores the visualization data in the application's database.

[2339] The server transmits the visualization data to the terminal in response to a user request.

[2340] The terminal displays graphs and charts on the screen for the user to view.

[2341] Example 1

[2342] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2343] In modern elections, voters often lack sufficient information, resulting in low voter turnout. It is difficult for voters to easily access and understand candidate information and election-related news. Even when voters ask specific questions, they often cannot receive immediate answers. Furthermore, predicting and analyzing election results and voting trends is difficult for the average voter, and the scattered nature of the information makes it difficult to make comprehensive judgments. A system that can solve these problems is needed.

[2344] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[2345] In this invention, the server includes means for collecting candidate information, profiles, policies, and election-related news articles, means for preprocessing the collected information and generating summaries using a generation AI, means for transmitting the generated summaries to a user terminal, means for receiving questions entered by users, means for preprocessing the received questions and generating answers using a generation AI, means for transmitting the generated answers to the user terminal, means for collecting election-related data and analyzing election predictions and voting trends using a generation AI and a data analysis tool, means for visualizing the analysis results and transmitting them to the user terminal, and means for displaying the received information on the user terminal. This allows voters to obtain election information comprehensively and quickly, contributing to an increase in voter turnout.

[2346] "Candidate information" refers to information about the name, background, past activities, policies, etc. of a person running for election.

[2347] A "profile" is a collection of detailed information about a particular individual, including that individual's career history, educational background, work history, hobbies, etc.

[2348] "Policies" refer to the measures and promises that candidates put forward during the election, as well as the plans and guidelines that they intend to implement after the election.

[2349] "Election-related news articles" are articles containing reports or news about elections, providing information on election progress, candidate activities, election results, etc.

[2350] "Preprocessing" refers to the process of converting collected data into a format suitable for analysis or generative AI, and includes data cleaning, tokenization, normalization, etc.

[2351] "Generative AI" refers to an artificial intelligence model that learns from large amounts of data to generate text and information, and has technology specialized in natural language processing.

[2352] A "user terminal" is a device used by a user, such as a computer or smartphone, that displays information and accepts operations through applications.

[2353] "Tokenization" is the process of dividing text data into units such as words and sentences, and is performed as a preliminary step in natural language processing.

[2354] "Data analysis tools" are software and libraries used to process and analyze collected data based on statistical analysis and machine learning models.

[2355] "Visualization" refers to displaying data in a visually easy-to-understand manner, and refers to representing it as a graph or chart.

[2356] A "RESTful API" is a standardized interface for exchanging data between web services, and is based on HTTP.

[2357] "JSON" stands for JavaScript Object Notation and is a lightweight data format for structuring and representing data.

[2358] MODE FOR CARRYING OUT THE INVENTION

[2359] The present invention provides a system for efficiently providing information about elections and aiming to increase voter turnout. Detailed embodiments for realizing the following various functions are described below.

[2360] Candidate information & election news summary feature

[2361] System Configuration

[2362] The server collects candidate information, profiles, policies, and election-related news articles from the internet and specific databases using APIs and web scraping tools.

[2363] The server preprocesses the collected information, tokenizing and normalizing it using natural language processing tools such as NLTK and spaCy.

[2364] The server inputs the preprocessed information into a generative AI (e.g., GPT-4) to generate a summary.

[2365] The server sends the generated summary information to the terminal in JSON format via a RESTful API.

[2366] Users can check the summary information sent through the app. Specifically, the app parses the received JSON data and displays it on the screen.

[2367] Specific examples

[2368] A server collects candidate information and latest news about a particular city council election.

[2369] The server preprocesses the collected data and sends the generation AI a prompt: "Please summarize Candidate A's profile and key policies."

[2370] The server sends the generated summary to the user's device and displays it in the app.

[2371] Q&A format information provision function

[2372] System Configuration

[2373] The user enters a question in the app and presses the submit button, which sends the question to the server as an HTTP POST request.

[2374] The server pre-processes the received questions by tokenizing and parsing them.

[2375] The server inputs the preprocessed questions into a generative AI (e.g., GPT-4) to generate appropriate answers.

[2376] The server sends the generated response in JSON format to the terminal.

[2377] The user can check the submitted answers in the app, which parses the received JSON data and displays it on the screen.

[2378] Specific examples

[2379] A user asks, "What are Candidate A's key policies?"

[2380] The terminal sends the question to the server, and the server sends the prompt to the generation AI: "Please briefly explain Candidate A's policies."

[2381] The server sends the generated answer to the user's device and displays it in the app.

[2382] Election forecasts, trend analysis, and data visualization features

[2383] System Configuration

[2384] The server collects election-related data (such as voter turnout, poll data, and past election results) using APIs and database queries.

[2385] The server preprocesses and analyzes the collected data using data analysis tools (e.g., Pandas and NumPy).

[2386] The server then feeds the preprocessed data into generative AI (e.g., GPT-4) and machine learning models to predict election results and voting trends.

[2387] The server converts the prediction results into graphs or charts using a data visualization tool (e.g., Matplotlib or Plotly) and sends them to the terminal in JSON format.

[2388] Users can view the visualization data sent through the app, which parses the received data and displays it as an interactive graph.

[2389] Specific examples

[2390] The server collects voting trend data from urban and rural areas and uses generative AI and data analysis tools to send a prompt message: "Please predict the results of the next election."

[2391] The server visualizes the prediction results and sends them to the user's device, where they are displayed as interactive graphs in the app.

[2392] The above configuration effectively provides information on candidates, answers questions, and analyzes election predictions and trends, allowing voters to quickly and easily obtain the information they need. This is expected to increase interest in elections and contribute to an increase in voter turnout.

[2393] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2394] Candidate information & election news summary feature

[2395] Step 1: Gather information

[2396] The server collects candidate information, profiles, policies, and election-related news articles from the Internet and specific databases.

[2397] Input: Raw data obtained via API or web scraping.

[2398] Output: The raw data collected.

[2399] Specific operation: The server collects data using RESTful APIs or web scraping tools (e.g., BeautifulSoup) and stores it in an internal database.

[2400] Step 2: Preprocessing the information

[2401] The server performs pre-processing such as tokenization and normalization of the collected information.

[2402] Input: Raw data collected.

[2403] Output: Preprocessed data.

[2404] What happens: The server uses natural language processing tools (e.g., NLTK or spaCy) to cleanse the text data and remove unnecessary characters and formatting.

[2405] Step 3: Generate a summary

[2406] The server inputs the preprocessed data into a generative AI model (e.g., GPT-4) to generate a summary.

[2407] Input: Preprocessed data and a prompt to the generative AI (e.g., "Please summarize Candidate A's profile and key policies.").

[2408] Output: The generated summary.

[2409] Specific operation: The server sends the preprocessed data and prompt sentences to the generative AI model and receives the resulting summary.

[2410] Step 4: Submit summary information

[2411] The server transmits the generated summary information to the terminal.

[2412] Input: The generated summary.

[2413] Output: Summary data in JSON format sent to the user's device.

[2414] Specific operation: The server uses a RESTful API to send summary data to the user terminal.

[2415] Step 5: View summary information

[2416] The device allows the user to view summary information sent through the app.

[2417] Input: JSON data received by the user device.

[2418] Output: Summary information displayed on the screen.

[2419] Specific operation: The terminal parses the received JSON data and displays the information using a GUI.

[2420] Q&A format information provision function

[2421] Step 1: Submit your question

[2422] The user enters a question into the app and presses the submit button.

[2423] Input: The text of the question entered by the user.

[2424] Output: Send request.

[2425] What happens: The app captures user input and sends an HTTP POST request to the server.

[2426] Step 2: Ask a question

[2427] The terminal sends the user's question to the server.

[2428] Input: The outgoing request from the app.

[2429] Output: The query data received by the server.

[2430] Specific operation: The terminal sends an HTTP POST request, which is received by the server.

[2431] Step 3: Preprocessing the Question

[2432] The server preprocesses the received query.

[2433] Input: The raw query data as it arrives at the server.

[2434] Output: Preprocessed question data.

[2435] Specific operation: The server tokenizes and parses the question data into a format suitable for the generative AI.

[2436] Step 4: Generate an answer

[2437] The server inputs the preprocessed question into a generative AI model (e.g., GPT-4) to generate an answer.

[2438] Input: Preprocessed question data and prompt statement (e.g., "What are Candidate A's major policies?").

[2439] Output: The generated answer.

[2440] Specific operation: The server sends the preprocessed question data and prompt sentence to the generation AI and receives the resulting answer.

[2441] Step 5: Submit your response

[2442] The server sends the generated response to the terminal.

[2443] Input: The generated answer.

[2444] Output: JSON formatted answer data sent to the user's device.

[2445] Specific operation: The server sends the answer data to the user terminal using a RESTful API.

[2446] Step 6: View your answers

[2447] The device allows the user to check the submitted answers within the app.

[2448] Input: JSON data received by the user device.

[2449] Output: The answers displayed on the screen.

[2450] Specific operation: The terminal parses the received JSON data and displays the information using a GUI.

[2451] Election forecasts, trend analysis, and data visualization features

[2452] Step 1: Collect data

[2453] The server collects election-related data (such as voter turnout, poll data, and past election results).

[2454] Input: Raw data retrieved via API or database query.

[2455] Output: The raw data collected.

[2456] Specific operation: The server collects the necessary data through APIs and database queries and stores it in an internal database.

[2457] Step 2: Preprocessing the data

[2458] The server preprocesses the collected data using data analysis tools (e.g., Pandas and NumPy).

[2459] Input: Raw data collected.

[2460] Output: Preprocessed data.

[2461] Specific operation: The server uses Pandas and NumPy to clean the data and process it statistically.

[2462] Step 3: Generate prediction results

[2463] The server inputs the preprocessed data into generative AI (e.g., GPT-4) and machine learning models to generate predictions.

[2464] Input: Preprocessed data and a prompt (e.g., "Based on urban and rural voting trend data, please predict the outcome of the upcoming election.").

[2465] Output: The generated prediction results.

[2466] Specific operation: The server sends the preprocessed data and prompt sentences to the generation AI and receives the prediction results.

[2467] Step 4: Data visualization

[2468] The server visualizes the prediction results as graphs and charts.

[2469] Input: The generated prediction results.

[2470] Output: Visualized graphs and charts.

[2471] Specific operation: The server visualizes the data using Matplotlib or Plotly and converts it into an image file or HTML.

[2472] Step 5: Send visualization data

[2473] The server transmits the generated visualization data to the terminal.

[2474] Input: A visualized graph or chart.

[2475] Output: Visualized data sent to the user's device.

[2476] Specific operation: The server sends visualization data to the user's terminal using a RESTful API.

[2477] Step 6: Displaying the visualized data

[2478] The device allows the user to view the transmitted visualization data within the app.

[2479] Input: Visualization data received by the user terminal.

[2480] Output: Visualized graphs and charts displayed on the screen.

[2481] Specific operation: The device parses the data it receives and displays it as an interactive graph.

[2482] The above are the processing steps for carrying out the present invention, and this system allows users to obtain comprehensive and quick information about elections.

[2483] (Application example 1)

[2484] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2485] The challenge is to make it easier for users to efficiently obtain and understand election information, as well as to raise interest in elections and encourage actual voting behavior. In particular, there is a need for a method to provide election information intuitively and in real time in physical stores.

[2486] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[2487] In this invention, the server includes means for collecting candidate information, profiles, policies, and election-related news articles, means for summarizing the collected information using a generation AI, means for transmitting the generated summary information to a display device, means for receiving questions entered by users, means for generating answers to the received questions using a generation AI, means for transmitting the generated answers to a display device, means for collecting election-related data and analyzing election predictions and voting trends using a generation AI and a data analysis tool, means for visualizing the analysis results and transmitting them to a display device, and means for providing the collected election information and prediction data to users in physical stores using AR technology. This allows users to intuitively obtain election information in real time even in physical stores, thereby increasing their interest in elections.

[2488] "Candidate information" refers to information about the profile, claims, background, and policies of a person running for election.

[2489] A "profile" is basic information about a person, such as background information such as date of birth, educational background, and work history.

[2490] "Policy" refers to the plans and guidelines proposed by candidates to solve public problems.

[2491] "Election-related news articles" is a general term for news and articles reported about elections.

[2492] "Collection" is the act of systematically gathering data or information.

[2493] "Generative AI" is a system that uses artificial intelligence technology to automatically generate and summarize data.

[2494] A "summary" is a concise summary of the original information.

[2495] A "display device" is a device for visually displaying information, such as smart glasses or a display.

[2496] A "question" is a question that a user enters to verify information.

[2497] An "answer" is information or a solution provided to a question.

[2498] "Election-related data" refers to data related to elections, such as voter turnout, opinion poll results, and past election results.

[2499] A "data analysis tool" is software or technology for analyzing data.

[2500] An "election forecast" is an analytical result that predicts the outcome of an election in advance.

[2501] "Voting trends" are changes in data regarding voting behavior and tendencies.

[2502] "Visualization" is a method of visually representing data.

[2503] "AR technology" stands for augmented reality technology, which is a technology that overlays digital information onto the real-world environment.

[2504] "Users in a physical store" refers to consumers or customers who visit a particular physical store.

[2505] The present invention is a system that efficiently collects and summarizes candidate information and election-related news and provides it to users. This system uses augmented reality (AR) technology to provide election information to users, particularly in brick-and-mortar stores. Specific embodiments of the system are described below.

[2506] System Configuration

[2507] The system includes a server, a display device (e.g., smart glasses or a head-mounted display), and a network within a physical store. The server operates using the following hardware and software:

[2508] Hardware: High-performance server connected to the Internet

[2509] Software: Python, Hugging Face transformers library, data analysis tools, OpenCV library

[2510] Collecting and summarizing candidate information and news

[2511] The server automatically collects election-related data from the internet and specific databases, including candidate information, profiles, key policies, and election-related news articles, and generates summaries using a generative AI model that uses Hugging Face's transformers library.

[2512] Question and Answer Function

[2513] The server receives questions from users and generates appropriate answers. At this time, the questions are input into a generative AI model, and the AI ​​generates appropriate answers and sends them to the user's display device. An example of a question a user might ask is, "What are Candidate A's main policies?"

[2514] Election predictions and trend analysis

[2515] The server collects election-related data (such as voter turnout, opinion poll data, and past election results) and uses data analysis tools to predict election results and analyze voting trends. The generated analysis results are visualized as graphs and charts and sent to a display device.

[2516] Providing information using AR technology

[2517] Users in physical stores can wear smart glasses or head-mounted displays and intuitively obtain election information on the spot through AR technology. For example, when they enter a specific election information area, candidate profiles and the latest election news are displayed in their field of vision. Furthermore, when a user asks through the smart glasses, "What are Candidate A's main policies?", the server uses generative AI to instantly provide an answer and displays it on the smart glasses.

[2518] Examples of concrete examples and prompts

[2519] For example, when a user wears smart glasses in a brick-and-mortar store and enters the election information area, the following information is displayed:

[2520] Candidate A's main policies:

[2521] education reform

[2522] environmental protection

[2523] Revitalizing the local economy

[2524] An example prompt is:

[2525] Candidate A has been a teacher for many years and has been active in educational reform. He has also proposed many policies related to environmental protection. In terms of economic policy, he places emphasis on revitalizing the local economy.

[2526] Q: What are Candidate A's key policies?

[2527] This allows users to intuitively obtain election information in real time even in physical stores, thereby increasing their interest in elections.

[2528] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2529] Step 1:

[2530] The server collects candidate information, profiles, policies, and election-related news articles from the Internet and specific databases.

[2531] Input: Election-related data from the internet and specific databases.

[2532] Output: A list of collected candidate information and news articles.

[2533] The server automatically collects election-related information through web scraping and API data acquisition, and stores the collected data for further processing.

[2534] Step 2:

[2535] The server summarizes the collected information using generative AI.

[2536] Input: Collected candidate information, profiles, policies, and election-related news articles.

[2537] Output: Candidate information and news articles summarized by generative AI.

[2538] The server uses Hugging Face's transformers library to summarize information about each candidate and news article, then converts the summarized information into a format that is easy to present to users.

[2539] Step 3:

[2540] The server transmits the generated summary information to the display device.

[2541] Input: Information summarized by the generative AI.

[2542] Output: Summary information sent to the user's display device.

[2543] The server structures the summary information and sends it in an appropriate format (e.g., JSON) to the display device (smart glasses or head-mounted display).

[2544] Step 4:

[2545] The terminal sends the question entered by the user to the server.

[2546] Input: The question entered by the user.

[2547] Output: The query data received by the server.

[2548] The user inputs a question using voice input, eye contact, etc., and the question is sent to the server. The terminal receives the user's question, formats it appropriately, and sends it to the server.

[2549] Step 5:

[2550] The server uses a generation AI to generate an answer to the received question.

[2551] Input: User question and associated election data.

[2552] Output: The answer generated by the generative AI.

[2553] The server uses a generative AI model to generate an appropriate answer to the user's question, inputs a prompt into the model, and passes the resulting answer on to the next step.

[2554] Step 6:

[2555] The server transmits the generated answer to the display device.

[2556] Input: The answer generated by the generative AI.

[2557] Output: The answer sent to the user's display device.

[2558] The server structures the generated answers and sends them to the user's display device for display.

[2559] Step 7:

[2560] The server collects election-related data and uses generative AI and data analysis tools to analyze election predictions and voting trends.

[2561] Input: Election-related data (voter turnout, poll data, past election results).

[2562] Output: Election forecasts and voting trend analysis.

[2563] The server collects election-related data and analyzes it using data analytics tools, including generative AI models, to predict election results and conduct trend analysis.

[2564] Step 8:

[2565] The server visualizes the analysis results and transmits them to a display device.

[2566] Input: Election forecasts and voting trend analysis results.

[2567] Output: Visualized graphs and charts.

[2568] The server visualizes the analysis results in graphs and charts and sends them to the user's display device, allowing the user to visually confirm the analysis results.

[2569] Step 9:

[2570] Users can obtain election information by wearing smart glasses or a head-mounted display in a physical store.

[2571] Input: Summary information, answers, and analysis results sent from the server.

[2572] Output: Visual information displayed on smart glasses or a head-mounted display.

[2573] When users enter a specific election information area, candidate information and the latest election news are displayed in their field of view using AR technology. When users enter a question, the answer is immediately displayed in their field of view.

[2574] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[2575] The present invention aims to improve voter turnout by efficiently providing information about elections through a system with the following specific functions and processing flow. In particular, by combining an emotion engine, the present invention realizes dynamic information provision according to the user's emotional state.

[2576] 1. Candidate information & election news summary function

[2577] System Configuration

[2578] The server collects candidate information, profiles, policies, and election-related news articles from the Internet and specific databases.

[2579] The server prepro...

Claims

1. A means of gathering candidate information, profiles, policies, and election-related news articles; A means of summarizing collected information using generative AI; means for transmitting the generated summary information to a user terminal; means for receiving a user-entered question; A means for generating an answer to the received question using a generation AI; means for transmitting the generated answer to a user terminal; A means of collecting election-related data and using generative AI and data analytics tools to conduct election predictions and analysis of voting trends; The system includes a means for visualizing the analysis results and transmitting them to a user terminal.

2. 2. The system according to claim 1, further comprising means for appropriately formatting and analyzing a question input by a user and passing the result to the generation AI as input data.

3. 2. The system according to claim 1, further comprising means for storing the generated summary information, answers and analysis results in a database and providing them in response to a user request.

Images