System

Abstract

A system is provided.SOLUTION: A system includes a data collection means, a data analysis means, an information providing means, and a feedback collection means.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In modern elections, there is an information gap between politicians and voters, making it difficult to understand the detailed achievements and beliefs of each candidate, especially during the election period. As a result, it is not easy for voters to find politicians who align with their own values, and election results often depend on the popularity of each candidate. This information gap reduces the quality of democracy and hinders fair elections and political participation. The present invention aims to address these issues, improve political transparency, and promote fair elections and political participation. [Means for solving the problem]

[0005] The present invention solves the above problems with a system that includes a data collection means, a data analysis means, an information provision means, and a feedback collection means. The data collection means collects data such as candidate profiles, parliamentary activities, and campaign promises via the Internet. The data analysis means analyzes the collected data using a generative artificial intelligence model and summarizes information about the candidates. The information provision means displays the summarized information through an interface that provides it to users. The feedback collection means collects feedback from users and uses it to improve the system. This allows voters to easily obtain detailed information about candidates, making it easier to choose the right politician.

[0006] "Data collection methods" are means for collecting information such as candidate profiles, parliamentary activities, and campaign promises from the Internet and other sources.

[0007] The "data analysis means" is a means for analyzing collected data using a generative artificial intelligence model and summarizing information about candidates.

[0008] "Information providing means" refers to a means for providing summarized candidate information to a user through a user interface.

[0009] The "feedback collection means" is a means for collecting feedback from users and using that information to improve the system.

[0010] A "generative artificial intelligence model" refers to an artificial intelligence model that has the ability to generate language based on large amounts of data, and includes models such as ChatGPT.

[0011] "Candidate Data" refers to a candidate's profile information, parliamentary activities, campaign promises, and any other information relating to a candidate.

[0012] "User Interface" refers to the interface through which a user accesses a system to obtain information and provide feedback. [Brief explanation of the drawings]

[0013] [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

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] The present invention relates to a system having a data collection means, a data analysis means, an information provision means, and a feedback collection means, and in particular to a system for efficiently collecting, analyzing, and providing candidate information and collecting feedback in an election.

[0035] Data collection

[0036] The server collects data such as candidate profiles, parliamentary activities, and campaign promises via the Internet. Specifically, the server obtains data from candidates' official websites, newspaper articles, social media, and other online resources. This data is collected automatically using pre-configured scraping scripts.

[0037] Data analysis

[0038] The collected data is analyzed by the server using a generative artificial intelligence model (e.g., ChatGPT). The server inputs the candidate's profile and activity history and uses the generative artificial intelligence model to summarize this information. The summary results are presented in a concise and easy-to-understand format and passed to the information provider.

[0039] Information provision

[0040] The summarized information is provided to the user through a user interface on the device. The server sends the summarized candidate information to the device via an API and displays it on the user interface. Through this interface, the user can easily view each candidate's detailed profile, parliamentary activities, and campaign promises.

[0041] Feedback collection

[0042] Users can provide feedback on the information provided. The device interface includes a feedback input form, allowing users to rate the clarity and ease of understanding of the information. When a user submits feedback, the device sends the information to the server, which stores the feedback in a database and uses it to improve the system.

[0043] Specific examples

[0044] For example, if a user wants to research a particular candidate on the Internet during an election period, the user accesses "Election Navigator" through their device. The server collects detailed data on the candidate, analyzes the collected data using a generative artificial intelligence model, and generates a summary. The generated summary is displayed to the user through a user interface. The user views the information and enters feedback about the content. The feedback is sent to the server and used to improve the system.

[0045] In this way, the system of the present invention helps voters easily obtain appropriate information and choose appropriate politicians, thereby improving the transparency of elections and contributing to promoting political participation.

[0046] The processing flow will be explained below.

[0047] Step 1:

[0048] A server prepares a list of target website URLs for collecting candidate data.

[0049] Step 2:

[0050] The server sends an HTTP request to each URL in the prepared list to retrieve the web page content. Specifically, it retrieves the HTML content using the requests library or similar.

[0051] Step 3:

[0052] The server parses the retrieved HTML content using libraries such as BeautifulSoup to extract necessary information such as the candidate's profile, parliamentary activities, campaign promises, etc. The extracted information is then converted into a structured format.

[0053] Step 4:

[0054] The server stores the structured candidate data in a temporary storage area or database, for example using a json format or database entry structure for this storage process.

[0055] Step 5:

[0056] The server uses a generative artificial intelligence model (e.g., ChatGPT) to select and retrieve stored candidate data, then formats the retrieved data as analytical input.

[0057] Step 6:

[0058] The server then inputs the formatted data into a generative artificial intelligence model to generate a summary of the candidate information, which is then converted into a concise, easy-to-understand format.

[0059] Step 7:

[0060] The server places the generated abstract data into an API endpoint configured as an information provider, which is then accessed by the user interface.

[0061] Step 8:

[0062] A user accesses a user interface using a terminal and requests specific candidate information, which sends a request to an API endpoint.

[0063] Step 9:

[0064] In response to a request from the terminal, the server acquires summary data of the relevant candidate from the database and transmits the data to the terminal as a response.

[0065] Step 10:

[0066] The terminal displays the received summary data on a user interface, allowing the user to view the information.

[0067] Step 11:

[0068] The user enters feedback on the candidate information provided, including an assessment of the clarity and understandability of the information.

[0069] Step 12:

[0070] The terminal transmits the feedback input by the user to the server as a POST request.

[0071] Step 13:

[0072] The server stores the received feedback data and analyzes and uses it for future system improvements.

[0073] This process flow allows the system to efficiently collect, analyze, and summarize candidate data, providing the information to voters in an easy-to-understand format, and collecting user feedback to help continuously improve the system.

[0074] Example 1

[0075] 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."

[0076] In elections, it is difficult for voters to quickly and accurately obtain information about candidates and make appropriate decisions based on that information. In particular, it is difficult to efficiently collect the vast amount of information scattered across the Internet and provide it in an easy-to-understand format. In addition to providing information, there are also insufficient means to collect feedback from voters and use it to improve the system.

[0077] 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.

[0078] In this invention, the server includes a data collection means, a data analysis means, an information provision means, and a feedback collection means, which enable the server to collect candidate data via the Internet, analyze and summarize the data using a generative artificial intelligence model, provide information through a user interface, and collect user feedback to use in improving the system.

[0079] "Data collection means" refers to devices or methods that automatically collect data such as candidate profiles, parliamentary activities, and campaign promises via the Internet.

[0080] "Data analysis means" refers to a device or method that analyzes collected data and summarizes it into meaningful information. In particular, it includes means that do this automatically and efficiently by using a generative artificial intelligence model.

[0081] The "information providing means" refers to a device or method that provides the analyzed data to the user through a user interface, thereby allowing the user to easily refer to information about the candidate.

[0082] "Feedback collection means" refers to a device or method that collects feedback from users, stores that information in a database, and uses it to improve the system.

[0083] A "generative artificial intelligence model" is an artificial intelligence algorithm that has the ability to generate new information based on given input data. For example, ChatGPT is an example of this.

[0084] A "user interface" is an interface that allows a user to operate a system or view information.

[0085] "Candidate data" refers to various information about candidates running in elections, including their profiles, parliamentary activities, and campaign promises.

[0086] The present invention is a system that collects and analyzes candidate information via the Internet, provides the results through a user interface, and collects feedback from users to help improve the system. Specific embodiments of the present invention are described below.

[0087] Data collection

[0088] The server connects to the Internet and collects data such as candidate profiles, parliamentary activities, and campaign promises from official candidate websites, newspaper articles, social media, etc. Web scraping tools such as Scrapy and BeautifulSoup are used to collect the data. The server uses these tools to automatically collect data based on the configured scraping script.

[0089] Data analysis

[0090] The server inputs the collected data into a generative artificial intelligence model (such as ChatGPT) for analysis. The server inputs the candidate's profile and activity history and uses ChatGPT to summarize this information. The summary results are generated in a concise and easy-to-understand format. OpenAI's API is used for data analysis.

[0091] Information provision

[0092] The server sends the analyzed and summarized candidate information to the device via API. The device displays the received information on the user interface. Through the device interface, users can easily view detailed candidate profiles, parliamentary activities, campaign promises, etc.

[0093] Feedback collection

[0094] Users enter feedback on the information provided. The device interface has a feedback input form, allowing users to rate the clarity and understandability of the information. When users submit feedback, the device sends the information to the server, which stores the feedback in a database. The collected feedback is used to improve the system.

[0095] Specific examples

[0096] For example, if a user wants to research a particular candidate during an election period, the user accesses the election navigation system through their device. The server collects detailed data on the candidate, analyzes and summarizes the data using a generative artificial intelligence model (ChatGPT), and generates a summary. The summary is then displayed to the user through a user interface. The user then browses the information and enters feedback about the content. The feedback is sent from the device to the server and used to improve the system.

[0097] Example prompt sentence:

[0098] "Analyze and summarize the profiles of the following candidates and their congressional activities to date.

[0099] Candidate Name: Taro Yamada

[0100] profile: ...

[0101] Parliamentary Activities: ...

[0102] Summary results:

[0103] "

[0104] As described above, the system of the present invention can efficiently collect, analyze, and provide candidate information and gather feedback in elections, helping voters easily obtain appropriate information and make appropriate decisions. This system will improve the transparency of elections and contribute to promoting political participation.

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

[0106] Step 1:

[0107] The server connects to the internet to collect candidate information. It runs a configured scraping script to collect data such as candidate profiles, parliamentary activities, and campaign promises from official websites, newspaper articles, social media, etc. It uses URLs and search queries as input and obtains a dataset of collected candidate information as output. This dataset is then stored in a database.

[0108] Specific working example:

[0109] The server uses Scrapy or BeautifulSoup to parse the content of the web page and extract the necessary data.

[0110] Step 2:

[0111] The server generates prompts to input the collected candidate data into the generative artificial intelligence model. The prompts include the candidate's name, profile, and parliamentary activities. The candidate data is used as input, and the prompts are generated as output.

[0112] Specific working example:

[0113] The server uses the OpenAI API to pass files to the generative artificial intelligence model.

[0114] Step 3:

[0115] The server inputs the prompt sentence into a generative AI model for analysis. Using a generative AI model such as ChatGPT, the server summarizes the candidate's information. The prompt sentence is used as input, and the summarized information is obtained as output. This summary information is stored in a database.

[0116] Specific working example:

[0117] The server passes the prompt to the OpenAI API and saves the resulting summary in text format.

[0118] Step 4:

[0119] The server sends the summarized candidate information to the terminal through the API. The terminal displays the received information on the user interface. The summarized information is used as input, and the information sent to the terminal is obtained as output.

[0120] Specific working example:

[0121] The server uses a framework (e.g., Flask or Django) to provide an API and send information to the device.

[0122] Step 5:

[0123] The user views the candidate information through the user interface of the terminal. The summarized candidate information is used as input, and the user's act of viewing the information is obtained as output.

[0124] Specific working example:

[0125] The device uses front-end frameworks such as React and Vue.js to build the interface and display information.

[0126] Step 6:

[0127] The user enters feedback on the provided information. The terminal interface has a feedback input form, allowing the user to rate the clarity and understandability of the information. The user's feedback is used as input, and feedback information is obtained as output.

[0128] Specific working example:

[0129] The user enters their feedback into a form in the interface and clicks the submit button.

[0130] Step 7:

[0131] The terminal sends the user's feedback to the server, and the feedback information is used as input, and the feedback sent to the server is obtained as output.

[0132] Specific working example:

[0133] The device uses AJAX requests to send feedback to the server asynchronously.

[0134] Step 8:

[0135] The server stores the received feedback in a database and uses it to improve the system. Feedback information is used as input, and feedback data for system improvement is obtained as output.

[0136] Specific working example:

[0137] The server stores the feedback information in a database and uses it for analysis.

[0138] (Application example 1)

[0139] 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."

[0140] In modern society, election information is extremely diverse, making it difficult to easily gather and understand detailed information such as candidate profiles, parliamentary activities, and campaign promises. Furthermore, the means by which voters can obtain information based on their own interests are limited, making it necessary to improve the transparency of election information and promote political participation.

[0141] 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.

[0142] In this invention, the server includes a data collection means, a data analysis means, an information provision means, a feedback collection means, a means for generating and providing summary information based on the user's interests using the collected data, and a means for the user to input feedback on the summary information provided. This allows the user to easily and efficiently obtain detailed information about candidates and obtain information personalized based on their own interests. Furthermore, the system is improved based on the feedback, increasing the transparency and ease of understanding of the information.

[0143] A "data collection means" is a device or program means that automatically collects data such as candidate profiles, parliamentary activities, and campaign promises via the Internet.

[0144] "Data analysis means" means a device or program means that analyzes collected data using a generative artificial intelligence model and extracts and summarizes important information.

[0145] "Information providing means" refers to a device or program means for providing summarized information to a user through a user interface.

[0146] The "feedback collection means" is a device or program means that allows a user to input feedback on the provided information and collects that feedback.

[0147] The "means for generating and providing summary information according to the user's interests" refers to a device or program means that analyzes collected data, generates personalized summary information based on the user's interests, and provides it to the user.

[0148] The "means for a user to input feedback on the provided summary information" refers to a device or program means by which a user inputs an evaluation or opinion on the provided summary information and transmits the information to the system.

[0149] The system for implementing the present invention has the following means, thereby enabling efficient collection, analysis, provision and feedback collection of election information.

[0150] Data collection

[0151] The server collects data such as candidate profiles, parliamentary activities, and campaign promises via the Internet. Specifically, the server uses a web scraping tool to automatically collect data from candidate official websites, news articles, social media, and other online resources. The hardware used is a standard server machine, and the software used is Python and BeautifulSoup.

[0152] Data analysis

[0153] The collected data is analyzed by the server using a generative AI model (e.g., ChatGPT). The server inputs the candidate's profile and activity history into the generative AI model and summarizes this information. This summary result is generated in a concise and easy-to-understand format. The hardware is a similarly standard server machine, and the software uses OpenAI's API.

[0154] Information provision

[0155] The summarized information is sent from the server to the device and provided to the user through a user interface. The information is sent via an API and displayed in an application on the device. Users can easily view detailed profiles, activities, and campaign promises of candidates through the smartphone application.

[0156] Feedback collection

[0157] Users can provide feedback on the information provided. The device interface includes a feedback input form, allowing users to rate the clarity and understandability of the information. The feedback is sent from the device to the server, which stores the collected feedback in a database and uses it to improve the system.

[0158] Specific examples

[0159] For example, if a user wants more information about a particular candidate during an election, they can open a smartphone app and see a prompt such as, "Please summarize the recent activities of candidate XX." The server analyzes the collected data and generates a summary using a generative artificial intelligence model. The summary is then displayed on the app's user interface, allowing the user to view the information and provide their rating and feedback.

[0160] The system allows users to efficiently obtain personalized election information based on their interests, improves the transparency and understandability of the information provided, and continuously improves the system based on feedback, resulting in higher quality information being provided.

[0161] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0162] System program processing flow

[0163] Step 1:

[0164] The server collects detailed data on candidates via the Internet. Specifically, it uses a web scraping tool (e.g., Python's BeautifulSoup) to extract information such as the candidate's profile, parliamentary activities, and campaign promises from online resources such as the candidate's official website, news articles, and social media. In this process, a list of URLs is given as input, and HTML content is obtained as output.

[0165] Step 2:

[0166] The server inputs the collected data into a generative artificial intelligence model (e.g., ChatGPT). The collected text data is sent to OpenAI's API, which extracts key information about the candidate and generates a summary. This process uses the collected text data as input and produces summarized candidate information as output.

[0167] Step 3:

[0168] The server sends the summarized information to the device. The generated summary information is transferred to the smartphone application via a RESTful API. This allows the information to be displayed on the user's smartphone. The summarized data is passed to the API as input, and the data is provided to the device as output.

[0169] Step 4:

[0170] The terminal displays the summary information to the user through a user interface. The data acquired by the smartphone application is displayed in a visually easy-to-read format for the user. The input of this step is the summary data sent from the server, and the output is an information screen that the user can view.

[0171] Step 5:

[0172] Users can provide feedback on the information provided, such as clarity and understandability of the information, as well as additional questions and comments, via a feedback form. The input is the user's feedback, and the output is the feedback data sent to the server.

[0173] Step 6:

[0174] The server collects the feedback sent by users and stores it in a database. The feedback data is accumulated and used to improve the system. The input is the user feedback data, and the output is the feedback record stored in the database.

[0175] Specific operation example

[0176] For example, to collect information about a particular candidate during an election, the server scrapes the URL of the candidate's official website and obtains HTML data. The HTML data is then input into ChatGPT to generate a summary of the candidate's recent activities. The summary is then sent to the smartphone application via API and displayed on the user interface. The user can then enter a prompt such as "Please summarize the recent activities of candidate XX" and provide feedback based on the information. This feedback is returned to the server and stored in the feedback database.

[0177] 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.

[0178] The present invention relates to a system that combines a data collection means, a data analysis means, an information provision means, a feedback collection means, and an emotion engine that recognizes user emotions, and in particular, is a system for efficiently collecting, analyzing, and providing candidate information and collecting feedback in elections. The following describes an embodiment of the present invention.

[0179] Data collection

[0180] The server collects data such as candidate profiles, parliamentary activities, and campaign promises via the Internet. The server obtains the necessary data from the candidates' official websites, newspaper articles, social media, and other online resources. This data is collected automatically using pre-configured scraping scripts and APIs.

[0181] Data analysis

[0182] The collected data is analyzed by the server using a generative artificial intelligence model (e.g., ChatGPT). The server passes the candidate's profile and activity history as input to the generative artificial intelligence model, and generates summary information as the analysis result. This summary result is provided in a concise and easy-to-understand format.

[0183] Information provision

[0184] The summarized information is provided to the user through a user interface on the device. The server sends the summarized information to the device via an API and displays it on the user interface. Through this interface, the user can view each candidate's detailed profile, parliamentary activities, and campaign promises.

[0185] Feedback collection

[0186] Users can provide feedback on the information provided. The device interface has a feedback input form, where users can rate the clarity and ease of understanding of the information. When a user submits feedback, the device sends the information to the server. The server stores the feedback in a database and uses it to improve the system.

[0187] Use of emotion engine

[0188] The emotion engine recognizes emotions from user input and operations and adjusts the information provided based on those emotions. For example, if a user performs an operation or makes a comment that indicates dissatisfaction while viewing information about a candidate, the emotion engine analyzes that emotion and notifies the server. The server then adjusts the content and format of the information provided based on this information, providing the information in a more appropriate form for the user.

[0189] Specific examples

[0190] For example, if a user wants to research a particular candidate during an election, they access the "Election Navigator" using their device. The server collects detailed data on the candidate and analyzes and summarizes this data using a generative artificial intelligence model. The generated summary is displayed to the user through the device's user interface. If the user is dissatisfied while viewing this summary information, the emotion engine recognizes their emotion and notifies the server. The server adjusts the information it provides based on the information it receives and presents it to the user again. Users can also provide feedback on the clarity and content of the information, which is sent to the server and used to improve the system.

[0191] In this way, the system of the present invention helps voters easily obtain appropriate information and make it easier to choose the right politician. Furthermore, by introducing an emotion engine, it is possible to provide information according to the user's emotions, improving the user experience of the system.

[0192] The processing flow will be explained below.

[0193] Step 1:

[0194] The server prepares a list of target website URLs to collect candidate data, including official candidate websites, news articles, social media accounts, etc.

[0195] Step 2:

[0196] The server sends an HTTP request to each URL in the prepared list to retrieve the web page content, specifically the HTML content, using the requests library.

[0197] Step 3:

[0198] The server parses the retrieved HTML content using BeautifulSoup and extracts necessary information such as candidate profiles, parliamentary activities, campaign promises, etc. The extracted information is converted into a structured format such as JSON.

[0199] Step 4:

[0200] The server stores the structured candidate data in a database, where the storage process involves creating a database entry or updating an existing entry.

[0201] Step 5:

[0202] The server retrieves and analyzes the stored data using a generative artificial intelligence model (e.g., ChatGPT). The server passes the candidate's profile and activity history as input to the generative artificial intelligence model and generates summary information.

[0203] Step 6:

[0204] The server places the generated summary information at an API endpoint configured as an information provider, which is accessed by a user interface.

[0205] Step 7:

[0206] A user accesses a user interface using a terminal and requests specific candidate information, which sends a request to an API endpoint.

[0207] Step 8:

[0208] In response to a request from the terminal, the server acquires summary information of the relevant candidate from the database and transmits the data to the terminal as a response.

[0209] Step 9:

[0210] The terminal displays the received summary information on a user interface, allowing the user to view the information.

[0211] Step 10:

[0212] The user reacts to the displayed candidate information. The device sends the user's comments and input actions to the emotion engine to recognize the user's emotions.

[0213] Step 11:

[0214] The emotion engine recognizes emotions from user input and operations and sends the emotion data to the server. For example, if a user enters a comment expressing dissatisfaction, it will be recognized as a negative emotion.

[0215] Step 12:

[0216] The server receives the emotion data provided by the emotion engine and determines an action based on the emotion. For example, if the user expresses dissatisfaction, the server may provide more detailed information.

[0217] Step 13:

[0218] The user inputs feedback on the provided information. The terminal sends the feedback data to the server as a POST request.

[0219] Step 14:

[0220] The server stores, analyzes, and uses your feedback data for future system improvements. This feedback includes your evaluation of the clarity and understandability of the information.

[0221] This process flow allows the system of the present invention to efficiently collect, analyze, and summarize candidate data, and provide information to voters in an easy-to-understand format. Furthermore, by adjusting the information according to the user's emotions, the system can improve the user experience.

[0222] Example 2

[0223] 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."

[0224] There is a need for systems that allow users to quickly and accurately collect, analyze, and evaluate information in elections and other decision-making processes. However, conventional systems have had difficulty efficiently collecting and analyzing large amounts of data and providing it appropriately to users. They also lacked the ability to adjust information taking into account user feedback and emotions. The purpose of this invention is to solve these problems and provide a system that provides users with accurate information that is easy to understand.

[0225] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0226] In this invention, the server includes a data collection means, a data analysis means, an information provision means, a feedback collection means, an emotion recognition means, and a data adjustment means, which makes it possible to efficiently collect and analyze large amounts of data and to adjust and provide information based on the user's feedback and emotions.

[0227] "Data collection means" refers to a means for collecting target data via the Internet.

[0228] "Data analysis means" refers to means for analyzing collected data using a generative artificial intelligence model.

[0229] The "information providing means" is a means for providing the analyzed information to the user.

[0230] The "feedback collection means" is a means for collecting feedback from users.

[0231] The "emotion recognition means" is a means for recognizing emotions from user inputs and operations.

[0232] The "data adjustment means" is a means for adjusting the content and format of the information to be provided based on the information from the emotion recognition means.

[0233] The present invention is a system that combines data collection means, data analysis means, information provision means, feedback collection means, emotion recognition means, and data adjustment means. This system is designed to efficiently collect, analyze, and provide candidate information and collect feedback, particularly in elections. The detailed configuration and operating procedures for implementing the present invention are described below.

[0234] Hardware and software used

[0235] Hardware: Servers, devices (PCs, smartphones, etc.)

[0236] Software: scraping scripts, APIs, generative AI models (e.g., ChatGPT), sentiment engines, user interfaces, databases

[0237] Data collection

[0238] The server collects data such as candidate profiles, parliamentary activities, and campaign promises from the internet. The server automatically retrieves the necessary data from the candidates' official websites, newspaper articles, social media, and other online resources. This process is performed using pre-configured scraping scripts and APIs.

[0239] Data analysis

[0240] The server passes the collected data to a generative artificial intelligence model (e.g., ChatGPT). The generative artificial intelligence model is used to analyze the collected data and concisely summarize the candidate's information. During this analysis and summarization process, specific prompts (e.g., "Please summarize the candidate's profile") are input to the generative artificial intelligence model. The summarized information is then organized by the server and stored in a database in its final form.

[0241] Information provision

[0242] The server sends the summarized information via an API to the device, which then displays it to the user through a user interface. The user can navigate through this interface to view each candidate's detailed profile, parliamentary activities, and campaign promises.

[0243] Feedback collection

[0244] The device's user interface displays a form for entering feedback. When the user enters their thoughts and suggestions for improvement in the form and submits it, the device sends the feedback information to the server. The server stores the received feedback in a database and uses it later to improve the system.

[0245] Use of emotion engine

[0246] The emotion engine recognizes emotions from user input and operations. For example, if a user becomes dissatisfied while viewing information about a candidate, the emotion engine analyzes that emotion and notifies the server. The server then adjusts the content and format of the information it provides based on this notification. The adjusted information is then sent back to the terminal and redisplayed on the user interface.

[0247] Specific examples

[0248] For example, if a user wants to research a particular candidate during an election, the user accesses the "Election Navigator" app using a device. The server collects detailed data on the candidate and analyzes and summarizes this data using a generative artificial intelligence model. The generated summary is displayed to the user through the device's user interface. If the user is dissatisfied with the summary information, the emotion engine recognizes the user's emotion and notifies the server. The server then adjusts the information provided based on the information received and presents it to the user again. The user also provides feedback on the information's understandability and content, which is sent to the server and used to improve the system. In this way, the system of the present invention helps users easily obtain appropriate information and make appropriate decisions. Furthermore, the introduction of an emotion engine enables the provision of information tailored to the user's emotions, improving the user experience of the system.

[0249] Prompt Sentence Examples

[0250] "Use Election Navigator to find out information about candidates. Please provide detailed data on the candidates."

[0251] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0252] Step 1: Data collection

[0253] The server identifies the source of candidate information by referencing a list of URLs, such as the candidate's official website, newspaper articles, and social media.

[0254] Input: A list of URLs from which data is collected.

[0255] Output: URL to be scraped or API called

[0256] How it works: The server checks the URL list and prepares to collect data.

[0257] Step 2: Performing data collection

[0258] The server runs scraping scripts and APIs to collect data, specifically, it retrieves HTML data from specific web pages and JSON data from API endpoints.

[0259] Input: URL list, scraping script, API settings

[0260] Output: Raw candidate information obtained

[0261] How it works: The server uses configured scripts and APIs to collect data and store it in temporary storage.

[0262] Step 3: Save Data

[0263] The server stores the collected data in a temporary database.

[0264] Input: Raw candidate data collected

[0265] Output: Data stored in a temporary database

[0266] How it works: The server formats the collected data, filters out missing and duplicate data, and stores it in a temporary database.

[0267] Step 4: Prepare for data analysis

[0268] The server reads the collected data from the temporary database and prepares the input for the generative artificial intelligence model.

[0269] Input: Data stored in a temporary database

[0270] Output: Formatted data to feed into a generative artificial intelligence model

[0271] How it works: The server formats the data and passes it to a generative artificial intelligence model with appropriate prompts.

[0272] Step 5: Data analysis

[0273] The server uses a generative artificial intelligence model to analyze the data and summarize the candidate's information, for example using prompts such as "Please summarize the candidate's profile."

[0274] Input: Formatted data, prompt

[0275] Output: Summarized candidate information

[0276] How it works: The server runs a generative artificial intelligence model to obtain summary information that is then organized.

[0277] Step 6: Save summary information

[0278] The server organizes the summary results and stores them in their final form.

[0279] Input: Summary information from a generative artificial intelligence model

[0280] Output: Organized summary information, stored in a database

[0281] How it works: The server organizes the summary information and stores it in a database, filtering out unnecessary information in the process.

[0282] Step 7: Provide information

[0283] The server sends the summarized information to the device via API.

[0284] Input: Organized summary information, API settings

[0285] Output: Result sent to terminal

[0286] How it works: The server sends summary information to the device via the API.

[0287] Step 8: Display information

[0288] The terminal displays the information on a user interface.

[0289] Input: Summary information received from the server

[0290] Output: Information displayed in the user interface

[0291] What it does: The device formats the information and displays it on the user interface.

[0292] Step 9: Enter your feedback

[0293] The user enters feedback on the information provided.

[0294] Input: User actions to view information

[0295] Output: Feedback content

[0296] How it works: The user fills out a feedback form on the interface with their thoughts and ratings.

[0297] Step 10: Send feedback

[0298] The terminal sends feedback information to the server.

[0299] Input: Feedback entered by the user

[0300] Output: Result sent to the server

[0301] Operation: The device sends the feedback content to the server using a communication protocol.

[0302] Step 11: Save your feedback

[0303] The server stores the feedback in a database.

[0304] Input: Feedback sent from the device

[0305] Output: Feedback information stored in a database

[0306] How it works: The server stores the feedback information in a database for later use in improving the system.

[0307] Step 12: Sentiment Analysis

[0308] The emotion engine analyzes user input and operations.

[0309] Input: User operation history and comment content

[0310] Output: Emotion analysis results

[0311] How it works: The emotion engine performs real-time analysis and notifies the emotional state to the server.

[0312] Step 13: Information Reconciliation

[0313] The server adjusts the information based on the results of emotion analysis.

[0314] Input: Analysis results from the emotion engine

[0315] Output: Adjusted information

[0316] Operation: Adjusts the content and format of the information provided by the server and sends it back to the device.

[0317] Step 14: Redisplay

[0318] The re-adjusted information is sent to the terminal and displayed again on the interface.

[0319] Input: Adjusted information

[0320] Output: Information redisplayed in the user interface

[0321] How it works: The server sends the adjusted information to the device, which displays it on its user interface.

[0322] (Application example 2)

[0323] 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."

[0324] In physical stores, it is difficult for customers to quickly obtain appropriate product information based on their preferences and past purchase history. Furthermore, the information provided cannot be adjusted in real time based on the customer's emotions and reactions, which means that the customer experience is not fully improved. This makes it difficult to improve customer satisfaction and stimulate purchasing motivation.

[0325] 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.

[0326] In this invention, the server includes a data collection means, a data analysis means, an information provision means, a feedback collection means, an emotion recognition means, a means for acquiring customer profile data, a means for providing product information based on customer preferences, and a means for providing summary information, thereby making it possible to provide appropriate product information based on the customer's past purchase history and preferences, and to adjust information according to the customer's emotions.

[0327] "Data collection means" refers to a function that acquires information such as customer profile data, purchase history, and preferences via the Internet at physical stores.

[0328] "Data analysis means" is a function that analyzes collected data using a generative artificial intelligence model to generate summaries of customer-based information.

[0329] The "information provision means" is a function that presents appropriate product information and summaries through a user interface for providing the analyzed results to customers.

[0330] The "feedback collection means" is a function that collects feedback from users and transmits it to the server.

[0331] "Emotion recognition means" is a function that recognizes emotions from customer input and operations and adjusts the information provided in real time based on those emotions.

[0332] "Means for obtaining customer profile data" refers to a function for collecting customers' past purchase history, preferences, and other related information via the Internet.

[0333] The "means for providing product information based on customer preferences" is a function that provides optimal product information to customers based on collected customer data.

[0334] The "means for providing summary information" is a function that provides summary information analyzed by a generative artificial intelligence model to customers in an easy-to-understand manner.

[0335] The system for implementing this invention mainly consists of three elements: a server, a terminal, and a user. The server has a data collection means, a data analysis means, an information provision means, a feedback collection means, and an emotion recognition means, while the terminal provides an interface for providing information and collecting feedback. The user also uses the terminal to access the system to obtain information and send feedback.

[0336] Data collection via the internet

[0337] The server first collects customer profile data from various online resources, a process automated using predefined scraping scripts and APIs, including information about past purchases and preferences.

[0338] Data analysis

[0339] The collected data is then analyzed using a generative artificial intelligence model (e.g., ChatGPT). The server inputs the customer's profile and past purchase history into the model, and generates summary information as the analysis result. This summary information is presented in a concise and easy-to-understand format.

[0340] Examples of prompt statements

[0341] For example, provide the following prompt to a generative AI model:

[0342] Purchase history: 'Tea, Coffee, Mineral Water'

[0343] Preferences: 'Healthy food, I like organic products'

[0344] Information provision

[0345] The summarized information is provided to the user through a user interface on the device. The server sends the summarized information to the device via an API, and the device displays it on the user interface. The user can view detailed product information and recommended products through this interface.

[0346] Feedback collection

[0347] Users can provide feedback on the information provided. A feedback input form is provided in the device interface. Users rate the information on its clarity and understandability, and the device sends this to the server. The server stores the feedback in a database and uses it to improve the system.

[0348] emotion recognition

[0349] The emotion engine recognizes emotions from user operations and inputs and adjusts the information provided based on those emotions. For example, if a user makes a comment expressing uncertainty while browsing product information, the emotion engine analyzes this and notifies the server. The server then adjusts the content and format of the information provided based on this information and presents it to the user again.

[0350] For example, if a user enters a comment such as "I want to see the ingredients list for this product," the emotion engine will interpret this as an indication of interest and display additional detailed information such as "All of the ingredients in this product are organic and additive-free." In this way, information can be provided that reflects the customer's emotions, improving the user experience.

[0351] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0352] Step 1:

[0353] The server collects customer profile data via the internet. The input includes customer ID, interest categories, etc. These data are collected using predefined scraping scripts or APIs. As output, customer profile data (purchase history, preferences, etc.) is obtained and stored in a database.

[0354] Step 2:

[0355] The server extracts the collected customer data and passes it to a generative artificial intelligence model (such as ChatGPT) for analysis. The input is the customer's past purchase history and preferences, which are provided as prompts. Summary information (e.g., a list of products recommended to the customer and their overview) is generated as output.

[0356] Step 3:

[0357] The server sends the summarized information to the terminal. As input, it contains the generated summarized information. As output, the summarized information is sent to the terminal through the API. The terminal prepares this information to be displayed on the user interface.

[0358] Step 4:

[0359] The terminal displays the provided summary information to the user through a user interface, which includes the summary information sent from the server as input, and displays the information on the terminal screen in a form that can be viewed by the user as output.

[0360] Step 5:

[0361] The user inputs feedback about the displayed information. The input includes the user's feedback comments and ratings. The output is sent from the terminal to the server.

[0362] Step 6:

[0363] The server stores the feedback sent by the user in a database. The input includes the feedback information. The output is the feedback stored and data for system improvement is accumulated based on the feedback.

[0364] Step 7:

[0365] The device or server recognizes emotions from the user's actions and comments. The input includes the user's actions and comments. The processing involves analysis using an emotion analysis engine (such as NVIDIA NeMo). The output is a result based on the user's emotions.

[0366] Step 8:

[0367] The server adjusts the information provided based on the emotion analysis results. The emotion analysis results are included as input. The adjusted information is generated as output and sent back to the device. The device then redisplays the adjusted information, improving the user experience.

[0368] 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.

[0369] 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.

[0370] 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.

[0371] [Second embodiment]

[0372] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0373] 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.

[0374] 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).

[0375] 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.

[0376] 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.

[0377] 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).

[0378] 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.

[0379] 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.

[0380] 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.

[0381] 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.

[0382] 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.

[0383] 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."

[0384] The present invention relates to a system having a data collection means, a data analysis means, an information provision means, and a feedback collection means, and in particular to a system for efficiently collecting, analyzing, and providing candidate information and collecting feedback in an election.

[0385] Data collection

[0386] The server collects data such as candidate profiles, parliamentary activities, and campaign promises via the Internet. Specifically, the server obtains data from candidates' official websites, newspaper articles, social media, and other online resources. This data is collected automatically using pre-configured scraping scripts.

[0387] Data analysis

[0388] The collected data is analyzed by the server using a generative artificial intelligence model (e.g., ChatGPT). The server inputs the candidate's profile and activity history and uses the generative artificial intelligence model to summarize this information. The summary results are presented in a concise and easy-to-understand format and passed to the information provider.

[0389] Information provision

[0390] The summarized information is provided to the user through a user interface on the device. The server sends the summarized candidate information to the device via an API and displays it on the user interface. Through this interface, the user can easily view each candidate's detailed profile, parliamentary activities, and campaign promises.

[0391] Feedback collection

[0392] Users can provide feedback on the information provided. The device interface includes a feedback input form, allowing users to rate the clarity and ease of understanding of the information. When a user submits feedback, the device sends the information to the server, which stores the feedback in a database and uses it to improve the system.

[0393] Specific examples

[0394] For example, if a user wants to research a particular candidate on the Internet during an election period, the user accesses "Election Navigator" through their device. The server collects detailed data on the candidate, analyzes the collected data using a generative artificial intelligence model, and generates a summary. The generated summary is displayed to the user through a user interface. The user views the information and enters feedback about the content. The feedback is sent to the server and used to improve the system.

[0395] In this way, the system of the present invention helps voters easily obtain appropriate information and choose appropriate politicians, thereby improving the transparency of elections and contributing to promoting political participation.

[0396] The processing flow will be explained below.

[0397] Step 1:

[0398] A server prepares a list of target website URLs for collecting candidate data.

[0399] Step 2:

[0400] The server sends an HTTP request to each URL in the prepared list to retrieve the web page content. Specifically, it retrieves the HTML content using the requests library or similar.

[0401] Step 3:

[0402] The server parses the retrieved HTML content using libraries such as BeautifulSoup to extract necessary information such as the candidate's profile, parliamentary activities, campaign promises, etc. The extracted information is then converted into a structured format.

[0403] Step 4:

[0404] The server stores the structured candidate data in a temporary storage area or database, for example using a json format or database entry structure for this storage process.

[0405] Step 5:

[0406] The server uses a generative artificial intelligence model (e.g., ChatGPT) to select and retrieve stored candidate data, then formats the retrieved data as analytical input.

[0407] Step 6:

[0408] The server then inputs the formatted data into a generative artificial intelligence model to generate a summary of the candidate information, which is then converted into a concise, easy-to-understand format.

[0409] Step 7:

[0410] The server places the generated abstract data into an API endpoint configured as an information provider, which is then accessed by the user interface.

[0411] Step 8:

[0412] A user accesses a user interface using a terminal and requests specific candidate information, which sends a request to an API endpoint.

[0413] Step 9:

[0414] In response to a request from the terminal, the server acquires summary data of the relevant candidate from the database and transmits the data to the terminal as a response.

[0415] Step 10:

[0416] The terminal displays the received summary data on a user interface, allowing the user to view the information.

[0417] Step 11:

[0418] The user enters feedback on the candidate information provided, including an assessment of the clarity and understandability of the information.

[0419] Step 12:

[0420] The terminal transmits the feedback input by the user to the server as a POST request.

[0421] Step 13:

[0422] The server stores the received feedback data and analyzes and uses it for future system improvements.

[0423] This process flow allows the system to efficiently collect, analyze, and summarize candidate data, providing information to voters in an easy-to-understand format, and collecting user feedback to help continuously improve the system.

[0424] Example 1

[0425] 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."

[0426] In elections, it is difficult for voters to quickly and accurately obtain information about candidates and make appropriate decisions based on that information. In particular, it is difficult to efficiently collect the vast amount of information scattered across the Internet and provide it in an easy-to-understand format. In addition to providing information, there are also insufficient means to collect feedback from voters and use it to improve the system.

[0427] 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.

[0428] In this invention, the server includes a data collection means, a data analysis means, an information provision means, and a feedback collection means, which enable the server to collect candidate data via the Internet, analyze and summarize the data using a generative artificial intelligence model, provide information through a user interface, and collect user feedback to use in improving the system.

[0429] "Data collection means" refers to devices or methods that automatically collect data such as candidate profiles, parliamentary activities, and campaign promises via the Internet.

[0430] "Data analysis means" refers to a device or method that analyzes collected data and summarizes it into meaningful information. In particular, it includes means that do this automatically and efficiently by using a generative artificial intelligence model.

[0431] The "information providing means" refers to a device or method that provides the analyzed data to the user through a user interface, thereby allowing the user to easily refer to information about the candidate.

[0432] "Feedback collection means" refers to a device or method that collects feedback from users, stores that information in a database, and uses it to improve the system.

[0433] A "generative artificial intelligence model" is an artificial intelligence algorithm that has the ability to generate new information based on given input data. For example, ChatGPT is an example of this.

[0434] A "user interface" is an interface that allows a user to operate a system or view information.

[0435] "Candidate data" refers to various information about candidates running in elections, including their profiles, parliamentary activities, and campaign promises.

[0436] The present invention is a system that collects and analyzes candidate information via the Internet, provides the results through a user interface, and collects feedback from users to help improve the system. Specific embodiments of the present invention are described below.

[0437] Data collection

[0438] The server connects to the Internet and collects data such as candidate profiles, parliamentary activities, and campaign promises from official candidate websites, newspaper articles, social media, etc. Web scraping tools such as Scrapy and BeautifulSoup are used to collect the data. The server uses these tools to automatically collect data based on the configured scraping script.

[0439] Data analysis

[0440] The server inputs the collected data into a generative artificial intelligence model (such as ChatGPT) for analysis. The server inputs the candidate's profile and activity history and uses ChatGPT to summarize this information. The summary results are generated in a concise and easy-to-understand format. OpenAI's API is used for data analysis.

[0441] Information provision

[0442] The server sends the analyzed and summarized candidate information to the device via API. The device displays the received information on the user interface. Through the device interface, users can easily view detailed candidate profiles, parliamentary activities, campaign promises, etc.

[0443] Feedback collection

[0444] Users enter feedback on the information provided. The device interface has a feedback input form, allowing users to rate the clarity and understandability of the information. When users submit feedback, the device sends the information to the server, which stores the feedback in a database. The collected feedback is used to improve the system.

[0445] Specific examples

[0446] For example, if a user wants to research a particular candidate during an election period, the user accesses the election navigation system through their device. The server collects detailed data on the candidate, analyzes and summarizes the data using a generative artificial intelligence model (ChatGPT), and generates a summary. The summary is then displayed to the user through a user interface. The user then browses the information and enters feedback about the content. The feedback is sent from the device to the server and used to improve the system.

[0447] Example prompt sentence:

[0448] "Analyze and summarize the profiles of the following candidates and their congressional activities to date.

[0449] Candidate Name: Taro Yamada

[0450] profile: ...

[0451] Parliamentary Activities: ...

[0452] Summary results:

[0453] "

[0454] As described above, the system of the present invention can efficiently collect, analyze, and provide candidate information and gather feedback in elections, helping voters easily obtain appropriate information and make appropriate decisions. This system will improve the transparency of elections and contribute to promoting political participation.

[0455] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0456] Step 1:

[0457] The server connects to the internet to collect candidate information. It runs a configured scraping script to collect data such as candidate profiles, parliamentary activities, and campaign promises from official websites, newspaper articles, social media, etc. It uses URLs and search queries as input and obtains a dataset of collected candidate information as output. This dataset is then stored in a database.

[0458] Specific working example:

[0459] The server uses Scrapy or BeautifulSoup to parse the content of the web page and extract the necessary data.

[0460] Step 2:

[0461] The server generates prompts to input the collected candidate data into the generative artificial intelligence model. The prompts include the candidate's name, profile, and parliamentary activities. The candidate data is used as input, and the prompts are generated as output.

[0462] Specific working example:

[0463] The server uses the OpenAI API to pass files to the generative artificial intelligence model.

[0464] Step 3:

[0465] The server inputs the prompt sentence into a generative AI model for analysis. Using a generative AI model such as ChatGPT, the server summarizes the candidate's information. The prompt sentence is used as input, and the summarized information is obtained as output. This summary information is stored in a database.

[0466] Specific working example:

[0467] The server passes the prompt to the OpenAI API and saves the resulting summary in text format.

[0468] Step 4:

[0469] The server sends the summarized candidate information to the terminal through the API. The terminal displays the received information on the user interface. The summarized information is used as input, and the information sent to the terminal is obtained as output.

[0470] Specific working example:

[0471] The server uses a framework (e.g., Flask or Django) to provide an API and send information to the device.

[0472] Step 5:

[0473] The user views the candidate information through the user interface of the terminal. The summarized candidate information is used as input, and the user's act of viewing the information is obtained as output.

[0474] Specific working example:

[0475] The device uses front-end frameworks such as React and Vue.js to build the interface and display information.

[0476] Step 6:

[0477] The user enters feedback on the provided information. The terminal interface has a feedback input form, allowing the user to rate the clarity and understandability of the information. The user's feedback is used as input, and feedback information is obtained as output.

[0478] Specific working example:

[0479] The user enters their feedback into a form in the interface and clicks the submit button.

[0480] Step 7:

[0481] The terminal sends the user's feedback to the server, and the feedback information is used as input, and the feedback sent to the server is obtained as output.

[0482] Specific working example:

[0483] The device uses AJAX requests to send feedback to the server asynchronously.

[0484] Step 8:

[0485] The server stores the received feedback in a database and uses it to improve the system. Feedback information is used as input, and feedback data for system improvement is obtained as output.

[0486] Specific working example:

[0487] The server stores the feedback information in a database and uses it for analysis.

[0488] (Application example 1)

[0489] 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."

[0490] In modern society, election information is extremely diverse, making it difficult to easily gather and understand detailed information such as candidate profiles, parliamentary activities, and campaign promises. Furthermore, the means by which voters can obtain information based on their own interests are limited, making it necessary to improve the transparency of election information and promote political participation.

[0491] 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.

[0492] In this invention, the server includes a data collection means, a data analysis means, an information provision means, a feedback collection means, a means for generating and providing summary information based on the user's interests using the collected data, and a means for the user to input feedback on the summary information provided. This allows the user to easily and efficiently obtain detailed information about candidates and obtain information personalized based on their own interests. Furthermore, the system is improved based on the feedback, increasing the transparency and ease of understanding of the information.

[0493] A "data collection means" is a device or program means that automatically collects data such as candidate profiles, parliamentary activities, and campaign promises via the Internet.

[0494] "Data analysis means" means a device or program means that analyzes collected data using a generative artificial intelligence model and extracts and summarizes important information.

[0495] "Information providing means" refers to a device or program means for providing summarized information to a user through a user interface.

[0496] The "feedback collection means" is a device or program means that allows a user to input feedback on the provided information and collects that feedback.

[0497] The "means for generating and providing summary information according to the user's interests" refers to a device or program means that analyzes collected data, generates personalized summary information based on the user's interests, and provides it to the user.

[0498] The "means for a user to input feedback on the provided summary information" refers to a device or program means by which a user inputs an evaluation or opinion on the provided summary information and transmits the information to the system.

[0499] The system for implementing the present invention has the following means, thereby enabling efficient collection, analysis, provision and feedback collection of election information.

[0500] Data collection

[0501] The server collects data such as candidate profiles, parliamentary activities, and campaign promises via the Internet. Specifically, the server uses a web scraping tool to automatically collect data from candidate official websites, news articles, social media, and other online resources. The hardware used is a standard server machine, and the software used is Python and BeautifulSoup.

[0502] Data analysis

[0503] The collected data is analyzed by the server using a generative AI model (e.g., ChatGPT). The server inputs the candidate's profile and activity history into the generative AI model and summarizes this information. This summary result is generated in a concise and easy-to-understand format. The hardware is a similarly standard server machine, and the software uses OpenAI's API.

[0504] Information provision

[0505] The summarized information is sent from the server to the device and provided to the user through a user interface. The information is sent via an API and displayed in an application on the device. Users can easily view detailed profiles, activities, and campaign promises of candidates through the smartphone application.

[0506] Feedback collection

[0507] Users can provide feedback on the information provided. The device interface includes a feedback input form, allowing users to rate the clarity and understandability of the information. The feedback is sent from the device to the server, which stores the collected feedback in a database and uses it to improve the system.

[0508] Specific examples

[0509] For example, if a user wants more information about a particular candidate during an election, they can open a smartphone app and see a prompt such as, "Please summarize the recent activities of candidate XX." The server analyzes the collected data and generates a summary using a generative artificial intelligence model. The summary is then displayed on the app's user interface, allowing the user to view the information and provide their rating and feedback.

[0510] The system allows users to efficiently obtain personalized election information based on their interests, improves the transparency and understandability of the information provided, and continuously improves the system based on feedback, resulting in higher quality information being provided.

[0511] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0512] System program processing flow

[0513] Step 1:

[0514] The server collects detailed data on candidates via the Internet. Specifically, it uses a web scraping tool (e.g., Python's BeautifulSoup) to extract information such as the candidate's profile, parliamentary activities, and campaign promises from online resources such as the candidate's official website, news articles, and social media. In this process, a list of URLs is given as input, and HTML content is obtained as output.

[0515] Step 2:

[0516] The server inputs the collected data into a generative artificial intelligence model (e.g., ChatGPT). The collected text data is sent to OpenAI's API, which extracts key information about the candidate and generates a summary. This process uses the collected text data as input and produces summarized candidate information as output.

[0517] Step 3:

[0518] The server sends the summarized information to the device. The generated summary information is transferred to the smartphone application via a RESTful API. This allows the information to be displayed on the user's smartphone. The summarized data is passed to the API as input, and the data is provided to the device as output.

[0519] Step 4:

[0520] The terminal displays the summary information to the user through a user interface. The data acquired by the smartphone application is displayed in a visually easy-to-read format for the user. The input of this step is the summary data sent from the server, and the output is an information screen that the user can view.

[0521] Step 5:

[0522] Users can provide feedback on the information provided, such as clarity and understandability of the information, as well as additional questions and comments, via a feedback form. The input is the user's feedback, and the output is the feedback data sent to the server.

[0523] Step 6:

[0524] The server collects the feedback sent by users and stores it in a database. The feedback data is accumulated and used to improve the system. The input is the user feedback data, and the output is the feedback record stored in the database.

[0525] Specific operation example

[0526] For example, to collect information about a particular candidate during an election, the server scrapes the URL of the candidate's official website and obtains HTML data. The HTML data is then input into ChatGPT to generate a summary of the candidate's recent activities. The summary is then sent to the smartphone application via API and displayed on the user interface. The user can then enter a prompt such as "Please summarize the recent activities of candidate XX" and provide feedback based on the information. This feedback is returned to the server and stored in the feedback database.

[0527] 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.

[0528] The present invention relates to a system that combines a data collection means, a data analysis means, an information provision means, a feedback collection means, and an emotion engine that recognizes user emotions, and in particular, is a system for efficiently collecting, analyzing, and providing candidate information and collecting feedback in elections. The following describes an embodiment of the present invention.

[0529] Data collection

[0530] The server collects data such as candidate profiles, parliamentary activities, and campaign promises via the Internet. The server obtains the necessary data from the candidates' official websites, newspaper articles, social media, and other online resources. This data is collected automatically using pre-configured scraping scripts and APIs.

[0531] Data analysis

[0532] The collected data is analyzed by the server using a generative artificial intelligence model (e.g., ChatGPT). The server passes the candidate's profile and activity history as input to the generative artificial intelligence model, and generates summary information as the analysis result. This summary result is provided in a concise and easy-to-understand format.

[0533] Information provision

[0534] The summarized information is provided to the user through a user interface on the device. The server sends the summarized information to the device via an API and displays it on the user interface. Through this interface, the user can view each candidate's detailed profile, parliamentary activities, and campaign promises.

[0535] Feedback collection

[0536] Users can provide feedback on the information provided. The device interface has a feedback input form, where users can rate the clarity and ease of understanding of the information. When a user submits feedback, the device sends the information to the server. The server stores the feedback in a database and uses it to improve the system.

[0537] Use of emotion engine

[0538] The emotion engine recognizes emotions from user input and operations and adjusts the information provided based on those emotions. For example, if a user performs an operation or makes a comment that indicates dissatisfaction while viewing information about a candidate, the emotion engine analyzes that emotion and notifies the server. The server then adjusts the content and format of the information provided based on this information, providing the information in a more appropriate form for the user.

[0539] Specific examples

[0540] For example, if a user wants to research a particular candidate during an election, they access the "Election Navigator" using their device. The server collects detailed data on the candidate and analyzes and summarizes this data using a generative artificial intelligence model. The generated summary is displayed to the user through the device's user interface. If the user is dissatisfied while viewing this summary information, the emotion engine recognizes their emotion and notifies the server. The server adjusts the information it provides based on the information it receives and presents it to the user again. Users can also provide feedback on the clarity and content of the information, which is sent to the server and used to improve the system.

[0541] In this way, the system of the present invention helps voters easily obtain appropriate information and make it easier to choose the right politician. Furthermore, by introducing an emotion engine, it is possible to provide information according to the user's emotions, improving the user experience of the system.

[0542] The processing flow will be explained below.

[0543] Step 1:

[0544] The server prepares a list of target website URLs to collect candidate data, including official candidate websites, news articles, social media accounts, etc.

[0545] Step 2:

[0546] The server sends an HTTP request to each URL in the prepared list to retrieve the web page content, specifically the HTML content, using the requests library.

[0547] Step 3:

[0548] The server parses the retrieved HTML content using BeautifulSoup and extracts necessary information such as candidate profiles, parliamentary activities, campaign promises, etc. The extracted information is converted into a structured format such as JSON.

[0549] Step 4:

[0550] The server stores the structured candidate data in a database, where the storage process involves creating a database entry or updating an existing entry.

[0551] Step 5:

[0552] The server retrieves and analyzes the stored data using a generative artificial intelligence model (e.g., ChatGPT). The server passes the candidate's profile and activity history as input to the generative artificial intelligence model and generates summary information.

[0553] Step 6:

[0554] The server places the generated summary information at an API endpoint configured as an information provider, which is accessed by a user interface.

[0555] Step 7:

[0556] A user accesses a user interface using a terminal and requests specific candidate information, which sends a request to an API endpoint.

[0557] Step 8:

[0558] In response to a request from the terminal, the server acquires summary information of the relevant candidate from the database and transmits the data to the terminal as a response.

[0559] Step 9:

[0560] The terminal displays the received summary information on a user interface, allowing the user to view the information.

[0561] Step 10:

[0562] The user reacts to the displayed candidate information. The device sends the user's comments and input actions to the emotion engine to recognize the user's emotions.

[0563] Step 11:

[0564] The emotion engine recognizes emotions from user input and operations and sends the emotion data to the server. For example, if a user enters a comment expressing dissatisfaction, it will be recognized as a negative emotion.

[0565] Step 12:

[0566] The server receives the emotion data provided by the emotion engine and determines an action based on the emotion. For example, if the user expresses dissatisfaction, the server may provide more detailed information.

[0567] Step 13:

[0568] The user inputs feedback on the provided information. The terminal sends the feedback data to the server as a POST request.

[0569] Step 14:

[0570] The server stores, analyzes, and uses feedback data for future system improvements. This feedback includes ratings of the clarity and understandability of the information.

[0571] This process flow allows the system of the present invention to efficiently collect, analyze, and summarize candidate data, and provide information to voters in an easy-to-understand format. Furthermore, by adjusting the information according to the user's emotions, the system can improve the user experience.

[0572] Example 2

[0573] 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."

[0574] There is a need for systems that allow users to quickly and accurately collect, analyze, and evaluate information in elections and other decision-making processes. However, conventional systems have had difficulty efficiently collecting and analyzing large amounts of data and providing it appropriately to users. They also lacked the ability to adjust information taking into account user feedback and emotions. The purpose of this invention is to solve these problems and provide a system that provides users with accurate information that is easy to understand.

[0575] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0576] In this invention, the server includes a data collection means, a data analysis means, an information provision means, a feedback collection means, an emotion recognition means, and a data adjustment means, which makes it possible to efficiently collect and analyze large amounts of data and to adjust and provide information based on the user's feedback and emotions.

[0577] "Data collection means" refers to a means for collecting target data via the Internet.

[0578] "Data analysis means" refers to means for analyzing collected data using a generative artificial intelligence model.

[0579] The "information providing means" is a means for providing the analyzed information to the user.

[0580] The "feedback collection means" is a means for collecting feedback from users.

[0581] The "emotion recognition means" is a means for recognizing emotions from user inputs and operations.

[0582] The "data adjustment means" is a means for adjusting the content and format of the information to be provided based on the information from the emotion recognition means.

[0583] The present invention is a system that combines data collection means, data analysis means, information provision means, feedback collection means, emotion recognition means, and data adjustment means. This system is designed to efficiently collect, analyze, and provide candidate information and collect feedback, particularly in elections. The detailed configuration and operating procedures for implementing the present invention are described below.

[0584] Hardware and software used

[0585] Hardware: Servers, devices (PCs, smartphones, etc.)

[0586] Software: scraping scripts, APIs, generative AI models (e.g., ChatGPT), sentiment engines, user interfaces, databases

[0587] Data collection

[0588] The server collects data such as candidate profiles, parliamentary activities, and campaign promises from the internet. The server automatically retrieves the necessary data from the candidates' official websites, newspaper articles, social media, and other online resources. This process is performed using pre-configured scraping scripts and APIs.

[0589] Data analysis

[0590] The server passes the collected data to a generative artificial intelligence model (e.g., ChatGPT). The generative artificial intelligence model is used to analyze the collected data and concisely summarize the candidate's information. During this analysis and summarization process, specific prompts (e.g., "Please summarize the candidate's profile") are input to the generative artificial intelligence model. The summarized information is then organized by the server and stored in a database in its final form.

[0591] Information provision

[0592] The server sends the summarized information via an API to the device, which then displays it to the user through a user interface. The user can navigate through this interface to view each candidate's detailed profile, parliamentary activities, and campaign promises.

[0593] Feedback collection

[0594] The device's user interface displays a form for entering feedback. When the user enters their thoughts and suggestions for improvement in the form and submits it, the device sends the feedback information to the server. The server stores the received feedback in a database and uses it later to improve the system.

[0595] Use of emotion engine

[0596] The emotion engine recognizes emotions from user input and operations. For example, if a user becomes dissatisfied while viewing information about a candidate, the emotion engine analyzes that emotion and notifies the server. The server then adjusts the content and format of the information it provides based on this notification. The adjusted information is then sent back to the terminal and redisplayed on the user interface.

[0597] Specific examples

[0598] For example, if a user wants to research a particular candidate during an election, the user accesses the "Election Navigator" app using a device. The server collects detailed data on the candidate and analyzes and summarizes this data using a generative artificial intelligence model. The generated summary is displayed to the user through the device's user interface. If the user is dissatisfied with the summary information, the emotion engine recognizes the user's emotion and notifies the server. The server then adjusts the information provided based on the information received and presents it to the user again. The user also provides feedback on the information's understandability and content, which is sent to the server and used to improve the system. In this way, the system of the present invention helps users easily obtain appropriate information and make appropriate decisions. Furthermore, the introduction of an emotion engine enables the provision of information tailored to the user's emotions, improving the user experience of the system.

[0599] Prompt Sentence Examples

[0600] "Use Election Navigator to find out information about candidates. Please provide detailed data on the candidates."

[0601] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0602] Step 1: Data collection

[0603] The server identifies the source of candidate information by referencing a list of URLs, such as the candidate's official website, newspaper articles, and social media.

[0604] Input: A list of URLs from which data is collected.

[0605] Output: URL to be scraped or API called

[0606] How it works: The server checks the URL list and prepares to collect data.

[0607] Step 2: Performing data collection

[0608] The server runs scraping scripts and APIs to collect data, specifically, it retrieves HTML data from specific web pages and JSON data from API endpoints.

[0609] Input: URL list, scraping script, API settings

[0610] Output: Raw candidate information obtained

[0611] How it works: The server uses configured scripts and APIs to collect data and store it in temporary storage.

[0612] Step 3: Save Data

[0613] The server stores the collected data in a temporary database.

[0614] Input: Raw candidate data collected

[0615] Output: Data stored in a temporary database

[0616] How it works: The server formats the collected data, filters out missing and duplicate data, and stores it in a temporary database.

[0617] Step 4: Prepare for data analysis

[0618] The server reads the collected data from the temporary database and prepares the input for the generative artificial intelligence model.

[0619] Input: Data stored in a temporary database

[0620] Output: Formatted data to feed into a generative artificial intelligence model

[0621] How it works: The server formats the data and passes it to a generative artificial intelligence model with appropriate prompts.

[0622] Step 5: Data analysis

[0623] The server uses a generative artificial intelligence model to analyze the data and summarize the candidate's information, for example using prompts such as "Please summarize the candidate's profile."

[0624] Input: Formatted data, prompt

[0625] Output: Summarized candidate information

[0626] How it works: The server runs a generative artificial intelligence model to obtain summary information that is then organized.

[0627] Step 6: Save summary information

[0628] The server organizes the summary results and stores them in their final form.

[0629] Input: Summary information from a generative artificial intelligence model

[0630] Output: Organized summary information, stored in a database

[0631] How it works: The server organizes the summary information and stores it in a database, filtering out unnecessary information in the process.

[0632] Step 7: Provide information

[0633] The server sends the summarized information to the device via API.

[0634] Input: Organized summary information, API settings

[0635] Output: Result sent to terminal

[0636] How it works: The server sends summary information to the device via the API.

[0637] Step 8: Display information

[0638] The terminal displays the information on a user interface.

[0639] Input: Summary information received from the server

[0640] Output: Information displayed in the user interface

[0641] What it does: The device formats the information and displays it on the user interface.

[0642] Step 9: Enter your feedback

[0643] The user enters feedback on the information provided.

[0644] Input: User actions to view information

[0645] Output: Feedback content

[0646] How it works: The user fills out a feedback form on the interface with their thoughts and ratings.

[0647] Step 10: Send feedback

[0648] The terminal sends feedback information to the server.

[0649] Input: Feedback entered by the user

[0650] Output: Result sent to the server

[0651] Operation: The device sends the feedback content to the server using a communication protocol.

[0652] Step 11: Save your feedback

[0653] The server stores the feedback in a database.

[0654] Input: Feedback sent from the device

[0655] Output: Feedback information stored in a database

[0656] How it works: The server stores the feedback information in a database for later use in improving the system.

[0657] Step 12: Sentiment Analysis

[0658] The emotion engine analyzes user input and operations.

[0659] Input: User operation history and comment content

[0660] Output: Emotion analysis results

[0661] How it works: The emotion engine performs real-time analysis and notifies the emotional state to the server.

[0662] Step 13: Information Reconciliation

[0663] The server adjusts the information based on the results of emotion analysis.

[0664] Input: Analysis results from the emotion engine

[0665] Output: Adjusted information

[0666] Operation: Adjusts the content and format of the information provided by the server and sends it back to the device.

[0667] Step 14: Redisplay

[0668] The re-adjusted information is sent to the terminal and displayed again on the interface.

[0669] Input: Adjusted information

[0670] Output: Information redisplayed in the user interface

[0671] How it works: The server sends the adjusted information to the device, which displays it on its user interface.

[0672] (Application example 2)

[0673] 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."

[0674] In physical stores, it is difficult for customers to quickly obtain appropriate product information based on their preferences and past purchase history. Furthermore, the information provided cannot be adjusted in real time based on the customer's emotions and reactions, which means that the customer experience is not fully improved. This makes it difficult to improve customer satisfaction and stimulate purchasing motivation.

[0675] 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.

[0676] In this invention, the server includes a data collection means, a data analysis means, an information provision means, a feedback collection means, an emotion recognition means, a means for acquiring customer profile data, a means for providing product information based on customer preferences, and a means for providing summary information, thereby making it possible to provide appropriate product information based on the customer's past purchase history and preferences, and to adjust information according to the customer's emotions.

[0677] "Data collection means" refers to a function that acquires information such as customer profile data, purchase history, and preferences via the Internet at physical stores.

[0678] "Data analysis means" is a function that analyzes collected data using a generative artificial intelligence model to generate summaries of customer-based information.

[0679] The "information provision means" is a function that presents appropriate product information and summaries through a user interface for providing the analyzed results to customers.

[0680] The "feedback collection means" is a function that collects feedback from users and transmits it to the server.

[0681] "Emotion recognition means" is a function that recognizes emotions from customer input and operations and adjusts the information provided in real time based on those emotions.

[0682] "Means for obtaining customer profile data" refers to a function for collecting customers' past purchase history, preferences, and other related information via the Internet.

[0683] The "means for providing product information based on customer preferences" is a function that provides optimal product information to customers based on collected customer data.

[0684] The "means for providing summary information" is a function that provides summary information analyzed by a generative artificial intelligence model to customers in an easy-to-understand manner.

[0685] The system for implementing this invention mainly consists of three elements: a server, a terminal, and a user. The server has a data collection means, a data analysis means, an information provision means, a feedback collection means, and an emotion recognition means, while the terminal provides an interface for providing information and collecting feedback. The user also uses the terminal to access the system to obtain information and send feedback.

[0686] Data collection via the internet

[0687] The server first collects customer profile data from various online resources, a process automated using predefined scraping scripts and APIs, including information about past purchases and preferences.

[0688] Data analysis

[0689] The collected data is then analyzed using a generative artificial intelligence model (e.g., ChatGPT). The server inputs the customer's profile and past purchase history into the model, and generates summary information as the analysis result. This summary information is presented in a concise and easy-to-understand format.

[0690] Examples of prompt statements

[0691] For example, provide the following prompt to a generative AI model:

[0692] Purchase history: 'Tea, Coffee, Mineral Water'

[0693] Preferences: 'Healthy food, I like organic products'

[0694] Information provision

[0695] The summarized information is provided to the user through a user interface on the device. The server sends the summarized information to the device via an API, and the device displays it on the user interface. The user can view detailed product information and recommended products through this interface.

[0696] Feedback collection

[0697] Users can provide feedback on the information provided. A feedback input form is provided in the device interface. Users rate the information on its clarity and understandability, and the device sends this to the server. The server stores the feedback in a database and uses it to improve the system.

[0698] emotion recognition

[0699] The emotion engine recognizes emotions from user operations and inputs and adjusts the information provided based on those emotions. For example, if a user makes a comment expressing uncertainty while browsing product information, the emotion engine analyzes this and notifies the server. The server then adjusts the content and format of the information provided based on this information and presents it to the user again.

[0700] For example, if a user enters a comment such as "I want to see the ingredients list for this product," the emotion engine will interpret this as an indication of interest and display additional detailed information such as "All of the ingredients in this product are organic and additive-free." In this way, information can be provided that reflects the customer's emotions, improving the user experience.

[0701] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0702] Step 1:

[0703] The server collects customer profile data via the internet. The input includes customer ID, interest categories, etc. These data are collected using predefined scraping scripts or APIs. As output, customer profile data (purchase history, preferences, etc.) is obtained and stored in a database.

[0704] Step 2:

[0705] The server extracts the collected customer data and passes it to a generative artificial intelligence model (such as ChatGPT) for analysis. The input is the customer's past purchase history and preferences, which are provided as prompts. Summary information (e.g., a list of products recommended to the customer and their overview) is generated as output.

[0706] Step 3:

[0707] The server sends the summarized information to the terminal. As input, it contains the generated summarized information. As output, the summarized information is sent to the terminal through the API. The terminal prepares this information to be displayed on the user interface.

[0708] Step 4:

[0709] The terminal displays the provided summary information to the user through a user interface, which includes the summary information sent from the server as input, and displays the information on the terminal screen in a form that can be viewed by the user as output.

[0710] Step 5:

[0711] The user inputs feedback about the displayed information. The input includes the user's feedback comments and ratings. The output is sent from the terminal to the server.

[0712] Step 6:

[0713] The server stores the feedback sent by the user in a database. The input includes the feedback information. The output is the feedback stored and data for system improvement is accumulated based on the feedback.

[0714] Step 7:

[0715] The device or server recognizes emotions from the user's actions and comments. The input includes the user's actions and comments. The processing involves analysis using an emotion analysis engine (such as NVIDIA NeMo). The output is a result based on the user's emotions.

[0716] Step 8:

[0717] The server adjusts the information provided based on the emotion analysis results. The emotion analysis results are included as input. The adjusted information is generated as output and sent back to the device. The device then redisplays the adjusted information, improving the user experience.

[0718] 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.

[0719] 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.

[0720] 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.

[0721] [Third embodiment]

[0722] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0723] 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.

[0724] 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).

[0725] 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.

[0726] 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.

[0727] 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).

[0728] 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.

[0729] 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.

[0730] 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.

[0731] 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.

[0732] 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.

[0733] 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."

[0734] The present invention relates to a system having a data collection means, a data analysis means, an information provision means, and a feedback collection means, and in particular to a system for efficiently collecting, analyzing, and providing candidate information and collecting feedback in an election.

[0735] Data collection

[0736] The server collects data such as candidate profiles, parliamentary activities, and campaign promises via the Internet. Specifically, the server obtains data from candidates' official websites, newspaper articles, social media, and other online resources. This data is collected automatically using pre-configured scraping scripts.

[0737] Data analysis

[0738] The collected data is analyzed by the server using a generative artificial intelligence model (e.g., ChatGPT). The server inputs the candidate's profile and activity history and uses the generative artificial intelligence model to summarize this information. The summary results are presented in a concise and easy-to-understand format and passed to the information provider.

[0739] Providing information

[0740] The summarized information is provided to the user through a user interface on the device. The server sends the summarized candidate information to the device via an API and displays it on the user interface. Through this interface, the user can easily view each candidate's detailed profile, parliamentary activities, and campaign promises.

[0741] Feedback collection

[0742] Users can provide feedback on the information provided. The device interface includes a feedback input form, allowing users to rate the clarity and ease of understanding of the information. When a user submits feedback, the device sends the information to the server, which stores the feedback in a database and uses it to improve the system.

[0743] Specific examples

[0744] For example, if a user wants to research a particular candidate on the Internet during an election period, the user accesses "Election Navigator" through their device. The server collects detailed data on the candidate, analyzes the collected data using a generative artificial intelligence model, and generates a summary. The generated summary is displayed to the user through a user interface. The user views the information and enters feedback about the content. The feedback is sent to the server and used to improve the system.

[0745] In this way, the system of the present invention helps voters easily obtain appropriate information and choose appropriate politicians, thereby improving the transparency of elections and contributing to promoting political participation.

[0746] The processing flow will be explained below.

[0747] Step 1:

[0748] A server prepares a list of target website URLs for collecting candidate data.

[0749] Step 2:

[0750] The server sends an HTTP request to each URL in the prepared list to retrieve the web page content. Specifically, it retrieves the HTML content using the requests library or similar.

[0751] Step 3:

[0752] The server parses the retrieved HTML content using libraries such as BeautifulSoup to extract necessary information such as the candidate's profile, parliamentary activities, campaign promises, etc. The extracted information is then converted into a structured format.

[0753] Step 4:

[0754] The server stores the structured candidate data in a temporary storage area or database, for example using a json format or database entry structure for this storage process.

[0755] Step 5:

[0756] The server uses a generative artificial intelligence model (e.g., ChatGPT) to select and retrieve stored candidate data, then formats the retrieved data as analytical input.

[0757] Step 6:

[0758] The server then inputs the formatted data into a generative artificial intelligence model to generate a summary of the candidate information, which is then converted into a concise, easy-to-understand format.

[0759] Step 7:

[0760] The server places the generated abstract data into an API endpoint configured as an information provider, which is then accessed by the user interface.

[0761] Step 8:

[0762] A user accesses a user interface using a terminal and requests specific candidate information, which sends a request to an API endpoint.

[0763] Step 9:

[0764] In response to a request from the terminal, the server acquires summary data of the relevant candidate from the database and transmits the data to the terminal as a response.

[0765] Step 10:

[0766] The terminal displays the received summary data on a user interface, allowing the user to view the information.

[0767] Step 11:

[0768] The user enters feedback on the candidate information provided, including an assessment of the clarity and understandability of the information.

[0769] Step 12:

[0770] The terminal transmits the feedback input by the user to the server as a POST request.

[0771] Step 13:

[0772] The server stores the received feedback data and analyzes and uses it for future system improvements.

[0773] This process flow allows the system to efficiently collect, analyze, and summarize candidate data, providing the information to voters in an easy-to-understand format, and collecting user feedback to help continuously improve the system.

[0774] Example 1

[0775] 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."

[0776] In elections, it is difficult for voters to quickly and accurately obtain information about candidates and make appropriate decisions based on that information. In particular, it is difficult to efficiently collect the vast amount of information scattered across the Internet and provide it in an easy-to-understand format. In addition to providing information, there are also insufficient means to collect feedback from voters and use it to improve the system.

[0777] 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.

[0778] In this invention, the server includes a data collection means, a data analysis means, an information provision means, and a feedback collection means, which enable the server to collect candidate data via the Internet, analyze and summarize the data using a generative artificial intelligence model, provide information through a user interface, and collect user feedback to use in improving the system.

[0779] "Data collection means" refers to devices or methods that automatically collect data such as candidate profiles, parliamentary activities, and campaign promises via the Internet.

[0780] "Data analysis means" refers to a device or method that analyzes collected data and summarizes it into meaningful information. In particular, it includes means that do this automatically and efficiently by using a generative artificial intelligence model.

[0781] The "information providing means" refers to a device or method that provides the analyzed data to the user through a user interface, thereby allowing the user to easily refer to information about the candidate.

[0782] "Feedback collection means" refers to a device or method that collects feedback from users, stores that information in a database, and uses it to improve the system.

[0783] A "generative artificial intelligence model" is an artificial intelligence algorithm that has the ability to generate new information based on given input data. For example, ChatGPT is an example of this.

[0784] A "user interface" is an interface that allows a user to operate a system or view information.

[0785] "Candidate data" refers to various information about candidates running in elections, including their profiles, parliamentary activities, and campaign promises.

[0786] The present invention is a system that collects and analyzes candidate information via the Internet, provides the results through a user interface, and collects feedback from users to help improve the system. Specific embodiments of the present invention are described below.

[0787] Data collection

[0788] The server connects to the Internet and collects data such as candidate profiles, parliamentary activities, and campaign promises from official candidate websites, newspaper articles, social media, etc. Web scraping tools such as Scrapy and BeautifulSoup are used to collect the data. The server uses these tools to automatically collect data based on the configured scraping script.

[0789] Data analysis

[0790] The server inputs the collected data into a generative artificial intelligence model (such as ChatGPT) for analysis. The server inputs the candidate's profile and activity history and uses ChatGPT to summarize this information. The summary results are generated in a concise and easy-to-understand format. OpenAI's API is used for data analysis.

[0791] Information provision

[0792] The server sends the analyzed and summarized candidate information to the device via API. The device displays the received information on the user interface. Through the device interface, users can easily view detailed candidate profiles, parliamentary activities, campaign promises, etc.

[0793] Feedback collection

[0794] Users enter feedback on the information provided. The device interface has a feedback input form, allowing users to rate the clarity and understandability of the information. When users submit feedback, the device sends the information to the server, which stores the feedback in a database. The collected feedback is used to improve the system.

[0795] Specific examples

[0796] For example, if a user wants to research a particular candidate during an election period, the user accesses the election navigation system through their device. The server collects detailed data on the candidate, analyzes and summarizes the data using a generative artificial intelligence model (ChatGPT), and generates a summary. The summary is then displayed to the user through a user interface. The user then browses the information and enters feedback about the content. The feedback is sent from the device to the server and used to improve the system.

[0797] Example prompt sentence:

[0798] "Analyze and summarize the profiles of the following candidates and their congressional activities to date.

[0799] Candidate Name: Taro Yamada

[0800] profile: ...

[0801] Parliamentary Activities: ...

[0802] Summary results:

[0803] "

[0804] As described above, the system of the present invention can efficiently collect, analyze, and provide candidate information and gather feedback in elections, helping voters easily obtain appropriate information and make appropriate decisions. This system will improve the transparency of elections and contribute to promoting political participation.

[0805] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0806] Step 1:

[0807] The server connects to the internet to collect candidate information. It runs a configured scraping script to collect data such as candidate profiles, parliamentary activities, and campaign promises from official websites, newspaper articles, social media, etc. It uses URLs and search queries as input and obtains a dataset of collected candidate information as output. This dataset is then stored in a database.

[0808] Specific working example:

[0809] The server uses Scrapy or BeautifulSoup to parse the content of the web page and extract the necessary data.

[0810] Step 2:

[0811] The server generates prompts to input the collected candidate data into the generative artificial intelligence model. The prompts include the candidate's name, profile, and parliamentary activities. The candidate data is used as input, and the prompts are generated as output.

[0812] Specific working example:

[0813] The server uses the OpenAI API to pass files to the generative artificial intelligence model.

[0814] Step 3:

[0815] The server inputs the prompt sentence into a generative AI model for analysis. Using a generative AI model such as ChatGPT, the server summarizes the candidate's information. The prompt sentence is used as input, and the summarized information is obtained as output. This summary information is stored in a database.

[0816] Specific working example:

[0817] The server passes the prompt to the OpenAI API and saves the resulting summary in text format.

[0818] Step 4:

[0819] The server sends the summarized candidate information to the terminal through the API. The terminal displays the received information on the user interface. The summarized information is used as input, and the information sent to the terminal is obtained as output.

[0820] Specific working example:

[0821] The server uses a framework (e.g., Flask or Django) to provide an API and send information to the device.

[0822] Step 5:

[0823] The user views the candidate information through the user interface of the terminal. The summarized candidate information is used as input, and the user's act of viewing the information is obtained as output.

[0824] Specific working example:

[0825] The device uses front-end frameworks such as React and Vue.js to build the interface and display information.

[0826] Step 6:

[0827] The user enters feedback on the provided information. The terminal interface has a feedback input form, allowing the user to rate the clarity and understandability of the information. The user's feedback is used as input, and feedback information is obtained as output.

[0828] Specific working example:

[0829] The user enters their feedback into a form in the interface and clicks the submit button.

[0830] Step 7:

[0831] The terminal sends the user's feedback to the server, and the feedback information is used as input, and the feedback sent to the server is obtained as output.

[0832] Specific working example:

[0833] The device uses AJAX requests to send feedback to the server asynchronously.

[0834] Step 8:

[0835] The server stores the received feedback in a database and uses it to improve the system. Feedback information is used as input, and feedback data for system improvement is obtained as output.

[0836] Specific working example:

[0837] The server stores the feedback information in a database and uses it for analysis.

[0838] (Application example 1)

[0839] 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."

[0840] In modern society, election information is extremely diverse, making it difficult to easily gather and understand detailed information such as candidate profiles, parliamentary activities, and campaign promises. Furthermore, the means by which voters can obtain information based on their own interests are limited, making it necessary to improve the transparency of election information and promote political participation.

[0841] 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.

[0842] In this invention, the server includes a data collection means, a data analysis means, an information provision means, a feedback collection means, a means for generating and providing summary information based on the user's interests using the collected data, and a means for the user to input feedback on the summary information provided. This allows the user to easily and efficiently obtain detailed information about candidates and obtain information personalized based on their own interests. Furthermore, the system is improved based on the feedback, increasing the transparency and ease of understanding of the information.

[0843] A "data collection means" is a device or program means that automatically collects data such as candidate profiles, parliamentary activities, and campaign promises via the Internet.

[0844] "Data analysis means" means a device or program means that analyzes collected data using a generative artificial intelligence model and extracts and summarizes important information.

[0845] "Information providing means" refers to a device or program means for providing summarized information to a user through a user interface.

[0846] The "feedback collection means" is a device or program means that allows a user to input feedback on the provided information and collects that feedback.

[0847] The "means for generating and providing summary information according to the user's interests" refers to a device or program means that analyzes collected data, generates personalized summary information based on the user's interests, and provides it to the user.

[0848] The "means for a user to input feedback on the provided summary information" refers to a device or program means by which a user inputs an evaluation or opinion on the provided summary information and transmits the information to the system.

[0849] The system for implementing the present invention has the following means, thereby enabling efficient collection, analysis, provision and feedback collection of election information.

[0850] Data collection

[0851] The server collects data such as candidate profiles, parliamentary activities, and campaign promises via the Internet. Specifically, the server uses a web scraping tool to automatically collect data from candidate official websites, news articles, social media, and other online resources. The hardware used is a standard server machine, and the software used is Python and BeautifulSoup.

[0852] Data analysis

[0853] The collected data is analyzed by the server using a generative AI model (e.g., ChatGPT). The server inputs the candidate's profile and activity history into the generative AI model and summarizes this information. This summary result is generated in a concise and easy-to-understand format. The hardware is a similarly standard server machine, and the software uses OpenAI's API.

[0854] Information provision

[0855] The summarized information is sent from the server to the device and provided to the user through a user interface. The information is sent via an API and displayed in an application on the device. Users can easily view detailed profiles, activities, and campaign promises of candidates through the smartphone application.

[0856] Feedback collection

[0857] Users can provide feedback on the information provided. The device interface includes a feedback input form, allowing users to rate the clarity and understandability of the information. The feedback is sent from the device to the server, which stores the collected feedback in a database and uses it to improve the system.

[0858] Specific examples

[0859] For example, if a user wants more information about a particular candidate during an election, they can open a smartphone app and see a prompt such as, "Please summarize the recent activities of candidate XX." The server analyzes the collected data and generates a summary using a generative artificial intelligence model. The summary is then displayed on the app's user interface, allowing the user to view the information and provide their rating and feedback.

[0860] The system allows users to efficiently obtain personalized election information based on their interests, improves the transparency and understandability of the information provided, and continuously improves the system based on feedback, resulting in higher quality information being provided.

[0861] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0862] System program processing flow

[0863] Step 1:

[0864] The server collects detailed data on candidates via the Internet. Specifically, it uses a web scraping tool (e.g., Python's BeautifulSoup) to extract information such as the candidate's profile, parliamentary activities, and campaign promises from online resources such as the candidate's official website, news articles, and social media. In this process, a list of URLs is given as input, and HTML content is obtained as output.

[0865] Step 2:

[0866] The server inputs the collected data into a generative artificial intelligence model (e.g., ChatGPT). The collected text data is sent to OpenAI's API, which extracts key information about the candidate and generates a summary. This process uses the collected text data as input and produces summarized candidate information as output.

[0867] Step 3:

[0868] The server sends the summarized information to the device. The generated summary information is transferred to the smartphone application via a RESTful API. This allows the information to be displayed on the user's smartphone. The summarized data is passed to the API as input, and the data is provided to the device as output.

[0869] Step 4:

[0870] The terminal displays the summary information to the user through a user interface. The data acquired by the smartphone application is displayed in a visually easy-to-read format for the user. The input of this step is the summary data sent from the server, and the output is an information screen that the user can view.

[0871] Step 5:

[0872] Users can provide feedback on the information provided, such as clarity and understandability of the information, as well as additional questions and comments, via a feedback form. The input is the user's feedback, and the output is the feedback data sent to the server.

[0873] Step 6:

[0874] The server collects the feedback sent by users and stores it in a database. The feedback data is accumulated and used to improve the system. The input is the user feedback data, and the output is the feedback record stored in the database.

[0875] Specific operation example

[0876] For example, to collect information about a particular candidate during an election, the server scrapes the URL of the candidate's official website and obtains HTML data. The HTML data is then input into ChatGPT to generate a summary of the candidate's recent activities. The summary is then sent to the smartphone application via API and displayed on the user interface. The user can then enter a prompt such as "Please summarize the recent activities of candidate XX" and provide feedback based on the information. This feedback is returned to the server and stored in the feedback database.

[0877] 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.

[0878] The present invention relates to a system that combines a data collection means, a data analysis means, an information provision means, a feedback collection means, and an emotion engine that recognizes user emotions, and in particular, is a system for efficiently collecting, analyzing, and providing candidate information and collecting feedback in elections. The following describes an embodiment of the present invention.

[0879] Data collection

[0880] The server collects data such as candidate profiles, parliamentary activities, and campaign promises via the Internet. The server obtains the necessary data from the candidates' official websites, newspaper articles, social media, and other online resources. This data is collected automatically using pre-configured scraping scripts and APIs.

[0881] Data analysis

[0882] The collected data is analyzed by the server using a generative artificial intelligence model (e.g., ChatGPT). The server passes the candidate's profile and activity history as input to the generative artificial intelligence model, and generates summary information as the analysis result. This summary result is provided in a concise and easy-to-understand format.

[0883] Information provision

[0884] The summarized information is provided to the user through a user interface on the device. The server sends the summarized information to the device via an API and displays it on the user interface. Through this interface, the user can view each candidate's detailed profile, parliamentary activities, and campaign promises.

[0885] Feedback collection

[0886] Users can provide feedback on the information provided. The device interface has a feedback input form, where users can rate the clarity and ease of understanding of the information. When a user submits feedback, the device sends the information to the server. The server stores the feedback in a database and uses it to improve the system.

[0887] Use of emotion engine

[0888] The emotion engine recognizes emotions from user input and operations and adjusts the information provided based on those emotions. For example, if a user performs an operation or makes a comment that indicates dissatisfaction while viewing information about a candidate, the emotion engine analyzes that emotion and notifies the server. The server then adjusts the content and format of the information provided based on this information, providing the information in a more appropriate form for the user.

[0889] Specific examples

[0890] For example, if a user wants to research a particular candidate during an election, they access the "Election Navigator" using their device. The server collects detailed data on the candidate and analyzes and summarizes this data using a generative artificial intelligence model. The generated summary is displayed to the user through the device's user interface. If the user is dissatisfied while viewing this summary information, the emotion engine recognizes their emotion and notifies the server. The server adjusts the information it provides based on the information it receives and presents it to the user again. Users can also provide feedback on the clarity and content of the information, which is sent to the server and used to improve the system.

[0891] In this way, the system of the present invention helps voters easily obtain appropriate information and make it easier to choose the right politician. Furthermore, by introducing an emotion engine, it is possible to provide information according to the user's emotions, improving the user experience of the system.

[0892] The processing flow will be explained below.

[0893] Step 1:

[0894] The server prepares a list of target website URLs to collect candidate data, including official candidate websites, news articles, social media accounts, etc.

[0895] Step 2:

[0896] The server sends an HTTP request to each URL in the prepared list to retrieve the web page content, specifically the HTML content, using the requests library.

[0897] Step 3:

[0898] The server parses the retrieved HTML content using BeautifulSoup and extracts necessary information such as candidate profiles, parliamentary activities, campaign promises, etc. The extracted information is converted into a structured format such as JSON.

[0899] Step 4:

[0900] The server stores the structured candidate data in a database, where the storage process involves creating a database entry or updating an existing entry.

[0901] Step 5:

[0902] The server retrieves and analyzes the stored data using a generative artificial intelligence model (e.g., ChatGPT). The server passes the candidate's profile and activity history as input to the generative artificial intelligence model and generates summary information.

[0903] Step 6:

[0904] The server places the generated summary information at an API endpoint configured as an information provider, which is accessed by a user interface.

[0905] Step 7:

[0906] A user accesses a user interface using a terminal and requests specific candidate information, which sends a request to an API endpoint.

[0907] Step 8:

[0908] In response to a request from the terminal, the server acquires summary information of the relevant candidate from the database and transmits the data to the terminal as a response.

[0909] Step 9:

[0910] The terminal displays the received summary information on a user interface, allowing the user to view the information.

[0911] Step 10:

[0912] The user reacts to the displayed candidate information. The device sends the user's comments and input actions to the emotion engine to recognize the user's emotions.

[0913] Step 11:

[0914] The emotion engine recognizes emotions from user input and operations and sends the emotion data to the server. For example, if a user enters a comment expressing dissatisfaction, it will be recognized as a negative emotion.

[0915] Step 12:

[0916] The server receives the emotion data provided by the emotion engine and determines an action based on the emotion. For example, if the user expresses dissatisfaction, the server may provide more detailed information.

[0917] Step 13:

[0918] The user inputs feedback on the provided information. The terminal sends the feedback data to the server as a POST request.

[0919] Step 14:

[0920] The server stores, analyzes, and uses feedback data for future system improvements. This feedback includes ratings of the clarity and understandability of the information.

[0921] This process flow allows the system of the present invention to efficiently collect, analyze, and summarize candidate data, and provide information to voters in an easy-to-understand format. Furthermore, by adjusting the information according to the user's emotions, the system can improve the user experience.

[0922] Example 2

[0923] 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."

[0924] There is a need for systems that allow users to quickly and accurately collect, analyze, and evaluate information in elections and other decision-making processes. However, conventional systems have had difficulty efficiently collecting and analyzing large amounts of data and providing it appropriately to users. They also lacked the ability to adjust information taking into account user feedback and emotions. The purpose of this invention is to solve these problems and provide a system that provides users with accurate information that is easy to understand.

[0925] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0926] In this invention, the server includes a data collection means, a data analysis means, an information provision means, a feedback collection means, an emotion recognition means, and a data adjustment means, which makes it possible to efficiently collect and analyze large amounts of data and to adjust and provide information based on the user's feedback and emotions.

[0927] "Data collection means" refers to a means for collecting target data via the Internet.

[0928] "Data analysis means" refers to means for analyzing collected data using a generative artificial intelligence model.

[0929] The "information providing means" is a means for providing the analyzed information to the user.

[0930] The "feedback collection means" is a means for collecting feedback from users.

[0931] The "emotion recognition means" is a means for recognizing emotions from user inputs and operations.

[0932] The "data adjustment means" is a means for adjusting the content and format of the information to be provided based on the information from the emotion recognition means.

[0933] The present invention is a system that combines data collection means, data analysis means, information provision means, feedback collection means, emotion recognition means, and data adjustment means. This system is designed to efficiently collect, analyze, and provide candidate information and collect feedback, particularly in elections. The detailed configuration and operating procedures for implementing the present invention are described below.

[0934] Hardware and software used

[0935] Hardware: Servers, devices (PCs, smartphones, etc.)

[0936] Software: scraping scripts, APIs, generative AI models (e.g., ChatGPT), sentiment engines, user interfaces, databases

[0937] Data collection

[0938] The server collects data such as candidate profiles, parliamentary activities, and campaign promises from the internet. The server automatically retrieves the necessary data from the candidates' official websites, newspaper articles, social media, and other online resources. This process is performed using pre-configured scraping scripts and APIs.

[0939] Data analysis

[0940] The server passes the collected data to a generative artificial intelligence model (e.g., ChatGPT). The generative artificial intelligence model is used to analyze the collected data and concisely summarize the candidate's information. During this analysis and summarization process, specific prompts (e.g., "Please summarize the candidate's profile") are input to the generative artificial intelligence model. The summarized information is then organized by the server and stored in a database in its final form.

[0941] Information provision

[0942] The server sends the summarized information via an API to the device, which then displays it to the user through a user interface. The user can navigate through this interface to view each candidate's detailed profile, parliamentary activities, and campaign promises.

[0943] Feedback collection

[0944] The device's user interface displays a form for entering feedback. When the user enters their thoughts and suggestions for improvement in the form and submits it, the device sends the feedback information to the server. The server stores the received feedback in a database and uses it later to improve the system.

[0945] Use of emotion engine

[0946] The emotion engine recognizes emotions from user input and operations. For example, if a user becomes dissatisfied while viewing information about a candidate, the emotion engine analyzes that emotion and notifies the server. The server then adjusts the content and format of the information it provides based on this notification. The adjusted information is then sent back to the terminal and redisplayed on the user interface.

[0947] Specific examples

[0948] For example, if a user wants to research a particular candidate during an election, the user accesses the "Election Navigator" app using a device. The server collects detailed data on the candidate and analyzes and summarizes this data using a generative artificial intelligence model. The generated summary is displayed to the user through the device's user interface. If the user is dissatisfied with the summary information, the emotion engine recognizes the user's emotion and notifies the server. The server then adjusts the information provided based on the information received and presents it to the user again. The user also provides feedback on the information's understandability and content, which is sent to the server and used to improve the system. In this way, the system of the present invention helps users easily obtain appropriate information and make appropriate decisions. Furthermore, the introduction of an emotion engine enables the provision of information tailored to the user's emotions, improving the user experience of the system.

[0949] Prompt Sentence Examples

[0950] "Use Election Navigator to find out information about candidates. Please provide detailed data on the candidates."

[0951] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0952] Step 1: Data collection

[0953] The server identifies the source of candidate information by referencing a list of URLs, such as the candidate's official website, newspaper articles, and social media.

[0954] Input: A list of URLs from which data is collected.

[0955] Output: URL to be scraped or API called

[0956] How it works: The server checks the URL list and prepares to collect data.

[0957] Step 2: Performing data collection

[0958] The server runs scraping scripts and APIs to collect data, specifically, it retrieves HTML data from specific web pages and JSON data from API endpoints.

[0959] Input: URL list, scraping script, API settings

[0960] Output: Raw candidate information obtained

[0961] How it works: The server uses configured scripts and APIs to collect data and store it in temporary storage.

[0962] Step 3: Save Data

[0963] The server stores the collected data in a temporary database.

[0964] Input: Raw candidate data collected

[0965] Output: Data stored in a temporary database

[0966] How it works: The server formats the collected data, filters out missing and duplicate data, and stores it in a temporary database.

[0967] Step 4: Prepare for data analysis

[0968] The server reads the collected data from the temporary database and prepares the input for the generative artificial intelligence model.

[0969] Input: Data stored in a temporary database

[0970] Output: Formatted data to feed into a generative artificial intelligence model

[0971] How it works: The server formats the data and passes it to a generative artificial intelligence model with appropriate prompts.

[0972] Step 5: Data analysis

[0973] The server uses a generative artificial intelligence model to analyze the data and summarize the candidate's information, for example using prompts such as "Please summarize the candidate's profile."

[0974] Input: Formatted data, prompt

[0975] Output: Summarized candidate information

[0976] How it works: The server runs a generative artificial intelligence model to obtain summary information that is then organized.

[0977] Step 6: Save summary information

[0978] The server organizes the summary results and stores them in their final form.

[0979] Input: Summary information from a generative artificial intelligence model

[0980] Output: Organized summary information, stored in a database

[0981] How it works: The server organizes the summary information and stores it in a database, filtering out unnecessary information in the process.

[0982] Step 7: Provide information

[0983] The server sends the summarized information to the device via API.

[0984] Input: Organized summary information, API settings

[0985] Output: Result sent to terminal

[0986] How it works: The server sends summary information to the device via the API.

[0987] Step 8: Display information

[0988] The terminal displays the information on a user interface.

[0989] Input: Summary information received from the server

[0990] Output: Information displayed in the user interface

[0991] What it does: The device formats the information and displays it on the user interface.

[0992] Step 9: Enter your feedback

[0993] The user enters feedback on the information provided.

[0994] Input: User actions to view information

[0995] Output: Feedback content

[0996] How it works: The user fills out a feedback form on the interface with their thoughts and ratings.

[0997] Step 10: Send feedback

[0998] The terminal sends feedback information to the server.

[0999] Input: Feedback entered by the user

[1000] Output: Result sent to the server

[1001] Operation: The device sends the feedback content to the server using a communication protocol.

[1002] Step 11: Save your feedback

[1003] The server stores the feedback in a database.

[1004] Input: Feedback sent from the device

[1005] Output: Feedback information stored in a database

[1006] How it works: The server stores the feedback information in a database for later use in improving the system.

[1007] Step 12: Sentiment Analysis

[1008] The emotion engine analyzes user input and operations.

[1009] Input: User operation history and comment content

[1010] Output: Emotion analysis results

[1011] How it works: The emotion engine performs real-time analysis and notifies the emotional state to the server.

[1012] Step 13: Information Reconciliation

[1013] The server adjusts the information based on the results of emotion analysis.

[1014] Input: Analysis results from the emotion engine

[1015] Output: Adjusted information

[1016] Operation: Adjusts the content and format of the information provided by the server and sends it back to the device.

[1017] Step 14: Redisplay

[1018] The re-adjusted information is sent to the terminal and displayed again on the interface.

[1019] Input: Adjusted information

[1020] Output: Information redisplayed in the user interface

[1021] How it works: The server sends the adjusted information to the device, which displays it on its user interface.

[1022] (Application example 2)

[1023] 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."

[1024] In physical stores, it is difficult for customers to quickly obtain appropriate product information based on their preferences and past purchase history. Furthermore, the information provided cannot be adjusted in real time based on the customer's emotions and reactions, which means that the customer experience is not fully improved. This makes it difficult to improve customer satisfaction and stimulate purchasing motivation.

[1025] 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.

[1026] In this invention, the server includes a data collection means, a data analysis means, an information provision means, a feedback collection means, an emotion recognition means, a means for acquiring customer profile data, a means for providing product information based on customer preferences, and a means for providing summary information, thereby making it possible to provide appropriate product information based on the customer's past purchase history and preferences, and to adjust information according to the customer's emotions.

[1027] "Data collection means" refers to a function that acquires information such as customer profile data, purchase history, and preferences via the Internet at physical stores.

[1028] "Data analysis means" is a function that analyzes collected data using a generative artificial intelligence model to generate summaries of customer-based information.

[1029] The "information provision means" is a function that presents appropriate product information and summaries through a user interface for providing the analyzed results to customers.

[1030] The "feedback collection means" is a function that collects feedback from users and transmits it to the server.

[1031] "Emotion recognition means" is a function that recognizes emotions from customer input and operations and adjusts the information provided in real time based on those emotions.

[1032] "Means for obtaining customer profile data" refers to a function for collecting customers' past purchase history, preferences, and other related information via the Internet.

[1033] The "means for providing product information based on customer preferences" is a function that provides optimal product information to customers based on collected customer data.

[1034] The "means for providing summary information" is a function that provides summary information analyzed by a generative artificial intelligence model to customers in an easy-to-understand manner.

[1035] The system for implementing this invention mainly consists of three elements: a server, a terminal, and a user. The server has a data collection means, a data analysis means, an information provision means, a feedback collection means, and an emotion recognition means, while the terminal provides an interface for providing information and collecting feedback. The user also uses the terminal to access the system to obtain information and send feedback.

[1036] Data collection via the internet

[1037] The server first collects customer profile data from various online resources, a process automated using predefined scraping scripts and APIs, including information about past purchases and preferences.

[1038] Data analysis

[1039] The collected data is then analyzed using a generative artificial intelligence model (e.g., ChatGPT). The server inputs the customer's profile and past purchase history into the model, and generates summary information as the analysis result. This summary information is presented in a concise and easy-to-understand format.

[1040] Examples of prompt statements

[1041] For example, provide the following prompt to a generative AI model:

[1042] Purchase history: 'Tea, Coffee, Mineral Water'

[1043] Preferences: 'Healthy food, I like organic products'

[1044] Information provision

[1045] The summarized information is provided to the user through a user interface on the device. The server sends the summarized information to the device via an API, and the device displays it on the user interface. The user can view detailed product information and recommended products through this interface.

[1046] Feedback collection

[1047] Users can provide feedback on the information provided. A feedback input form is provided in the device interface. Users rate the information on its clarity and understandability, and the device sends this to the server. The server stores the feedback in a database and uses it to improve the system.

[1048] emotion recognition

[1049] The emotion engine recognizes emotions from user operations and inputs and adjusts the information provided based on those emotions. For example, if a user makes a comment expressing uncertainty while browsing product information, the emotion engine analyzes this and notifies the server. The server then adjusts the content and format of the information provided based on this information and presents it to the user again.

[1050] For example, if a user enters a comment such as "I want to see the ingredients list for this product," the emotion engine will interpret this as an indication of interest and display additional detailed information such as "All of the ingredients in this product are organic and additive-free." In this way, information can be provided that reflects the customer's emotions, improving the user experience.

[1051] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1052] Step 1:

[1053] The server collects customer profile data via the internet. The input includes customer ID, interest categories, etc. These data are collected using predefined scraping scripts or APIs. As output, customer profile data (purchase history, preferences, etc.) is obtained and stored in a database.

[1054] Step 2:

[1055] The server extracts the collected customer data and passes it to a generative artificial intelligence model (such as ChatGPT) for analysis. The input is the customer's past purchase history and preferences, which are provided as prompts. Summary information (e.g., a list of products recommended to the customer and their overview) is generated as output.

[1056] Step 3:

[1057] The server sends the summarized information to the terminal. As input, it contains the generated summarized information. As output, the summarized information is sent to the terminal through the API. The terminal prepares this information to be displayed on the user interface.

[1058] Step 4:

[1059] The terminal displays the provided summary information to the user through a user interface, which includes the summary information sent from the server as input, and displays the information on the terminal screen in a form that can be viewed by the user as output.

[1060] Step 5:

[1061] The user inputs feedback about the displayed information. The input includes the user's feedback comments and ratings. The output is sent from the terminal to the server.

[1062] Step 6:

[1063] The server stores the feedback sent by the user in a database. The input includes the feedback information. The output is the feedback stored and data for system improvement is accumulated based on the feedback.

[1064] Step 7:

[1065] The device or server recognizes emotions from the user's actions and comments. The input includes the user's actions and comments. The processing involves analysis using an emotion analysis engine (such as NVIDIA NeMo). The output is a result based on the user's emotions.

[1066] Step 8:

[1067] The server adjusts the information provided based on the emotion analysis results. The emotion analysis results are included as input. The adjusted information is generated as output and sent back to the device. The device then redisplays the adjusted information, improving the user experience.

[1068] 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.

[1069] 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.

[1070] 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.

[1071] [Fourth embodiment]

[1072] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1073] 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.

[1074] 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).

[1075] 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.

[1076] 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.

[1077] 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).

[1078] 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.

[1079] 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.

[1080] 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.

[1081] 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.

[1082] 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.

[1083] 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.

[1084] 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."

[1085] The present invention relates to a system having a data collection means, a data analysis means, an information provision means, and a feedback collection means, and in particular to a system for efficiently collecting, analyzing, and providing candidate information and collecting feedback in an election.

[1086] Data collection

[1087] The server collects data such as candidate profiles, parliamentary activities, and campaign promises via the Internet. Specifically, the server obtains data from candidates' official websites, newspaper articles, social media, and other online resources. This data is collected automatically using pre-configured scraping scripts.

[1088] Data analysis

[1089] The collected data is analyzed by the server using a generative artificial intelligence model (e.g., ChatGPT). The server inputs the candidate's profile and activity history and uses the generative artificial intelligence model to summarize this information. The summary results are presented in a concise and easy-to-understand format and passed to the information provider.

[1090] Information provision

[1091] The summarized information is provided to the user through a user interface on the device. The server sends the summarized candidate information to the device via an API and displays it on the user interface. Through this interface, the user can easily view each candidate's detailed profile, parliamentary activities, and campaign promises.

[1092] Feedback collection

[1093] Users can provide feedback on the information provided. The device interface includes a feedback input form, allowing users to rate the clarity and ease of understanding of the information. When a user submits feedback, the device sends the information to the server, which stores the feedback in a database and uses it to improve the system.

[1094] Specific examples

[1095] For example, if a user wants to research a particular candidate on the Internet during an election period, the user accesses "Election Navigator" through their device. The server collects detailed data on the candidate, analyzes the collected data using a generative artificial intelligence model, and generates a summary. The generated summary is displayed to the user through a user interface. The user views the information and enters feedback about the content. The feedback is sent to the server and used to improve the system.

[1096] In this way, the system of the present invention helps voters easily obtain appropriate information and choose appropriate politicians, thereby improving the transparency of elections and contributing to promoting political participation.

[1097] The processing flow will be explained below.

[1098] Step 1:

[1099] A server prepares a list of target website URLs for collecting candidate data.

[1100] Step 2:

[1101] The server sends an HTTP request to each URL in the prepared list to retrieve the web page content. Specifically, it retrieves the HTML content using the requests library or similar.

[1102] Step 3:

[1103] The server parses the retrieved HTML content using libraries such as BeautifulSoup to extract necessary information such as the candidate's profile, parliamentary activities, campaign promises, etc. The extracted information is then converted into a structured format.

[1104] Step 4:

[1105] The server stores the structured candidate data in a temporary storage area or database, for example using a json format or database entry structure for this storage process.

[1106] Step 5:

[1107] The server uses a generative artificial intelligence model (e.g., ChatGPT) to select and retrieve stored candidate data, then formats the retrieved data as analytical input.

[1108] Step 6:

[1109] The server then inputs the formatted data into a generative artificial intelligence model to generate a summary of the candidate information, which is then converted into a concise, easy-to-understand format.

[1110] Step 7:

[1111] The server places the generated abstract data into an API endpoint configured as an information provider, which is then accessed by the user interface.

[1112] Step 8:

[1113] A user accesses a user interface using a terminal and requests specific candidate information, which sends a request to an API endpoint.

[1114] Step 9:

[1115] In response to a request from the terminal, the server acquires summary data of the relevant candidate from the database and transmits the data to the terminal as a response.

[1116] Step 10:

[1117] The terminal displays the received summary data on a user interface, allowing the user to view the information.

[1118] Step 11:

[1119] The user enters feedback on the candidate information provided, including an assessment of the clarity and understandability of the information.

[1120] Step 12:

[1121] The terminal transmits the feedback input by the user to the server as a POST request.

[1122] Step 13:

[1123] The server stores the received feedback data and analyzes and uses it for future system improvements.

[1124] This process flow allows the system to efficiently collect, analyze, and summarize candidate data, providing the information to voters in an easy-to-understand format, and collecting user feedback to help continuously improve the system.

[1125] Example 1

[1126] 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."

[1127] In elections, it is difficult for voters to quickly and accurately obtain information about candidates and make appropriate decisions based on that information. In particular, it is difficult to efficiently collect the vast amount of information scattered across the Internet and provide it in an easy-to-understand format. In addition to providing information, there are also insufficient means to collect feedback from voters and use it to improve the system.

[1128] 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.

[1129] In this invention, the server includes a data collection means, a data analysis means, an information provision means, and a feedback collection means, which enable the server to collect candidate data via the Internet, analyze and summarize the data using a generative artificial intelligence model, provide information through a user interface, and collect user feedback to use in improving the system.

[1130] "Data collection means" refers to devices or methods that automatically collect data such as candidate profiles, parliamentary activities, and campaign promises via the Internet.

[1131] "Data analysis means" refers to a device or method that analyzes collected data and summarizes it into meaningful information. In particular, it includes means that do this automatically and efficiently by using a generative artificial intelligence model.

[1132] The "information providing means" refers to a device or method that provides the analyzed data to the user through a user interface, thereby allowing the user to easily refer to information about the candidate.

[1133] "Feedback collection means" refers to a device or method that collects feedback from users, stores that information in a database, and uses it to improve the system.

[1134] A "generative artificial intelligence model" is an artificial intelligence algorithm that has the ability to generate new information based on given input data. For example, ChatGPT is an example of this.

[1135] A "user interface" is an interface that allows a user to operate a system or view information.

[1136] "Candidate data" refers to various information about candidates running in elections, including their profiles, parliamentary activities, and campaign promises.

[1137] The present invention is a system that collects and analyzes candidate information via the Internet, provides the results through a user interface, and collects feedback from users to help improve the system. Specific embodiments of the present invention are described below.

[1138] Data collection

[1139] The server connects to the Internet and collects data such as candidate profiles, parliamentary activities, and campaign promises from official candidate websites, newspaper articles, social media, etc. Web scraping tools such as Scrapy and BeautifulSoup are used to collect the data. The server uses these tools to automatically collect data based on the configured scraping script.

[1140] Data analysis

[1141] The server inputs the collected data into a generative artificial intelligence model (such as ChatGPT) for analysis. The server inputs the candidate's profile and activity history and uses ChatGPT to summarize this information. The summary results are generated in a concise and easy-to-understand format. OpenAI's API is used for data analysis.

[1142] Information provision

[1143] The server sends the analyzed and summarized candidate information to the device via API. The device displays the received information on the user interface. Through the device interface, users can easily view detailed candidate profiles, parliamentary activities, campaign promises, etc.

[1144] Feedback collection

[1145] Users enter feedback on the information provided. The device interface has a feedback input form, allowing users to rate the clarity and understandability of the information. When users submit feedback, the device sends the information to the server, which stores the feedback in a database. The collected feedback is used to improve the system.

[1146] Specific examples

[1147] For example, if a user wants to research a particular candidate during an election period, the user accesses the election navigation system through their device. The server collects detailed data on the candidate, analyzes and summarizes the data using a generative artificial intelligence model (ChatGPT), and generates a summary. The summary is then displayed to the user through a user interface. The user then browses the information and enters feedback about the content. The feedback is sent from the device to the server and used to improve the system.

[1148] Example prompt sentence:

[1149] "Analyze and summarize the profiles of the following candidates and their congressional activities to date.

[1150] Candidate Name: Taro Yamada

[1151] profile: ...

[1152] Parliamentary Activities: ...

[1153] Summary results:

[1154] "

[1155] As described above, the system of the present invention can efficiently collect, analyze, and provide candidate information and gather feedback in elections, helping voters easily obtain appropriate information and make appropriate decisions. This system will improve the transparency of elections and contribute to promoting political participation.

[1156] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1157] Step 1:

[1158] The server connects to the internet to collect candidate information. It runs a configured scraping script to collect data such as candidate profiles, parliamentary activities, and campaign promises from official websites, newspaper articles, social media, etc. It uses URLs and search queries as input and obtains a dataset of collected candidate information as output. This dataset is then stored in a database.

[1159] Specific working example:

[1160] The server uses Scrapy or BeautifulSoup to parse the content of the web page and extract the necessary data.

[1161] Step 2:

[1162] The server generates prompts to input the collected candidate data into the generative artificial intelligence model. The prompts include the candidate's name, profile, and parliamentary activities. The candidate data is used as input, and the prompts are generated as output.

[1163] Specific working example:

[1164] The server uses the OpenAI API to pass files to the generative artificial intelligence model.

[1165] Step 3:

[1166] The server inputs the prompt sentence into a generative AI model for analysis. Using a generative AI model such as ChatGPT, the server summarizes the candidate's information. The prompt sentence is used as input, and the summarized information is obtained as output. This summary information is stored in a database.

[1167] Specific working example:

[1168] The server passes the prompt to the OpenAI API and saves the resulting summary in text format.

[1169] Step 4:

[1170] The server sends the summarized candidate information to the terminal through the API. The terminal displays the received information on the user interface. The summarized information is used as input, and the information sent to the terminal is obtained as output.

[1171] Specific working example:

[1172] The server uses a framework (e.g., Flask or Django) to provide an API and send information to the device.

[1173] Step 5:

[1174] The user views the candidate information through the user interface of the terminal. The summarized candidate information is used as input, and the user's act of viewing the information is obtained as output.

[1175] Specific working example:

[1176] The device uses front-end frameworks such as React and Vue.js to build the interface and display information.

[1177] Step 6:

[1178] The user enters feedback on the provided information. The terminal interface has a feedback input form, allowing the user to rate the clarity and understandability of the information. The user's feedback is used as input, and feedback information is obtained as output.

[1179] Specific working example:

[1180] The user enters their feedback into a form in the interface and clicks the submit button.

[1181] Step 7:

[1182] The terminal sends the user's feedback to the server, and the feedback information is used as input, and the feedback sent to the server is obtained as output.

[1183] Specific working example:

[1184] The device uses AJAX requests to send feedback to the server asynchronously.

[1185] Step 8:

[1186] The server stores the received feedback in a database and uses it to improve the system. Feedback information is used as input, and feedback data for system improvement is obtained as output.

[1187] Specific working example:

[1188] The server stores the feedback information in a database and uses it for analysis.

[1189] (Application example 1)

[1190] 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."

[1191] In modern society, election information is extremely diverse, making it difficult to easily gather and understand detailed information such as candidate profiles, parliamentary activities, and campaign promises. Furthermore, the means by which voters can obtain information based on their own interests are limited, making it necessary to improve the transparency of election information and promote political participation.

[1192] 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.

[1193] In this invention, the server includes a data collection means, a data analysis means, an information provision means, a feedback collection means, a means for generating and providing summary information based on the user's interests using the collected data, and a means for the user to input feedback on the summary information provided. This allows the user to easily and efficiently obtain detailed information about candidates and obtain information personalized based on their own interests. Furthermore, the system is improved based on the feedback, increasing the transparency and ease of understanding of the information.

[1194] A "data collection means" is a device or program means that automatically collects data such as candidate profiles, parliamentary activities, and campaign promises via the Internet.

[1195] "Data analysis means" means a device or program means that analyzes collected data using a generative artificial intelligence model and extracts and summarizes important information.

[1196] "Information providing means" refers to a device or program means for providing summarized information to a user through a user interface.

[1197] The "feedback collection means" is a device or program means that allows a user to input feedback on the provided information and collects that feedback.

[1198] The "means for generating and providing summary information according to the user's interests" refers to a device or program means that analyzes collected data, generates personalized summary information based on the user's interests, and provides it to the user.

[1199] The "means for a user to input feedback on the provided summary information" refers to a device or program means by which a user inputs an evaluation or opinion on the provided summary information and transmits the information to the system.

[1200] The system for implementing the present invention has the following means, thereby enabling efficient collection, analysis, provision and feedback collection of election information.

[1201] Data collection

[1202] The server collects data such as candidate profiles, parliamentary activities, and campaign promises via the Internet. Specifically, the server uses a web scraping tool to automatically collect data from candidate official websites, news articles, social media, and other online resources. The hardware used is a standard server machine, and the software used is Python and BeautifulSoup.

[1203] Data analysis

[1204] The collected data is analyzed by the server using a generative AI model (e.g., ChatGPT). The server inputs the candidate's profile and activity history into the generative AI model and summarizes this information. This summary result is generated in a concise and easy-to-understand format. The hardware is a similarly standard server machine, and the software uses OpenAI's API.

[1205] Information provision

[1206] The summarized information is sent from the server to the device and provided to the user through a user interface. The information is sent via an API and displayed in an application on the device. Users can easily view detailed profiles, activities, and campaign promises of candidates through the smartphone application.

[1207] Feedback collection

[1208] Users can provide feedback on the information provided. The device interface includes a feedback input form, allowing users to rate the clarity and understandability of the information. The feedback is sent from the device to the server, which stores the collected feedback in a database and uses it to improve the system.

[1209] Specific examples

[1210] For example, if a user wants more information about a particular candidate during an election, they can open a smartphone app and see a prompt such as, "Please summarize the recent activities of candidate XX." The server analyzes the collected data and generates a summary using a generative artificial intelligence model. The summary is then displayed on the app's user interface, allowing the user to view the information and provide their rating and feedback.

[1211] The system allows users to efficiently obtain personalized election information based on their interests, improves the transparency and understandability of the information provided, and continuously improves the system based on feedback, resulting in higher quality information being provided.

[1212] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1213] System program processing flow

[1214] Step 1:

[1215] The server collects detailed data on candidates via the Internet. Specifically, it uses a web scraping tool (e.g., Python's BeautifulSoup) to extract information such as the candidate's profile, parliamentary activities, and campaign promises from online resources such as the candidate's official website, news articles, and social media. In this process, a list of URLs is given as input, and HTML content is obtained as output.

[1216] Step 2:

[1217] The server inputs the collected data into a generative artificial intelligence model (e.g., ChatGPT). The collected text data is sent to OpenAI's API, which extracts key information about the candidate and generates a summary. This process uses the collected text data as input and produces summarized candidate information as output.

[1218] Step 3:

[1219] The server sends the summarized information to the device. The generated summary information is transferred to the smartphone application via a RESTful API. This allows the information to be displayed on the user's smartphone. The summarized data is passed to the API as input, and the data is provided to the device as output.

[1220] Step 4:

[1221] The terminal displays the summary information to the user through a user interface. The data acquired by the smartphone application is displayed in a visually easy-to-read format for the user. The input of this step is the summary data sent from the server, and the output is an information screen that the user can view.

[1222] Step 5:

[1223] Users can provide feedback on the information provided, such as clarity and understandability of the information, as well as additional questions and comments, via a feedback form. The input is the user's feedback, and the output is the feedback data sent to the server.

[1224] Step 6:

[1225] The server collects the feedback sent by users and stores it in a database. The feedback data is accumulated and used to improve the system. The input is the user feedback data, and the output is the feedback record stored in the database.

[1226] Specific operation example

[1227] For example, to collect information about a particular candidate during an election, the server scrapes the URL of the candidate's official website and obtains HTML data. The HTML data is then input into ChatGPT to generate a summary of the candidate's recent activities. The summary is then sent to the smartphone application via API and displayed on the user interface. The user can then enter a prompt such as "Please summarize the recent activities of candidate XX" and provide feedback based on the information. This feedback is returned to the server and stored in the feedback database.

[1228] 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.

[1229] The present invention relates to a system that combines a data collection means, a data analysis means, an information provision means, a feedback collection means, and an emotion engine that recognizes user emotions, and in particular, is a system for efficiently collecting, analyzing, and providing candidate information and collecting feedback in elections. The following describes an embodiment of the present invention.

[1230] Data collection

[1231] The server collects data such as candidate profiles, parliamentary activities, and campaign promises via the Internet. The server obtains the necessary data from the candidates' official websites, newspaper articles, social media, and other online resources. This data is collected automatically using pre-configured scraping scripts and APIs.

[1232] Data analysis

[1233] The collected data is analyzed by the server using a generative artificial intelligence model (e.g., ChatGPT). The server passes the candidate's profile and activity history as input to the generative artificial intelligence model, and generates summary information as the analysis result. This summary result is provided in a concise and easy-to-understand format.

[1234] Information provision

[1235] The summarized information is provided to the user through a user interface on the device. The server sends the summarized information to the device via an API and displays it on the user interface. Through this interface, the user can view each candidate's detailed profile, parliamentary activities, and campaign promises.

[1236] Feedback collection

[1237] Users can provide feedback on the information provided. The device interface has a feedback input form, where users can rate the clarity and ease of understanding of the information. When a user submits feedback, the device sends the information to the server. The server stores the feedback in a database and uses it to improve the system.

[1238] Use of emotion engine

[1239] The emotion engine recognizes emotions from user input and operations and adjusts the information provided based on those emotions. For example, if a user performs an operation or makes a comment that indicates dissatisfaction while viewing information about a candidate, the emotion engine analyzes that emotion and notifies the server. The server then adjusts the content and format of the information provided based on this information, providing the information in a more appropriate form for the user.

[1240] Specific examples

[1241] For example, if a user wants to research a particular candidate during an election, they access the "Election Navigator" using their device. The server collects detailed data on the candidate and analyzes and summarizes this data using a generative artificial intelligence model. The generated summary is displayed to the user through the device's user interface. If the user is dissatisfied while viewing this summary information, the emotion engine recognizes their emotion and notifies the server. The server adjusts the information it provides based on the information it receives and presents it to the user again. Users can also provide feedback on the clarity and content of the information, which is sent to the server and used to improve the system.

[1242] In this way, the system of the present invention helps voters easily obtain appropriate information and make it easier to choose the right politician. Furthermore, by introducing an emotion engine, it is possible to provide information according to the user's emotions, improving the user experience of the system.

[1243] The processing flow will be explained below.

[1244] Step 1:

[1245] The server prepares a list of target website URLs to collect candidate data, including official candidate websites, news articles, social media accounts, etc.

[1246] Step 2:

[1247] The server sends an HTTP request to each URL in the prepared list to retrieve the web page content, specifically the HTML content, using the requests library.

[1248] Step 3:

[1249] The server parses the retrieved HTML content using BeautifulSoup and extracts necessary information such as candidate profiles, parliamentary activities, campaign promises, etc. The extracted information is converted into a structured format such as JSON.

[1250] Step 4:

[1251] The server stores the structured candidate data in a database, where the storage process involves creating a database entry or updating an existing entry.

[1252] Step 5:

[1253] The server retrieves and analyzes the stored data using a generative artificial intelligence model (e.g., ChatGPT). The server passes the candidate's profile and activity history as input to the generative artificial intelligence model and generates summary information.

[1254] Step 6:

[1255] The server places the generated summary information at an API endpoint configured as an information provider, which is accessed by a user interface.

[1256] Step 7:

[1257] A user accesses a user interface using a terminal and requests specific candidate information, which sends a request to an API endpoint.

[1258] Step 8:

[1259] In response to a request from the terminal, the server acquires summary information of the relevant candidate from the database and transmits the data to the terminal as a response.

[1260] Step 9:

[1261] The terminal displays the received summary information on a user interface, allowing the user to view the information.

[1262] Step 10:

[1263] The user reacts to the displayed candidate information. The device sends the user's comments and input actions to the emotion engine to recognize the user's emotions.

[1264] Step 11:

[1265] The emotion engine recognizes emotions from user input and operations and sends the emotion data to the server. For example, if a user enters a comment expressing dissatisfaction, it will be recognized as a negative emotion.

[1266] Step 12:

[1267] The server receives the emotion data provided by the emotion engine and determines an action based on the emotion. For example, if the user expresses dissatisfaction, the server may provide more detailed information.

[1268] Step 13:

[1269] The user inputs feedback on the provided information. The terminal sends the feedback data to the server as a POST request.

[1270] Step 14:

[1271] The server stores, analyzes, and uses your feedback data for future system improvements. This feedback includes your evaluation of the clarity and understandability of the information.

[1272] This process flow allows the system of the present invention to efficiently collect, analyze, and summarize candidate data, and provide information to voters in an easy-to-understand format. Furthermore, by adjusting the information according to the user's emotions, the system can improve the user experience.

[1273] Example 2

[1274] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1275] There is a need for systems that allow users to quickly and accurately collect, analyze, and evaluate information in elections and other decision-making processes. However, conventional systems have had difficulty efficiently collecting and analyzing large amounts of data and providing it appropriately to users. They also lacked the ability to adjust information taking into account user feedback and emotions. The purpose of this invention is to solve these problems and provide a system that provides users with accurate information that is easy to understand.

[1276] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1277] In this invention, the server includes a data collection means, a data analysis means, an information provision means, a feedback collection means, an emotion recognition means, and a data adjustment means, which makes it possible to efficiently collect and analyze large amounts of data and to adjust and provide information based on the user's feedback and emotions.

[1278] "Data collection means" refers to a means for collecting target data via the Internet.

[1279] "Data analysis means" refers to means for analyzing collected data using a generative artificial intelligence model.

[1280] The "information providing means" is a means for providing the analyzed information to the user.

[1281] The "feedback collection means" is a means for collecting feedback from users.

[1282] The "emotion recognition means" is a means for recognizing emotions from user inputs and operations.

[1283] The "data adjustment means" is a means for adjusting the content and format of the information to be provided based on the information from the emotion recognition means.

[1284] The present invention is a system that combines data collection means, data analysis means, information provision means, feedback collection means, emotion recognition means, and data adjustment means. This system is designed to efficiently collect, analyze, and provide candidate information and collect feedback, particularly in elections. The detailed configuration and operating procedures for implementing the present invention are described below.

[1285] Hardware and software used

[1286] Hardware: Servers, devices (PCs, smartphones, etc.)

[1287] Software: scraping scripts, APIs, generative AI models (e.g., ChatGPT), sentiment engines, user interfaces, databases

[1288] Data collection

[1289] The server collects data such as candidate profiles, parliamentary activities, and campaign promises from the internet. The server automatically retrieves the necessary data from the candidates' official websites, newspaper articles, social media, and other online resources. This process is performed using pre-configured scraping scripts and APIs.

[1290] Data analysis

[1291] The server passes the collected data to a generative artificial intelligence model (e.g., ChatGPT). The generative artificial intelligence model is used to analyze the collected data and concisely summarize the candidate's information. During this analysis and summarization process, specific prompts (e.g., "Please summarize the candidate's profile") are input to the generative artificial intelligence model. The summarized information is then organized by the server and stored in a database in its final form.

[1292] Information provision

[1293] The server sends the summarized information via an API to the device, which then displays it to the user through a user interface. The user can navigate through this interface to view each candidate's detailed profile, parliamentary activities, and campaign promises.

[1294] Feedback collection

[1295] The device's user interface displays a form for entering feedback. When the user enters their thoughts and suggestions for improvement in the form and submits it, the device sends the feedback information to the server. The server stores the received feedback in a database and uses it later to improve the system.

[1296] Use of emotion engine

[1297] The emotion engine recognizes emotions from user input and operations. For example, if a user becomes dissatisfied while viewing information about a candidate, the emotion engine analyzes that emotion and notifies the server. The server then adjusts the content and format of the information it provides based on this notification. The adjusted information is then sent back to the terminal and redisplayed on the user interface.

[1298] Specific examples

[1299] For example, if a user wants to research a particular candidate during an election, the user accesses the "Election Navigator" app using a device. The server collects detailed data on the candidate and analyzes and summarizes this data using a generative artificial intelligence model. The generated summary is displayed to the user through the device's user interface. If the user is dissatisfied with the summary information, the emotion engine recognizes the user's emotion and notifies the server. The server then adjusts the information provided based on the information received and presents it to the user again. The user also provides feedback on the information's understandability and content, which is sent to the server and used to improve the system. In this way, the system of the present invention helps users easily obtain appropriate information and make appropriate decisions. Furthermore, the introduction of an emotion engine enables the provision of information tailored to the user's emotions, improving the user experience of the system.

[1300] Prompt Sentence Examples

[1301] "Use Election Navigator to find out information about candidates. Please provide detailed data on the candidates."

[1302] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1303] Step 1: Data collection

[1304] The server identifies the source of candidate information by referencing a list of URLs, such as the candidate's official website, newspaper articles, and social media.

[1305] Input: A list of URLs from which data is collected.

[1306] Output: URL to be scraped or API called

[1307] How it works: The server checks the URL list and prepares to collect data.

[1308] Step 2: Performing data collection

[1309] The server runs scraping scripts and APIs to collect data, specifically, it retrieves HTML data from specific web pages and JSON data from API endpoints.

[1310] Input: URL list, scraping script, API settings

[1311] Output: Raw candidate information obtained

[1312] How it works: The server uses configured scripts and APIs to collect data and store it in temporary storage.

[1313] Step 3: Save Data

[1314] The server stores the collected data in a temporary database.

[1315] Input: Raw candidate data collected

[1316] Output: Data stored in a temporary database

[1317] How it works: The server formats the collected data, filters out missing and duplicate data, and stores it in a temporary database.

[1318] Step 4: Prepare for data analysis

[1319] The server reads the collected data from the temporary database and prepares the input for the generative artificial intelligence model.

[1320] Input: Data stored in a temporary database

[1321] Output: Formatted data to feed into a generative artificial intelligence model

[1322] How it works: The server formats the data and passes it to a generative artificial intelligence model with appropriate prompts.

[1323] Step 5: Data analysis

[1324] The server uses a generative artificial intelligence model to analyze the data and summarize the candidate's information, for example using prompts such as "Please summarize the candidate's profile."

[1325] Input: Formatted data, prompt

[1326] Output: Summarized candidate information

[1327] How it works: The server runs a generative artificial intelligence model to obtain summary information that is then organized.

[1328] Step 6: Save summary information

[1329] The server organizes the summary results and stores them in their final form.

[1330] Input: Summary information from a generative artificial intelligence model

[1331] Output: Organized summary information, stored in a database

[1332] How it works: The server organizes the summary information and stores it in a database, filtering out unnecessary information in the process.

[1333] Step 7: Provide information

[1334] The server sends the summarized information to the device via API.

[1335] Input: Organized summary information, API settings

[1336] Output: Result sent to terminal

[1337] How it works: The server sends summary information to the device via the API.

[1338] Step 8: Display information

[1339] The terminal displays the information on a user interface.

[1340] Input: Summary information received from the server

[1341] Output: Information displayed in the user interface

[1342] What it does: The device formats the information and displays it on the user interface.

[1343] Step 9: Enter your feedback

[1344] The user enters feedback on the information provided.

[1345] Input: User actions to view information

[1346] Output: Feedback content

[1347] How it works: The user fills out a feedback form on the interface with their thoughts and ratings.

[1348] Step 10: Send feedback

[1349] The terminal sends feedback information to the server.

[1350] Input: Feedback entered by the user

[1351] Output: Result sent to the server

[1352] Operation: The device sends the feedback content to the server using a communication protocol.

[1353] Step 11: Save your feedback

[1354] The server stores the feedback in a database.

[1355] Input: Feedback sent from the device

[1356] Output: Feedback information stored in a database

[1357] How it works: The server stores the feedback information in a database for later use in improving the system.

[1358] Step 12: Sentiment Analysis

[1359] The emotion engine analyzes user input and operations.

[1360] Input: User operation history and comment content

[1361] Output: Emotion analysis results

[1362] How it works: The emotion engine performs real-time analysis and notifies the emotional state to the server.

[1363] Step 13: Information Reconciliation

[1364] The server adjusts the information based on the results of emotion analysis.

[1365] Input: Analysis results from the emotion engine

[1366] Output: Adjusted information

[1367] Operation: Adjusts the content and format of the information provided by the server and sends it back to the device.

[1368] Step 14: Redisplay

[1369] The re-adjusted information is sent to the terminal and displayed again on the interface.

[1370] Input: Adjusted information

[1371] Output: Information redisplayed in the user interface

[1372] How it works: The server sends the adjusted information to the device, which displays it on its user interface.

[1373] (Application example 2)

[1374] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1375] In physical stores, it is difficult for customers to quickly obtain appropriate product information based on their preferences and past purchase history. Furthermore, the information provided cannot be adjusted in real time based on the customer's emotions and reactions, which means that the customer experience is not fully improved. This makes it difficult to improve customer satisfaction and stimulate purchasing motivation.

[1376] 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.

[1377] In this invention, the server includes a data collection means, a data analysis means, an information provision means, a feedback collection means, an emotion recognition means, a means for acquiring customer profile data, a means for providing product information based on customer preferences, and a means for providing summary information, thereby making it possible to provide appropriate product information based on the customer's past purchase history and preferences, and to adjust information according to the customer's emotions.

[1378] "Data collection means" refers to a function that acquires information such as customer profile data, purchase history, and preferences via the Internet at physical stores.

[1379] "Data analysis means" is a function that analyzes collected data using a generative artificial intelligence model to generate summaries of customer-based information.

[1380] The "information provision means" is a function that presents appropriate product information and summaries through a user interface for providing the analyzed results to customers.

[1381] The "feedback collection means" is a function that collects feedback from users and transmits it to the server.

[1382] "Emotion recognition means" is a function that recognizes emotions from customer input and operations and adjusts the information provided in real time based on those emotions.

[1383] "Means for obtaining customer profile data" refers to a function for collecting customers' past purchase history, preferences, and other related information via the Internet.

[1384] The "means for providing product information based on customer preferences" is a function that provides optimal product information to customers based on collected customer data.

[1385] The "means for providing summary information" is a function that provides summary information analyzed by a generative artificial intelligence model to customers in an easy-to-understand manner.

[1386] The system for implementing this invention mainly consists of three elements: a server, a terminal, and a user. The server has a data collection means, a data analysis means, an information provision means, a feedback collection means, and an emotion recognition means, while the terminal provides an interface for providing information and collecting feedback. The user also uses the terminal to access the system to obtain information and send feedback.

[1387] Data collection via the internet

[1388] The server first collects customer profile data from various online resources, a process automated using predefined scraping scripts and APIs, including information about past purchases and preferences.

[1389] Data analysis

[1390] The collected data is then analyzed using a generative artificial intelligence model (e.g., ChatGPT). The server inputs the customer's profile and past purchase history into the model, and generates summary information as the analysis result. This summary information is presented in a concise and easy-to-understand format.

[1391] Examples of prompt statements

[1392] For example, provide the following prompt to a generative AI model:

[1393] Purchase history: 'Tea, Coffee, Mineral Water'

[1394] Preferences: 'Healthy food, I like organic products'

[1395] Information provision

[1396] The summarized information is provided to the user through a user interface on the device. The server sends the summarized information to the device via an API, and the device displays it on the user interface. The user can view detailed product information and recommended products through this interface.

[1397] Feedback collection

[1398] Users can provide feedback on the information provided. A feedback input form is provided in the device interface. Users rate the information on its clarity and understandability, and the device sends this to the server. The server stores the feedback in a database and uses it to improve the system.

[1399] emotion recognition

[1400] The emotion engine recognizes emotions from user operations and inputs and adjusts the information provided based on those emotions. For example, if a user makes a comment expressing uncertainty while browsing product information, the emotion engine analyzes this and notifies the server. The server then adjusts the content and format of the information provided based on this information and presents it to the user again.

[1401] For example, if a user enters a comment such as "I want to see the ingredients list for this product," the emotion engine will interpret this as an indication of interest and display additional detailed information such as "All of the ingredients in this product are organic and additive-free." In this way, information can be provided that reflects the customer's emotions, improving the user experience.

[1402] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1403] Step 1:

[1404] The server collects customer profile data via the internet. The input includes customer ID, interest categories, etc. These data are collected using predefined scraping scripts or APIs. As output, customer profile data (purchase history, preferences, etc.) is obtained and stored in a database.

[1405] Step 2:

[1406] The server extracts the collected customer data and passes it to a generative artificial intelligence model (such as ChatGPT) for analysis. The input is the customer's past purchase history and preferences, which are provided as prompts. Summary information (e.g., a list of products recommended to the customer and their overview) is generated as output.

[1407] Step 3:

[1408] The server sends the summarized information to the terminal. As input, it contains the generated summarized information. As output, the summarized information is sent to the terminal through the API. The terminal prepares this information to be displayed on the user interface.

[1409] Step 4:

[1410] The terminal displays the provided summary information to the user through a user interface, which includes the summary information sent from the server as input, and displays the information on the terminal screen in a form that can be viewed by the user as output.

[1411] Step 5:

[1412] The user inputs feedback about the displayed information. The input includes the user's feedback comments and ratings. The output is sent from the terminal to the server.

[1413] Step 6:

[1414] The server stores the feedback sent by the user in a database. The input includes the feedback information. The output is the feedback stored and data for system improvement is accumulated based on the feedback.

[1415] Step 7:

[1416] The device or server recognizes emotions from the user's actions and comments. The input includes the user's actions and comments. The processing involves analysis using an emotion analysis engine (such as NVIDIA NeMo). The output is a result based on the user's emotions.

[1417] Step 8:

[1418] The server adjusts the information provided based on the emotion analysis results. The emotion analysis results are included as input. The adjusted information is generated as output and sent back to the device. The device then redisplays the adjusted information, improving the user experience.

[1419] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1420] 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.

[1421] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1422] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1423] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1424] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1425] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1426] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, motorcycles, and other devices, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1427] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1428] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1429] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1430] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1431] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1432] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1433] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1434] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1435] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1436] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1437] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1438] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1439] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1440] The following is further disclosed regarding the above embodiment.

[1441] (Claim 1)

[1442] data collection means;

[1443] data analysis means;

[1444] Means of providing information;

[1445] a feedback collection means;

[1446] A system including:

[1447] (Claim 2)

[1448] 10. The system of claim 1, wherein the candidate data is collected via the Internet.

[1449] (Claim 3)

[1450] 10. The system of claim 1, wherein the system uses a generative artificial intelligence model to analyze the collected data and summarize candidate information.

[1451] "Example 1"

[1452] (Claim 1)

[1453] data collection means;

[1454] data analysis means;

[1455] Means of providing information;

[1456] a feedback collection means;

[1457] A system including:

[1458] (Claim 2)

[1459] 10. The system of claim 1, wherein the candidate data is collected via the Internet.

[1460] (Claim 3)

[1461] 10. The system of claim 1, wherein the system uses a generative artificial intelligence model to analyze the collected data and summarize candidate information.

[1462] (Claim 4)

[1463] 10. The system of claim 1, further comprising means for providing summarized candidate information through a user interface.

[1464] (Claim 5)

[1465] 10. The system of claim 1, further comprising means for a user to input feedback via a user interface and for transmitting the feedback to a server.

[1466] (Claim 6)

[1467] 10. The system of claim 1, further comprising means for storing collected feedback in a database and utilizing the feedback to improve the system.

[1468] "Application Example 1"

[1469] (Claim 1)

[1470] data collection means;

[1471] data analysis means;

[1472] Means of providing information;

[1473] a feedback collection means;

[1474] A means for generating and providing summary information according to the user's interests using the collected data;

[1475] a means for the user to input feedback on the provided summary information;

[1476] A system including:

[1477] (Claim 2)

[1478] 10. The system of claim 1, wherein the candidate data is collected via the Internet.

[1479] (Claim 3)

[1480] The system of claim 1, further comprising technology for analyzing collected data using a generative artificial intelligence model to summarize candidate information and provide summarized information based on the user's interests.

[1481] "Example 2: Combining Emotion Engines"

[1482] New Claims

[1483] (Claim 1)

[1484] data collection means;

[1485] data analysis means;

[1486] Means of providing information;

[1487] a feedback collection means;

[1488] An emotion recognition means;

[1489] data adjustment means;

[1490] A system including:

[1491] (Claim 2)

[1492] 10. The system of claim 1, wherein the target data is collected via the Internet.

[1493] (Claim 3)

[1494] 10. The system of claim 1, wherein the system uses a generative artificial intelligence model to analyze the collected data and summarize the information of interest.

[1495] "Application example 2 when combining emotion engines"

[1496] (Claim 1)

[1497] data collection means;

[1498] data analysis means;

[1499] Means of providing information;

[1500] a feedback collection means;

[1501] An emotion recognition means;

[1502] a means for obtaining customer profile data;

[1503] a means for providing product information based on customer preferences;

[1504] a means for providing summary information;

[1505] A system including:

[1506] (Claim 2)

[1507] 10. The system of claim 1, wherein the customer data is collected via the Internet.

[1508] (Claim 3)

[1509] The system of claim 1, wherein the system analyzes collected data using a generative artificial intelligence model to summarize product information suitable for the customer. [Explanation of symbols]

[1510] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. data collection means; data analysis means; Means of providing information; a feedback collection means; A system including:

2. 10. The system of claim 1, wherein candidate data is collected via the Internet.

3. 10. The system of claim 1, wherein the system uses a generative artificial intelligence model to analyze the collected data and summarize the candidate information.

Images