System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting information about a politician; means for pre-processing the collected information; means for analyzing the pre-processed information using a generative AI model to generate summary information; means for storing the generated summary information in a database; and means for providing the stored summary information in response to a request from a user.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 the current political system, voters are unable to obtain sufficient information and find it difficult to find politicians who suit them. This information imbalance arises from the limited election period and the tendency to rely heavily on the name recognition of candidates, while actual ability and ideals tend to be overlooked. Measures are needed to resolve this issue and increase political transparency. [Means for solving the problem]

[0005] To solve this problem, the present invention provides the following means. First, a server is provided with means for collecting data on politicians. Next, the server is provided with means for preprocessing the collected data, and means for analyzing the preprocessed data using a generative AI model to generate summary information is provided. Next, a system is constructed that includes means for storing the generated summary information in a database and means for providing the stored summary information in response to a user request. This allows users to efficiently obtain information about politicians through their terminals, making it easier to find candidates who fit their values. Furthermore, by including means for collecting feedback and using it to improve the system, continuous improvement can be achieved.

[0006] "Data on politicians" refers to information such as basic information about politicians, past achievements, statements made in parliament, campaign promises, and ideology.

[0007] "Means of collection" refers to the ability to obtain data about politicians via the internet or using APIs.

[0008] "Preprocessing means" refers to the function of removing unnecessary information from collected data and formatting the data.

[0009] A "generative AI model" refers to algorithms or software that uses artificial intelligence to analyze data and generate summary information.

[0010] "Summary information" refers to information that has been created from data analyzed by a generative AI model and condensed into an easy-to-understand form.

[0011] "Database" refers to a system for storing and managing generated summary information.

[0012] The "means for providing" refers to a function for providing summary information stored in a database in response to a user's request.

[0013] "User" refers to an ordinary voter who uses a terminal to access summary information about politicians and search for a politician who suits them.

[0014] "Terminal" refers to a device, such as a computer or smartphone, that a user uses to access information.

[0015] "Feedback" refers to information, opinions, and impressions provided by users, and is information used to improve the system. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0024] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0037] The present invention relates to a system for efficiently collecting, analyzing, and providing information about politicians. This system is composed of a server, a terminal, a generative AI model, a database, etc.

[0038] 1. Data Collection

[0039] The server first collects data about politicians through an API on the Internet, including basic information about the politicians, their past performance, statements in parliament, campaign promises, and ideology.

[0040] 2. Data Preprocessing

[0041] The server preprocesses the collected data. Specifically, it removes unnecessary tags and spaces from the data and standardizes the string format. This preprocessing makes the data easier to analyze.

[0042] 3. Data analysis using generative AI

[0043] The server then analyzes the preprocessed data with a generative AI model, which tokenizes the preprocessed text and generates a summary that succinctly summarizes the politician's key data.

[0044] 4. Data storage and provision

[0045] The generated summary information is stored in a database by the server. In response to a user request, the server retrieves information from this database and provides it to the terminal via an API. The user can access the summary information through the terminal and quickly obtain information that is relevant to them.

[0046] 5. User Access and Feedback

[0047] Users access the API endpoint using their devices to obtain the generated summary information. The obtained information is displayed on the device in a format that is easy for users to understand. Furthermore, by adding a feedback function, opinions and feedback provided by users can be collected and analyzed on the server to help improve the system.

[0048] Specific examples

[0049] This section explains the flow for obtaining information about a specific politician (e.g., ID: 12345) and generating a summary. In this case, the server first collects detailed information about politician ID: 12345 from the API. The collected data is then preprocessed and summary information is generated using a generative AI model. The generated summary information is stored in a database and returned to the device when the user submits a request. This series of processes allows the user to easily understand the politician's basic information and past achievements.

[0050] This system will enable voters to efficiently obtain information about politicians and eliminate information imbalances, thereby increasing the fairness of elections and promoting election campaigns that reflect the will of the people.

[0051] The processing flow will be explained below.

[0052] Step 1:

[0053] The server collects data about politicians through an API on the Internet by sending a request for a specific politician to the API and receiving the returned data in JSON format.

[0054] Step 2:

[0055] The server preprocesses the collected data, specifically removing unnecessary tags and whitespace from the data and standardizing the string format, which makes subsequent analysis easier.

[0056] Step 3:

[0057] The server analyzes the preprocessed data using a generative AI model. For this analysis, the preprocessed text is tokenized using a tokenizer and the tokens are input into the generative AI model. The AI ​​then generates summary information.

[0058] Step 4:

[0059] The server stores the generated summary information in a database, which includes basic information about the politician, their past achievements, and campaign promises.

[0060] Step 5:

[0061] The server retrieves the stored summary information from the database in response to a user request and provides the retrieved summary information to the user via the API.

[0062] Step 6:

[0063] A user accesses the API endpoint using a device and requests summary information about a specific politician. The device receives a response from the server and displays the summary information on the screen.

[0064] Step 7:

[0065] Based on the provided summary information, users can understand basic information about politicians, their past achievements, campaign promises, etc. If necessary, they can use the feedback function to send opinions that will help improve the system to the server.

[0066] Through this series of steps, the server, terminal, and user work together to efficiently collect, analyze, and provide information about politicians.

[0067] Example 1

[0068] 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."

[0069] Conventional politician information gathering systems lack the ability to efficiently collect, preprocess, and analyze massive amounts of data and easily provide it to users. As a result, information imbalances arise, and users are unable to quickly access the information on politicians they need. Furthermore, there is an insufficient mechanism for incorporating user feedback into system improvements, making it difficult to improve the quality of the system.

[0070] 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.

[0071] In this invention, the server includes means for collecting data from the Internet, means for deleting unnecessary information from the collected data and standardizing the format, means for analyzing the preprocessed data using a generative AI model to generate summary information, means for saving the generated summary information in a database, means for providing the saved summary information in response to a user request, and means for collecting feedback from users and using it to improve the system. This enables efficient data collection, analysis, and provision, allowing users to quickly obtain the politician information they need, and enabling system improvements based on user feedback.

[0072] "Internet data" refers to any information accessible through the internet, often obtained through APIs.

[0073] "Nonessential information" refers to data that is not important or useful for a particular data analysis or purpose.

[0074] "Unifying the format" refers to the process of arranging the collected data into a consistent structure so that it can be easily analyzed and processed.

[0075] A "generative AI model" is an artificial intelligence model that generates a specific output based on given input data. A natural language processing model is typically used.

[0076] "Summary information" refers to information that has been compiled concisely and clearly by extracting only the important points from detailed data.

[0077] A "database" is a system designed to allow the efficient retrieval, storage, and updating of stored data.

[0078] A "request" refers to a request or inquiry made by a user to a server.

[0079] "Feedback" refers to opinions and impressions provided by users after using the system, and is information used to improve the system.

[0080] This invention is a system that efficiently collects, preprocesses, analyzes, and provides information about politicians to users. This system mainly uses a server, a terminal, a generative AI model, and a database.

[0081] First, the server collects data from the Internet. Specifically, the server obtains data about politicians through an API on the Internet. For example, this includes basic information about politicians, their past achievements, statements in parliament, campaign promises, and ideology.

[0082] The server then preprocesses the collected data, removing unnecessary information and standardizing the format. For example, it uses Python's Pandas and regular expression libraries to remove unnecessary tags and whitespace, and ensure consistent string formatting.

[0083] The server then analyzes the preprocessed data using a generative AI model, such as OpenAI's GPT-3, which tokenizes the preprocessed text and extracts key points to generate a summary.

[0084] The generated summary information is stored in a database by the server. The database is a relational database management system such as PostgreSQL. When a user makes a request, the server retrieves the necessary summary information from the database and provides it to the terminal via the API.

[0085] Users can access the API endpoint using their devices to obtain the generated summary information. The obtained information is displayed on the device in a format that is easy for users to understand. In addition, the system has a feedback function that collects user opinions and feedback, which will be used to improve the system.

[0086] As a concrete example, we will explain the flow for obtaining information about a specific politician (e.g., ID: 12345) and generating a summary. In this case, the server first collects detailed information about politician ID: 12345 from the API. Then, it preprocesses the collected data and generates summary information using a generative AI model. This summary information is stored in a database and is returned to the device when the user submits a request.

[0087] Examples of prompts include:

[0088] "summarize the following text about the politician: 'Politician's statements and promises... (preprocessed data)'"

[0089] "SELECT FROM politician_summary WHERE politician_id = 12345;"

[0090] This system allows users to quickly access important information about politicians, helping them make decisions efficiently. Furthermore, the system will be improved based on user feedback, further enhancing its quality.

[0091] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0092] Step 1:

[0093] The server collects data about politicians through an API on the Internet. Specifically, the server sends a request to a specific API endpoint and retrieves detailed information by specifying the politician's ID. The input of this process is the politician's ID, and the output is the retrieved detailed information.

[0094] Step 2:

[0095] The server preprocesses the collected data. Specifically, it removes unnecessary tags and whitespace from the data and standardizes the string format. The input of this process is the raw data obtained, and the output is the preprocessed data. Python's Pandas and regular expression libraries are used to remove unnecessary elements and convert the data into a consistent format.

[0096] Step 3:

[0097] The server sends the preprocessed data to a generative AI model (e.g., GPT-3), which tokenizes the provided text and generates a summary. The input of this process is the preprocessed text data, and the output is the generated summary.

[0098] Step 4:

[0099] The server stores the generated summary information in a database. The database uses a relational database management system (e.g., PostgreSQL) that allows efficient searching, storage, and updating. The input of this process is the generated summary information, and the output is the summary information stored in the database.

[0100] Step 5:

[0101] The server receives requests from users and provides the stored summary information. A user uses a device to access the API endpoint and request summary information for a specific politician. The input of this process is the user request, and the output is the summary information according to the request.

[0102] Step 6:

[0103] The user accesses the API endpoint using a terminal and retrieves the generated summary information, which is then displayed on the user's terminal. The input of this process is the summary information provided by the server, and the output is the summary information displayed on the terminal.

[0104] Step 7:

[0105] Users send their opinions and thoughts to the server through the feedback function. The server collects this feedback and uses it to improve the system. The input of this process is the user feedback, and the output is the analyzed feedback information.

[0106] This series of processes enables efficient collection, analysis, and provision of information about politicians, resulting in a system that allows users to quickly obtain the information they need.

[0107] (Application example 1)

[0108] 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."

[0109] Conventional political information systems require complicated information collection, analysis, and provision, making it difficult for users to quickly and easily obtain the information they require. Furthermore, the devices and methods for viewing information in real time were limited, resulting in an inadequate user experience. Furthermore, there was a lack of systems that allowed users to intuitively search for information using voice input or touch operations.

[0110] 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.

[0111] In this invention, the server includes means for collecting data on politicians, means for preprocessing the collected data, means for analyzing the preprocessed data using a generative AI model and generating summary information, means for saving the generated summary information in a database, means for providing the saved summary information in response to a user request, means for allowing the user to view information displayed on the smart device, and means for the user to search for information on politicians using voice input or touch operation. This allows users to quickly and easily obtain the information they need about politicians and to view the information in real time using intuitive operations.

[0112] "Data on politicians" refers to basic information about politicians, their past achievements, statements in parliament, campaign promises, beliefs, and other related information.

[0113] "Means of collection" refers to devices or software for obtaining data about politicians using APIs on the Internet, etc.

[0114] "Preprocessing means" refers to a device or software for removing unnecessary elements from collected data and standardizing the data format.

[0115] A "generative AI model" refers to an artificial intelligence model that uses natural language processing technology to analyze text data and generate summary information and related information.

[0116] "Means for generating summary information" refers to a device or software that analyzes preprocessed data using a generative AI model and generates information that succinctly summarizes the key points.

[0117] "Means for storing in a database" refers to a storage device or software for storing the generated summary information and retrieving it when necessary.

[0118] The "means for providing" refers to a device or software for obtaining summary information from a database in response to a user request and transmitting the information to a user terminal.

[0119] "Smart Device" refers to smartphones, smart glasses, tablets and other internet-enabled portable information terminals.

[0120] "Voice input" refers to a means by which a user can give instructions to a device using voice recognition technology.

[0121] "Touch operation" refers to the means by which a user issues commands using the touchscreen of a device.

[0122] The present invention relates to a system for efficiently collecting, analyzing, and providing information about politicians. This system includes a server, a terminal, and a specific generative AI model.

[0123] 1. Data Collection

[0124] The server first collects data about politicians through an API on the Internet, including basic information about the politician, past achievements, statements in parliament, campaign promises, and ideology. For example, the server collects information through an API request using an ID number that identifies a specific politician.

[0125] 2. Data Preprocessing

[0126] The server then preprocesses the collected data, specifically removing unnecessary elements from the data and standardizing the string format, making the data easier to analyze.

[0127] 3. Summary information generation

[0128] The pre-processed data is then analyzed by a generative AI model, which uses natural language processing techniques to summarize the text data. The pre-processed text is tokenized and a summary is generated that succinctly summarizes the key points.

[0129] 4. Data storage and provision

[0130] The generated summary information is stored in a database by the server. In response to a user request, the server retrieves information from this database and provides it to the terminal via an API. If the terminal is a smart device (smart glasses or tablet), the user can search for information using voice input or touch operation.

[0131] 5. User Access

[0132] Users access the API endpoint using their device to retrieve the generated summary information, which is then displayed on the device in a format that is easy for users to understand.

[0133] Specific examples

[0134] This section explains the flow for obtaining information about a specific politician (e.g., ID: 12345) and generating a summary. In this case, the server first collects detailed information about politician ID: 12345 from the API. The collected data is then preprocessed and summary information is generated using a generative AI model. The generated summary information is stored in a database and returned to the device when the user submits a request. This series of processes allows the user to easily understand the politician's basic information and past achievements.

[0135] Prompt Sentence Examples

[0136] Below are some example prompts that users can use to request information using smart glasses:

[0137] A user puts on the smart glasses and requests information about a particular politician, for example, by saying "Show me information about politician ID 12345."

[0138] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0139] Step 1:

[0140] The server collects data about politicians using an API on the Internet. As input, it receives an ID number that identifies a specific politician and sends an API request. As output, it obtains detailed data such as the politician's basic information, past achievements, statements in parliament, campaign promises, and ideology.

[0141] Step 2:

[0142] The server pre-processes the collected data. As input, it receives the raw data from the API, removes unnecessary elements (e.g., HTML tags and extra spaces), and standardizes the string format. As output, it obtains pre-processed data that is easier to parse.

[0143] Step 3:

[0144] The server analyzes the preprocessed data using a generative AI model. As input, it receives the preprocessed text data, tokenizes it, and analyzes it. As output, it generates a summary of the politician's key points.

[0145] Step 4:

[0146] The server stores the generated summary information in a database. As input, it receives summary information from the generative AI model and stores it in the database. As output, it provides a database that is organized in a way that can respond to user requests.

[0147] Step 5:

[0148] A user accesses the server's API endpoint using a device and requests summary information. As input, the user sends a request about a specific politician (e.g., politician ID: 12345) using voice input or touch operation. As output, the user receives the summary information provided by the server on the device.

[0149] Step 6:

[0150] The terminal displays the received summary information. As input, it receives the summary information sent from the server and converts it into a format that is easy to display visually. As output, it displays it on the display in a format that is easy for the user to understand.

[0151] Step 7:

[0152] The user reviews the displayed information and, if necessary, asks additional questions or requests by voice or touch. As input, a new request or feedback is sent to the device. As output, a new request is generated to the server, and the information corresponding to the request is again collected, preprocessed, analyzed, and provided.

[0153] 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.

[0154] This invention relates to a system that efficiently collects, analyzes, and provides information about politicians, and also combines it with an emotion engine that recognizes the user's emotions. This system is composed of a server, a terminal, a generative AI model, a database, an emotion engine, etc.

[0155] 1. Data Collection

[0156] The server first collects data about politicians through an API on the Internet, including basic information about the politicians, their past performance, statements in parliament, campaign promises, and ideology.

[0157] 2. Data Preprocessing

[0158] The server preprocesses the collected data. Specifically, it removes unnecessary tags and spaces from the data and standardizes the string format. This preprocessing makes the data easier to analyze.

[0159] 3. Data analysis using generative AI

[0160] The server then analyzes the preprocessed data using a generative AI model. To do this, the preprocessed text is tokenized using a tokenizer and the tokens are input into the generative AI model, which then generates summary information.

[0161] 4. Data storage and provision

[0162] The generated summary information is stored in a database by the server. In response to a user request, the server retrieves information from this database and provides it to the terminal via an API. The user can access the summary information through the terminal and quickly obtain information that is relevant to them.

[0163] 5. Emotional Analysis of Users by Emotion Engine

[0164] The server also includes an emotion engine that recognizes the user's emotions. The emotion engine monitors the user's feedback and behavior during use, and analyzes emotions in real time. The analysis results are stored in a database and the presentation of summary information is adjusted based on the user's emotional state.

[0165] Specific examples

[0166] This section explains the process for obtaining information about a specific politician (e.g., ID: 12345) and generating a summary. In this case, the server collects detailed information about politician ID: 12345 from the API. The collected data is then preprocessed and summary information is generated using a generative AI model. The generated summary information is stored in a database and returned to the device when the user submits a request. Furthermore, when the user views the summary information, the server uses an emotion engine to analyze the user's emotions in real time and optimizes the presentation method based on the results. This series of processes not only allows the user to concisely grasp the politician's basic information and past performance, but also allows them to receive information optimally presented according to their emotions.

[0167] This system allows voters to efficiently obtain information about politicians and eliminate information imbalances. Furthermore, the emotion engine improves users' understanding and sense of satisfaction, thereby enhancing the fairness of elections.

[0168] The processing flow will be explained below.

[0169] This invention combines a system for efficiently collecting, analyzing, and providing information about politicians with an emotion engine that recognizes user emotions. This system is composed of a server, terminals, a generative AI model, a database, and an emotion engine.

[0170] Step 1:

[0171] The server first collects data about politicians through an API on the internet, which involves sending requests to specific API endpoints and receiving the returned data in JSON format.

[0172] Step 2:

[0173] The server preprocesses the collected data, which includes removing unnecessary tags and whitespace from the data and standardizing string formats, making the data easier to analyze.

[0174] Step 3:

[0175] The server analyzes the preprocessed data using a generative AI model. For this analysis, the preprocessed text is tokenized using a tokenizer and the tokens are input to the generative AI model. The generative AI model generates summary information from the tokenized text.

[0176] Step 4:

[0177] The server stores the generated summary information in a database, which includes the process of storing the summary information in a database and indexing the information for efficient retrieval.

[0178] Step 5:

[0179] The server retrieves the stored summary information from the database in response to a user request. This retrieval process involves searching the database based on the user request and extracting the relevant summary information as a search result.

[0180] Step 6:

[0181] The server provides the acquired summary information to the device via an API, allowing the user to access the summary information through the device and quickly obtain information about the politicians they need.

[0182] Step 7:

[0183] The device displays the summary information retrieved from the API to the user in a format that is easy for the user to understand, such as text, graphs, or images.

[0184] Step 8:

[0185] The server uses an emotion engine to monitor user feedback and behavior during use and analyze emotions in real time. For this analysis, it analyzes textual feedback and collects and analyzes device usage history data.

[0186] Step 9:

[0187] Based on the analysis results, the server adjusts the presentation of summary information according to the user's emotional state: for example, if the user is excited, it displays information in a clear and concise manner, while if the user is relaxed, it provides detailed information.

[0188] Step 10:

[0189] The user provides feedback through the terminal, which includes opinions and impressions about the provided summary information, and the server collects and stores the feedback in a database.

[0190] This system efficiently obtains information about politicians and presents information according to the user's emotions, thereby eliminating information imbalances and promoting fair election campaigns.

[0191] Example 2

[0192] 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."

[0193] In modern society, the amount of information about politicians is enormous, making it difficult for voters to grasp the overall picture. Furthermore, organizing and summarizing the collected information is time-consuming, and current systems do not provide information that takes into account the user's emotions. Therefore, there is a need for a system that can quickly provide appropriate information to users and present information in a way that suits their emotional state.

[0194] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting data on politicians, means for preprocessing the collected data, means for analyzing the preprocessed data using a generative AI model and generating summary information, means for saving the generated summary information in a database, and means for recognizing user emotions and optimizing the presentation method. This makes it possible to provide information on politicians to users quickly and efficiently, and further to present information optimally according to the user's emotions.

[0195] A "politician" is a public official or person who is running for or elected to public office or who holds a political role.

[0196] A "data collection tool" is a system or process for obtaining specific information from the Internet or other sources.

[0197] "Data preprocessing means" refers to a system or process for removing unnecessary elements from collected data and standardizing the data format.

[0198] A "generative AI model" is an artificial intelligence model that learns from large amounts of data and performs various tasks (e.g., summary generation, question answering).

[0199] A "summary generator" is a system or process for generating summary information from preprocessed data using a generative AI model.

[0200] "Database storage means" means a system or process for storing the generated summary information in a structured format in a database.

[0201] "Providing means" refers to a system or process for retrieving and providing information stored in a database in response to a user request.

[0202] An "emotion recognizer" is a system or process for analyzing a user's feedback and behavior to identify the user's emotional state.

[0203] A "presentation optimizer" is a system or process for adjusting the presentation of information based on the user's emotional state obtained by the emotion recognizer.

[0204] This invention is a system that efficiently collects, analyzes, and provides information about politicians, and also combines it with an emotion engine that recognizes the user's emotions. This system is composed of a server, a terminal, a generative AI model, a database, an emotion engine, etc.

[0205] The server first collects data about politicians through an API on the Internet. This data includes basic information about the politician, their past achievements, statements in parliament, campaign promises, and ideology. For example, information about politician ID: 12345 can be collected from a URL such as "https: / / api.example.com / politician / 12345."

[0206] Next, the server preprocesses the collected data. During this process, unnecessary tags and whitespace are removed and the string format is standardized. This preprocessing makes the data easier to analyze. For example, if HTML tags or special characters are included, they are removed and the date format is standardized to "YYYY-MM-DD".

[0207] The data is then analyzed using a generative AI model. The server tokenizes the preprocessed data using a tokenizer and inputs the tokens into a generative AI model. A large-scale language model (e.g., GPT-3) can be used as the generative AI model. This model is used to summarize the text and generate summary information. An example of a prompt sentence is, "Please summarize the basic information about politician ID: 12345."

[0208] The generated summary information is stored in a database by the server. This database typically uses a relational database such as SQL. When a user requests information through their device, the server retrieves the required information from the database and provides it to the device via an API. The user can then access the summary information using their device and obtain the information quickly.

[0209] Furthermore, the server uses an emotion engine to recognize the user's emotions. This emotion engine monitors and analyzes user feedback and usage behavior in real time. For example, it collects user click logs and page visit times and performs emotion analysis. The analysis results are stored in a database and the way summary information is presented is adjusted based on the user's emotional state. For example, detailed information is provided to users with positive emotions, and concise information is provided to users with negative emotions.

[0210] As a concrete example, we will explain the flow of obtaining information about a specific politician (e.g., ID: 12345) and generating a summary. In this case, the server collects detailed information about politician ID: 12345 from an API. The collected data is then preprocessed and summary information is generated using a generative AI model. The generated summary information is stored in a database and returned to the device when the user submits a request. Furthermore, when the user views the summary information, the server uses an emotion engine to analyze the user's emotions in real time and optimizes the presentation method based on the results. This series of processes not only allows the user to concisely grasp the politician's basic information and past performance, but also allows them to receive information that is optimally presented according to their emotions.

[0211] The system described above allows voters to efficiently obtain information about politicians and eliminate information imbalances. Furthermore, the emotion engine improves users' understanding and sense of satisfaction, potentially enhancing the fairness of elections.

[0212] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0213] Step 1:

[0214] Initializing and sending data collection

[0215] The server sets an interval to collect data about politicians using a pre-configured API endpoint. For example, it sets a timer to send an API request every hour. The server sends the API request to the URL "https: / / api.example.com / politician / 12345" and includes an API key or authentication token in the header, if necessary. The input at this point is the API request information, and the output is the response data from the API.

[0216] Step 2:

[0217] Data reception and preprocessing

[0218] The server receives a JSON-formatted response from the API. The received data includes basic information about politicians and their past achievements. This data is analyzed, unnecessary elements such as HTML tags and special characters are removed, and the format is standardized. For example, the date format is standardized to "YYYY-MM-DD." The input in this step is the API response data, and the output is clean data after preprocessing.

[0219] Step 3:

[0220] Data tokenization and summary generation

[0221] The server tokenizes the preprocessed text data using a tokenizer, which splits the sentence into words and phrases and generates an array of tokens. Next, the preprocessed data is input to a generative AI model (e.g., GPT-3) to generate summary information according to a prompt such as "Please summarize basic information about politician ID: 12345." The input in this step is the preprocessed data and the prompt, and the output is the generated summary information.

[0222] Step 4:

[0223] Save summary information

[0224] The server stores the generated summary information in a database. This process uses SQL queries to insert the summary information into the appropriate tables. The input to this step is the generated summary information, and the output is the summary information stored in the database.

[0225] Step 5:

[0226] Processing user requests and providing data

[0227] A user requests information about a particular politician through a terminal, for example, by submitting an information request through an application on the terminal or a web form. When the server receives this request, it retrieves the corresponding summary information from the database and returns it to the user terminal as a response in an appropriate format. The input in this step is the user request, and the output is the summary information provided to the user terminal.

[0228] Step 6:

[0229] User sentiment analysis and information presentation optimization

[0230] The server collects user feedback and behavioral data during use and analyzes it with an emotion engine. This engine analyzes data such as click logs and page visit times to identify the user's emotional state. For example, if there is a lot of negative feedback, it determines that the user is dissatisfied and changes the settings to provide more concise information. The input in this step is user behavior data, and the output is the emotion analysis results and adjustments to the information presentation method based on those results.

[0231] Combining these steps allows users to efficiently obtain detailed information about politicians and present it in the most relevant way based on their sentiment.

[0232] (Application example 2)

[0233] 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."

[0234] Conventional systems for collecting and analyzing information about politicians present information to users in a uniform manner, resulting in insufficient personalization based on the user's emotions and interests. Furthermore, when applied to advertising, this system suffers from the problem of reduced advertising effectiveness because it does not take into account the user's emotions. This makes it difficult to provide users with the information they desire quickly and appropriately, leading to information imbalances and lack of understanding.

[0235] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data on politicians, means for preprocessing the collected data, means for analyzing the preprocessed data using a generative AI model and generating summary information, means for saving the generated summary information in a database, means for providing the saved summary information in response to a user request, means for analyzing the user's emotions using an emotion engine that recognizes the user's emotions and adjusting the presentation method, and means for providing optimal advertisements based on the user's emotions. This makes it possible to present information and optimize advertisements taking into account the user's emotional state.

[0236] "Data on politicians" refers to information including basic information about politicians, past achievements, statements made in parliament, campaign promises, and ideology.

[0237] The "means of collection" refers to the means of obtaining data about politicians through APIs on the Internet, etc.

[0238] "Preprocessing means" refers to a means for removing unnecessary elements from collected data and standardizing the data format.

[0239] A "generative AI model" is an artificial intelligence model that analyzes tokenized text data using a tokenizer and generates summary information.

[0240] "Summary information" is concise information generated by a generative AI model based on data about politicians.

[0241] A "database" is a system for storing the generated summary information and providing the information in response to a user's request.

[0242] The "means for providing in response to a request from a user" refers to a means for providing summary information stored in a database to a terminal in response to a user request.

[0243] An "emotion engine" is software that recognizes and analyzes a user's emotions.

[0244] The "means for adjusting the presentation method" is a means for adjusting the method for presenting information to the user based on the analysis results of the emotion engine.

[0245] "Advertising" is marketing content that is provided in an optimal manner based on the user's emotions and interests.

[0246] This invention relates to a system that efficiently collects and analyzes information about politicians, and then recognizes users' emotions to present optimal advertisements. This system includes components such as a server, a terminal, a generative AI model, a database, and an emotion engine.

[0247] A specific embodiment is as follows.

[0248] 1. Data Collection

[0249] The server collects data about politicians through an API on the Internet, including basic information about the politicians, their past performance, statements in parliament, campaign promises, and beliefs.

[0250] 2. Data Preprocessing

[0251] The server preprocesses the collected data by removing unnecessary elements and standardizing the data format, making the data easier to analyze.

[0252] 3. Data analysis using generative AI models

[0253] The server inputs the preprocessed data into a generative AI model for analysis. This generative AI model uses a natural language processing tokenizer. The tokenizer tokenizes the text data and inputs it into the generative AI model to generate summary information. The generated summary information is stored in a database.

[0254] 4. Data provision

[0255] When a user sends a request from their terminal, the server retrieves the stored summary information from the database and provides it to the user's terminal, allowing the user to quickly access the information they need.

[0256] 5. Emotional Analysis of Users by Emotion Engine

[0257] The server analyzes the user's feedback and behavior during use using an emotion engine. The emotion engine monitors the user's emotional state in real time and stores the analysis results in a database. Based on this emotional data, the method of presenting information to the user is optimized.

[0258] 6. Providing optimal advertising

[0259] The server then presents the most appropriate advertisement based on the results of the user's emotion analysis. If the user's emotion is positive, the server provides more detailed information, and if the user's emotion is negative, the server provides less interesting information. In this way, advertisements are displayed that are tailored to the user's emotional state.

[0260] Specific examples

[0261] 1. Example prompt (input to the generative AI model):

[0262] "Please summarize the policies of the following politicians: Policy A is..."

[0263] 2. Example summary output from a generative AI model:

[0264] "Summary of Policy A: Policy A emphasizes social welfare..."

[0265] 3. Example of input for user sentiment analysis:

[0266] "Very interesting. I'd like to know more!"

[0267] 4. Example of user sentiment analysis results:

[0268] "emotion: positive"

[0269] This invention not only enables users to quickly and easily obtain information about politicians, but also allows them to receive optimal information and advertisements according to their emotions, which is expected to eliminate information imbalances and improve advertising effectiveness.

[0270] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0271] Step 1:

[0272] The server collects data about politicians through an API on the Internet. As input, it uses the API endpoint and politician ID. The data returned from the API includes basic information about the politician, past achievements, statements in parliament, campaign promises, and beliefs. The output is the collected data about the politician.

[0273] Step 2:

[0274] The server preprocesses the collected data. The data about politicians collected in step 1 is used as input for preprocessing. Specifically, it removes unnecessary tags and spaces from the data and standardizes the string format. This converts the data into a format that is easy to analyze. The output is the preprocessed data.

[0275] Step 3:

[0276] The server analyzes the preprocessed data using a generative AI model to generate summary information. As input, it uses a tokenizer to tokenize the preprocessed text data. The tokenized data is input to the generative AI model to obtain summary information. Specifically, the generative AI model analyzes the text data, extracts important information, and generates a summary. The output is the generated summary information.

[0277] Step 4:

[0278] The server stores the generated summary information in the database. It uses the summary information generated in step 3 as input. Specific operations include converting the summary information into an appropriate format and storing it in the database. The output is confirmation data of the stored summary information.

[0279] Step 5:

[0280] When a user sends a request from their device, the server retrieves the stored summary information from the database and provides it to the user's device. The input is a request from the user. Specifically, the server sends a query to the database, retrieves the corresponding summary information, and sends it to the device. The output is the summary information displayed on the user's device.

[0281] Step 6:

[0282] The user's device collects user feedback and usage behavior from time to time and sends it to the server. The input includes user feedback and operation logs during usage. The output is the feedback data sent to the server.

[0283] Step 7:

[0284] The server uses the emotion engine to analyze the user's emotions. The input is the user's feedback data sent in step 6. Specifically, the emotion engine analyzes the feedback data and extracts the user's emotional state (positive, negative, etc.). The output is the analyzed user's emotion data.

[0285] Step 8:

[0286] The server selects and serves the most appropriate advertisement based on the results of the user's sentiment analysis. The inputs are the sentiment analysis results from step 7 and the advertisement information stored in the database. Specifically, the server selects the advertisement that is most suitable for the user based on the sentiment analysis results and sends it to the terminal. The output is the most appropriate advertisement that is displayed on the user's terminal.

[0287] This allows users to not only efficiently obtain information about politicians, but also receive advertisements that are most appropriate for their emotions.

[0288] 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.

[0289] 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.

[0290] 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.

[0291] [Second embodiment]

[0292] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0293] 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.

[0294] 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).

[0295] 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.

[0296] 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.

[0297] 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).

[0298] 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.

[0299] 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.

[0300] 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.

[0301] 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.

[0302] 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.

[0303] 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."

[0304] The present invention relates to a system for efficiently collecting, analyzing, and providing information about politicians. This system is composed of a server, a terminal, a generative AI model, a database, etc.

[0305] 1. Data Collection

[0306] The server first collects data about politicians through an API on the Internet, including basic information about the politicians, their past performance, statements in parliament, campaign promises, and ideology.

[0307] 2. Data Preprocessing

[0308] The server preprocesses the collected data. Specifically, it removes unnecessary tags and spaces from the data and standardizes the string format. This preprocessing makes the data easier to analyze.

[0309] 3. Data analysis using generative AI

[0310] The server then analyzes the preprocessed data with a generative AI model, which tokenizes the preprocessed text and generates a summary that succinctly summarizes the politician's key data.

[0311] 4. Data storage and provision

[0312] The generated summary information is stored in a database by the server. In response to a user request, the server retrieves information from this database and provides it to the terminal via an API. The user can access the summary information through the terminal and quickly obtain information that is relevant to them.

[0313] 5. User Access and Feedback

[0314] Users access the API endpoint using their devices to obtain the generated summary information. The obtained information is displayed on the device in a format that is easy for users to understand. Furthermore, by adding a feedback function, opinions and feedback provided by users can be collected and analyzed on the server to help improve the system.

[0315] Specific examples

[0316] This section explains the flow for obtaining information about a specific politician (e.g., ID: 12345) and generating a summary. In this case, the server first collects detailed information about politician ID: 12345 from the API. The collected data is then preprocessed and summary information is generated using a generative AI model. The generated summary information is stored in a database and returned to the device when the user submits a request. This series of processes allows the user to easily understand the politician's basic information and past achievements.

[0317] This system will enable voters to efficiently obtain information about politicians and eliminate information imbalances, thereby increasing the fairness of elections and promoting election campaigns that reflect the will of the people.

[0318] The processing flow will be explained below.

[0319] Step 1:

[0320] The server collects data about politicians through an API on the Internet by sending a request for a specific politician to the API and receiving the returned data in JSON format.

[0321] Step 2:

[0322] The server preprocesses the collected data, specifically removing unnecessary tags and whitespace from the data and standardizing the string format, which makes subsequent analysis easier.

[0323] Step 3:

[0324] The server analyzes the preprocessed data using a generative AI model. For this analysis, the preprocessed text is tokenized using a tokenizer and the tokens are input into the generative AI model. The AI ​​then generates summary information.

[0325] Step 4:

[0326] The server stores the generated summary information in a database, which includes basic information about the politician, their past achievements, and campaign promises.

[0327] Step 5:

[0328] The server retrieves the stored summary information from the database in response to a user request and provides the retrieved summary information to the user via the API.

[0329] Step 6:

[0330] A user accesses the API endpoint using a device and requests summary information about a specific politician. The device receives a response from the server and displays the summary information on the screen.

[0331] Step 7:

[0332] Based on the provided summary information, users can understand basic information about politicians, their past achievements, campaign promises, etc. If necessary, they can use the feedback function to send opinions that will help improve the system to the server.

[0333] Through this series of steps, the server, terminal, and user work together to efficiently collect, analyze, and provide information about politicians.

[0334] Example 1

[0335] 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."

[0336] Conventional politician information gathering systems lack the ability to efficiently collect, preprocess, and analyze massive amounts of data and easily provide it to users. As a result, information imbalances arise, and users are unable to quickly access the information on politicians they need. Furthermore, there is an insufficient mechanism for incorporating user feedback into system improvements, making it difficult to improve the quality of the system.

[0337] 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.

[0338] In this invention, the server includes means for collecting data from the Internet, means for deleting unnecessary information from the collected data and standardizing the format, means for analyzing the preprocessed data using a generative AI model to generate summary information, means for saving the generated summary information in a database, means for providing the saved summary information in response to a user request, and means for collecting feedback from users and using it to improve the system. This enables efficient data collection, analysis, and provision, allowing users to quickly obtain the politician information they need, and enabling system improvements based on user feedback.

[0339] "Internet data" refers to any information accessible through the internet, often obtained through APIs.

[0340] "Nonessential information" refers to data that is not important or useful for a particular data analysis or purpose.

[0341] "Unifying the format" refers to the process of arranging the collected data into a consistent structure so that it can be easily analyzed and processed.

[0342] A "generative AI model" is an artificial intelligence model that generates a specific output based on given input data. A natural language processing model is typically used.

[0343] "Summary information" refers to information that has been compiled concisely and clearly by extracting only the important points from detailed data.

[0344] A "database" is a system designed to allow the efficient retrieval, storage, and updating of stored data.

[0345] A "request" refers to a request or inquiry made by a user to a server.

[0346] "Feedback" refers to opinions and impressions provided by users after using the system, and is information used to improve the system.

[0347] This invention is a system that efficiently collects, preprocesses, analyzes, and provides information about politicians to users. This system mainly uses a server, a terminal, a generative AI model, and a database.

[0348] First, the server collects data from the Internet. Specifically, the server obtains data about politicians through an API on the Internet. For example, this includes basic information about politicians, their past achievements, statements in parliament, campaign promises, and ideology.

[0349] The server then preprocesses the collected data, removing unnecessary information and standardizing the format. For example, it uses Python's Pandas and regular expression libraries to remove unnecessary tags and whitespace, and ensure consistent string formatting.

[0350] The server then analyzes the preprocessed data using a generative AI model, such as OpenAI's GPT-3, which tokenizes the preprocessed text and extracts key points to generate a summary.

[0351] The generated summary information is stored in a database by the server. The database is a relational database management system such as PostgreSQL. When a user makes a request, the server retrieves the necessary summary information from the database and provides it to the terminal via the API.

[0352] Users can access the API endpoint using their devices to obtain the generated summary information. The obtained information is displayed on the device in a format that is easy for users to understand. In addition, the system has a feedback function that collects user opinions and feedback, which will be used to improve the system.

[0353] As a concrete example, we will explain the flow for obtaining information about a specific politician (e.g., ID: 12345) and generating a summary. In this case, the server first collects detailed information about politician ID: 12345 from the API. Then, it preprocesses the collected data and generates summary information using a generative AI model. This summary information is stored in a database and is returned to the device when the user submits a request.

[0354] Examples of prompts include:

[0355] "summarize the following text about the politician: 'Politician's statements and promises... (preprocessed data)'"

[0356] "SELECT FROM politician_summary WHERE politician_id = 12345;"

[0357] This system allows users to quickly access important information about politicians, helping them make decisions efficiently. Furthermore, the system will be improved based on user feedback, further enhancing its quality.

[0358] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0359] Step 1:

[0360] The server collects data about politicians through an API on the Internet. Specifically, the server sends a request to a specific API endpoint and retrieves detailed information by specifying the politician's ID. The input of this process is the politician's ID, and the output is the retrieved detailed information.

[0361] Step 2:

[0362] The server preprocesses the collected data. Specifically, it removes unnecessary tags and whitespace from the data and standardizes the string format. The input of this process is the raw data obtained, and the output is the preprocessed data. Python's Pandas and regular expression libraries are used to remove unnecessary elements and convert the data into a consistent format.

[0363] Step 3:

[0364] The server sends the preprocessed data to a generative AI model (e.g., GPT-3), which tokenizes the provided text and generates a summary. The input of this process is the preprocessed text data, and the output is the generated summary.

[0365] Step 4:

[0366] The server stores the generated summary information in a database. The database uses a relational database management system (e.g., PostgreSQL) that allows efficient searching, storage, and updating. The input of this process is the generated summary information, and the output is the summary information stored in the database.

[0367] Step 5:

[0368] The server receives requests from users and provides the stored summary information. A user uses a device to access the API endpoint and request summary information for a specific politician. The input of this process is the user request, and the output is the summary information according to the request.

[0369] Step 6:

[0370] The user accesses the API endpoint using a terminal and retrieves the generated summary information, which is then displayed on the user's terminal. The input of this process is the summary information provided by the server, and the output is the summary information displayed on the terminal.

[0371] Step 7:

[0372] Users send their opinions and thoughts to the server through the feedback function. The server collects this feedback and uses it to improve the system. The input of this process is the user feedback, and the output is the analyzed feedback information.

[0373] This series of processes enables efficient collection, analysis, and provision of information about politicians, resulting in a system that allows users to quickly obtain the information they need.

[0374] (Application example 1)

[0375] 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."

[0376] Conventional political information systems require complicated information collection, analysis, and provision, making it difficult for users to quickly and easily obtain the information they require. Furthermore, the devices and methods for viewing information in real time were limited, resulting in an inadequate user experience. Furthermore, there was a lack of systems that allowed users to intuitively search for information using voice input or touch operations.

[0377] 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.

[0378] In this invention, the server includes means for collecting data on politicians, means for preprocessing the collected data, means for analyzing the preprocessed data using a generative AI model and generating summary information, means for saving the generated summary information in a database, means for providing the saved summary information in response to a user request, means for allowing the user to view information displayed on the smart device, and means for the user to search for information on politicians using voice input or touch operation. This allows users to quickly and easily obtain the information they need about politicians and to view the information in real time using intuitive operations.

[0379] "Data on politicians" refers to basic information about politicians, their past achievements, statements in parliament, campaign promises, beliefs, and other related information.

[0380] "Means of collection" refers to devices or software for obtaining data about politicians using APIs on the Internet, etc.

[0381] "Preprocessing means" refers to a device or software for removing unnecessary elements from collected data and standardizing the data format.

[0382] A "generative AI model" refers to an artificial intelligence model that uses natural language processing technology to analyze text data and generate summary information and related information.

[0383] "Means for generating summary information" refers to a device or software that analyzes preprocessed data using a generative AI model and generates information that succinctly summarizes the key points.

[0384] "Means for storing in a database" refers to a storage device or software for storing the generated summary information and retrieving it when necessary.

[0385] The "means for providing" refers to a device or software for obtaining summary information from a database in response to a user request and transmitting the information to a user terminal.

[0386] "Smart Device" refers to smartphones, smart glasses, tablets and other internet-enabled portable information terminals.

[0387] "Voice input" refers to a means by which a user can give instructions to a device using voice recognition technology.

[0388] "Touch operation" refers to the means by which a user issues commands using the touchscreen of a device.

[0389] The present invention relates to a system for efficiently collecting, analyzing, and providing information about politicians. This system includes a server, a terminal, and a specific generative AI model.

[0390] 1. Data Collection

[0391] The server first collects data about politicians through an API on the Internet, including basic information about the politician, past achievements, statements in parliament, campaign promises, and ideology. For example, the server collects information through an API request using an ID number that identifies a specific politician.

[0392] 2. Data Preprocessing

[0393] The server then preprocesses the collected data, specifically removing unnecessary elements from the data and standardizing the string format, making the data easier to analyze.

[0394] 3. Summary information generation

[0395] The pre-processed data is then analyzed by a generative AI model, which uses natural language processing techniques to summarize the text data. The pre-processed text is tokenized and a summary is generated that succinctly summarizes the key points.

[0396] 4. Data storage and provision

[0397] The generated summary information is stored in a database by the server. In response to a user request, the server retrieves information from this database and provides it to the terminal via an API. If the terminal is a smart device (smart glasses or tablet), the user can search for information using voice input or touch operation.

[0398] 5. User Access

[0399] Users access the API endpoint using their device to retrieve the generated summary information, which is then displayed on the device in a format that is easy for users to understand.

[0400] Specific examples

[0401] This section explains the flow for obtaining information about a specific politician (e.g., ID: 12345) and generating a summary. In this case, the server first collects detailed information about politician ID: 12345 from the API. The collected data is then preprocessed and summary information is generated using a generative AI model. The generated summary information is stored in a database and returned to the device when the user submits a request. This series of processes allows the user to easily understand the politician's basic information and past achievements.

[0402] Prompt Sentence Examples

[0403] Below are some example prompts that users can use to request information using smart glasses:

[0404] A user puts on the smart glasses and requests information about a particular politician, for example, by saying "Show me information about politician ID 12345."

[0405] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0406] Step 1:

[0407] The server collects data about politicians using an API on the Internet. As input, it receives an ID number that identifies a specific politician and sends an API request. As output, it obtains detailed data such as the politician's basic information, past achievements, statements in parliament, campaign promises, and ideology.

[0408] Step 2:

[0409] The server pre-processes the collected data. As input, it receives the raw data from the API, removes unnecessary elements (e.g., HTML tags and extra spaces), and standardizes the string format. As output, it obtains pre-processed data that is easier to parse.

[0410] Step 3:

[0411] The server analyzes the preprocessed data using a generative AI model. As input, it receives the preprocessed text data, tokenizes it, and analyzes it. As output, it generates a summary of the politician's key points.

[0412] Step 4:

[0413] The server stores the generated summary information in a database. As input, it receives summary information from the generative AI model and stores it in the database. As output, it provides a database that is organized in a way that can respond to user requests.

[0414] Step 5:

[0415] A user accesses the server's API endpoint using a device and requests summary information. As input, the user sends a request about a specific politician (e.g., politician ID: 12345) using voice input or touch operation. As output, the user receives the summary information provided by the server on the device.

[0416] Step 6:

[0417] The terminal displays the received summary information. As input, it receives the summary information sent from the server and converts it into a format that is easy to display visually. As output, it displays it on the display in a format that is easy for the user to understand.

[0418] Step 7:

[0419] The user reviews the displayed information and, if necessary, asks additional questions or requests by voice or touch. As input, a new request or feedback is sent to the device. As output, a new request is generated to the server, and the information corresponding to the request is again collected, preprocessed, analyzed, and provided.

[0420] 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.

[0421] This invention relates to a system that efficiently collects, analyzes, and provides information about politicians, and also combines it with an emotion engine that recognizes the user's emotions. This system is composed of a server, a terminal, a generative AI model, a database, an emotion engine, etc.

[0422] 1. Data Collection

[0423] The server first collects data about politicians through an API on the Internet, including basic information about the politicians, their past performance, statements in parliament, campaign promises, and ideology.

[0424] 2. Data Preprocessing

[0425] The server preprocesses the collected data. Specifically, it removes unnecessary tags and spaces from the data and standardizes the string format. This preprocessing makes the data easier to analyze.

[0426] 3. Data analysis using generative AI

[0427] The server then analyzes the preprocessed data using a generative AI model. To do this, the preprocessed text is tokenized using a tokenizer and the tokens are input into the generative AI model, which then generates summary information.

[0428] 4. Data storage and provision

[0429] The generated summary information is stored in a database by the server. In response to a user request, the server retrieves information from this database and provides it to the terminal via an API. The user can access the summary information through the terminal and quickly obtain information that is relevant to them.

[0430] 5. Emotional Analysis of Users by Emotion Engine

[0431] The server also includes an emotion engine that recognizes the user's emotions. The emotion engine monitors the user's feedback and behavior during use, and analyzes emotions in real time. The analysis results are stored in a database and the presentation of summary information is adjusted based on the user's emotional state.

[0432] Specific examples

[0433] This section explains the process for obtaining information about a specific politician (e.g., ID: 12345) and generating a summary. In this case, the server collects detailed information about politician ID: 12345 from the API. The collected data is then preprocessed and summary information is generated using a generative AI model. The generated summary information is stored in a database and returned to the device when the user submits a request. Furthermore, when the user views the summary information, the server uses an emotion engine to analyze the user's emotions in real time and optimizes the presentation method based on the results. This series of processes not only allows the user to concisely grasp the politician's basic information and past performance, but also allows them to receive information optimally presented according to their emotions.

[0434] This system allows voters to efficiently obtain information about politicians and eliminate information imbalances. Furthermore, the emotion engine improves users' understanding and sense of satisfaction, thereby enhancing the fairness of elections.

[0435] The processing flow will be explained below.

[0436] This invention combines a system for efficiently collecting, analyzing, and providing information about politicians with an emotion engine that recognizes user emotions. This system is composed of a server, terminals, a generative AI model, a database, and an emotion engine.

[0437] Step 1:

[0438] The server first collects data about politicians through an API on the internet, which involves sending requests to specific API endpoints and receiving the returned data in JSON format.

[0439] Step 2:

[0440] The server preprocesses the collected data, which includes removing unnecessary tags and whitespace from the data and standardizing string formats, making the data easier to analyze.

[0441] Step 3:

[0442] The server analyzes the preprocessed data using a generative AI model. For this analysis, the preprocessed text is tokenized using a tokenizer and the tokens are input to the generative AI model. The generative AI model generates summary information from the tokenized text.

[0443] Step 4:

[0444] The server stores the generated summary information in a database, which includes the process of storing the summary information in a database and indexing the information for efficient retrieval.

[0445] Step 5:

[0446] The server retrieves the stored summary information from the database in response to a user request. This retrieval process involves searching the database based on the user request and extracting the relevant summary information as a search result.

[0447] Step 6:

[0448] The server provides the acquired summary information to the device via an API, allowing the user to access the summary information through the device and quickly obtain information about the politicians they need.

[0449] Step 7:

[0450] The device displays the summary information retrieved from the API to the user in a format that is easy for the user to understand, such as text, graphs, or images.

[0451] Step 8:

[0452] The server uses an emotion engine to monitor user feedback and behavior during use and analyze emotions in real time. For this analysis, it analyzes textual feedback and collects and analyzes device usage history data.

[0453] Step 9:

[0454] Based on the analysis results, the server adjusts the presentation of summary information according to the user's emotional state: for example, if the user is excited, it displays information in a clear and concise manner, while if the user is relaxed, it provides detailed information.

[0455] Step 10:

[0456] The user provides feedback through the terminal, which includes opinions and impressions about the provided summary information, and the server collects and stores the feedback in a database.

[0457] This system efficiently obtains information about politicians and presents information according to the user's emotions, thereby eliminating information imbalances and promoting fair election campaigns.

[0458] Example 2

[0459] 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."

[0460] In modern society, the amount of information about politicians is enormous, making it difficult for voters to grasp the overall picture. Furthermore, organizing and summarizing the collected information is time-consuming, and current systems do not provide information that takes into account the user's emotions. Therefore, there is a need for a system that can quickly provide appropriate information to users and present information in a way that suits their emotional state.

[0461] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting data on politicians, means for preprocessing the collected data, means for analyzing the preprocessed data using a generative AI model and generating summary information, means for saving the generated summary information in a database, and means for recognizing user emotions and optimizing the presentation method. This makes it possible to provide information on politicians to users quickly and efficiently, and further to present information optimally according to the user's emotions.

[0462] A "politician" is a public official or person who is running for or elected to public office or who holds a political role.

[0463] A "data collection tool" is a system or process for obtaining specific information from the Internet or other sources.

[0464] "Data preprocessing means" refers to a system or process for removing unnecessary elements from collected data and standardizing the data format.

[0465] A "generative AI model" is an artificial intelligence model that learns from large amounts of data and performs various tasks (e.g., summary generation, question answering).

[0466] A "summary generator" is a system or process for generating summary information from preprocessed data using a generative AI model.

[0467] "Database storage means" means a system or process for storing the generated summary information in a structured format in a database.

[0468] "Providing means" refers to a system or process for retrieving and providing information stored in a database in response to a user request.

[0469] An "emotion recognizer" is a system or process for analyzing a user's feedback and behavior to identify the user's emotional state.

[0470] A "presentation optimizer" is a system or process for adjusting the presentation of information based on the user's emotional state obtained by the emotion recognizer.

[0471] This invention is a system that efficiently collects, analyzes, and provides information about politicians, and also combines it with an emotion engine that recognizes the user's emotions. This system is composed of a server, a terminal, a generative AI model, a database, an emotion engine, etc.

[0472] The server first collects data about politicians through an API on the Internet. This data includes basic information about the politician, their past achievements, statements in parliament, campaign promises, and ideology. For example, information about politician ID: 12345 can be collected from a URL such as "https: / / api.example.com / politician / 12345."

[0473] Next, the server preprocesses the collected data. During this process, unnecessary tags and whitespace are removed and the string format is standardized. This preprocessing makes the data easier to analyze. For example, if HTML tags or special characters are included, they are removed and the date format is standardized to "YYYY-MM-DD".

[0474] The data is then analyzed using a generative AI model. The server tokenizes the preprocessed data using a tokenizer and inputs the tokens into a generative AI model. A large-scale language model (e.g., GPT-3) can be used as the generative AI model. This model is used to summarize the text and generate summary information. An example of a prompt sentence is, "Please summarize the basic information about politician ID: 12345."

[0475] The generated summary information is stored in a database by the server. This database typically uses a relational database such as SQL. When a user requests information through their device, the server retrieves the required information from the database and provides it to the device via an API. The user can then access the summary information using their device and obtain the information quickly.

[0476] Furthermore, the server uses an emotion engine to recognize the user's emotions. This emotion engine monitors and analyzes user feedback and usage behavior in real time. For example, it collects user click logs and page visit times and performs emotion analysis. The analysis results are stored in a database and the way summary information is presented is adjusted based on the user's emotional state. For example, detailed information is provided to users with positive emotions, and concise information is provided to users with negative emotions.

[0477] As a concrete example, we will explain the flow of obtaining information about a specific politician (e.g., ID: 12345) and generating a summary. In this case, the server collects detailed information about politician ID: 12345 from an API. The collected data is then preprocessed and summary information is generated using a generative AI model. The generated summary information is stored in a database and returned to the device when the user submits a request. Furthermore, when the user views the summary information, the server uses an emotion engine to analyze the user's emotions in real time and optimizes the presentation method based on the results. This series of processes not only allows the user to concisely grasp the politician's basic information and past performance, but also allows them to receive information that is optimally presented according to their emotions.

[0478] The system described above allows voters to efficiently obtain information about politicians and eliminate information imbalances. Furthermore, the emotion engine improves users' understanding and sense of satisfaction, potentially enhancing the fairness of elections.

[0479] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0480] Step 1:

[0481] Initializing and sending data collection

[0482] The server sets an interval to collect data about politicians using a pre-configured API endpoint. For example, it sets a timer to send an API request every hour. The server sends the API request to the URL "https: / / api.example.com / politician / 12345" and includes an API key or authentication token in the header, if necessary. The input at this point is the API request information, and the output is the response data from the API.

[0483] Step 2:

[0484] Data reception and preprocessing

[0485] The server receives a JSON-formatted response from the API. The received data includes basic information about politicians and their past achievements. This data is analyzed, unnecessary elements such as HTML tags and special characters are removed, and the format is standardized. For example, the date format is standardized to "YYYY-MM-DD." The input in this step is the API response data, and the output is clean data after preprocessing.

[0486] Step 3:

[0487] Data tokenization and summary generation

[0488] The server tokenizes the preprocessed text data using a tokenizer, which splits the sentence into words and phrases and generates an array of tokens. Next, the preprocessed data is input to a generative AI model (e.g., GPT-3) to generate summary information according to a prompt such as "Please summarize basic information about politician ID: 12345." The input in this step is the preprocessed data and the prompt, and the output is the generated summary information.

[0489] Step 4:

[0490] Save summary information

[0491] The server stores the generated summary information in a database. This process uses SQL queries to insert the summary information into the appropriate tables. The input to this step is the generated summary information, and the output is the summary information stored in the database.

[0492] Step 5:

[0493] Processing user requests and providing data

[0494] A user requests information about a particular politician through a terminal, for example, by submitting an information request through an application on the terminal or a web form. When the server receives this request, it retrieves the corresponding summary information from the database and returns it to the user terminal as a response in an appropriate format. The input in this step is the user request, and the output is the summary information provided to the user terminal.

[0495] Step 6:

[0496] User sentiment analysis and information presentation optimization

[0497] The server collects user feedback and behavioral data during use and analyzes it with an emotion engine. This engine analyzes data such as click logs and page visit times to identify the user's emotional state. For example, if there is a lot of negative feedback, it determines that the user is dissatisfied and changes the settings to provide more concise information. The input in this step is user behavior data, and the output is the emotion analysis results and adjustments to the information presentation method based on those results.

[0498] Combining these steps allows users to efficiently obtain detailed information about politicians and present it in the most relevant way based on their sentiment.

[0499] (Application example 2)

[0500] 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."

[0501] Conventional systems for collecting and analyzing information about politicians present information to users in a uniform manner, resulting in insufficient personalization based on the user's emotions and interests. Furthermore, when applied to advertising, this system suffers from the problem of reduced advertising effectiveness because it does not take into account the user's emotions. This makes it difficult to provide users with the information they desire quickly and appropriately, leading to information imbalances and lack of understanding.

[0502] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data on politicians, means for preprocessing the collected data, means for analyzing the preprocessed data using a generative AI model and generating summary information, means for saving the generated summary information in a database, means for providing the saved summary information in response to a user request, means for analyzing the user's emotions using an emotion engine that recognizes the user's emotions and adjusting the presentation method, and means for providing optimal advertisements based on the user's emotions. This makes it possible to present information and optimize advertisements taking into account the user's emotional state.

[0503] "Data on politicians" refers to information including basic information about politicians, past achievements, statements made in parliament, campaign promises, and ideology.

[0504] The "means of collection" refers to the means of obtaining data about politicians through APIs on the Internet, etc.

[0505] "Preprocessing means" refers to a means for removing unnecessary elements from collected data and standardizing the data format.

[0506] A "generative AI model" is an artificial intelligence model that analyzes tokenized text data using a tokenizer and generates summary information.

[0507] "Summary information" is concise information generated by a generative AI model based on data about politicians.

[0508] A "database" is a system for storing the generated summary information and providing the information in response to a user's request.

[0509] The "means for providing in response to a request from a user" refers to a means for providing summary information stored in a database to a terminal in response to a user request.

[0510] An "emotion engine" is software that recognizes and analyzes a user's emotions.

[0511] The "means for adjusting the presentation method" is a means for adjusting the method for presenting information to the user based on the analysis results of the emotion engine.

[0512] "Advertising" is marketing content that is provided in an optimal manner based on the user's emotions and interests.

[0513] This invention relates to a system that efficiently collects and analyzes information about politicians, and then recognizes users' emotions to present optimal advertisements. This system includes components such as a server, a terminal, a generative AI model, a database, and an emotion engine.

[0514] A specific embodiment is as follows.

[0515] 1. Data Collection

[0516] The server collects data about politicians through an API on the Internet, including basic information about the politicians, their past performance, statements in parliament, campaign promises, and beliefs.

[0517] 2. Data Preprocessing

[0518] The server preprocesses the collected data by removing unnecessary elements and standardizing the data format, making the data easier to analyze.

[0519] 3. Data analysis using generative AI models

[0520] The server inputs the preprocessed data into a generative AI model for analysis. This generative AI model uses a natural language processing tokenizer. The tokenizer tokenizes the text data and inputs it into the generative AI model to generate summary information. The generated summary information is stored in a database.

[0521] 4. Data provision

[0522] When a user sends a request from their terminal, the server retrieves the stored summary information from the database and provides it to the user's terminal, allowing the user to quickly access the information they need.

[0523] 5. Emotional Analysis of Users by Emotion Engine

[0524] The server analyzes the user's feedback and behavior during use using an emotion engine. The emotion engine monitors the user's emotional state in real time and stores the analysis results in a database. Based on this emotional data, the method of presenting information to the user is optimized.

[0525] 6. Providing optimal advertising

[0526] The server then presents the most appropriate advertisement based on the results of the user's emotion analysis. If the user's emotion is positive, the server provides more detailed information, and if the user's emotion is negative, the server provides less interesting information. In this way, advertisements are displayed that are tailored to the user's emotional state.

[0527] Specific examples

[0528] 1. Example prompt (input to the generative AI model):

[0529] "Please summarize the policies of the following politicians: Policy A is..."

[0530] 2. Example summary output from a generative AI model:

[0531] "Summary of Policy A: Policy A emphasizes social welfare..."

[0532] 3. Example of input for user sentiment analysis:

[0533] "Very interesting. I'd like to know more!"

[0534] 4. Example of user sentiment analysis results:

[0535] "emotion: positive"

[0536] This invention not only enables users to quickly and easily obtain information about politicians, but also allows them to receive optimal information and advertisements according to their emotions, which is expected to eliminate information imbalances and improve advertising effectiveness.

[0537] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0538] Step 1:

[0539] The server collects data about politicians through an API on the Internet. As input, it uses the API endpoint and politician ID. The data returned from the API includes basic information about the politician, past achievements, statements in parliament, campaign promises, and beliefs. The output is the collected data about the politician.

[0540] Step 2:

[0541] The server preprocesses the collected data. The data about politicians collected in step 1 is used as input for preprocessing. Specifically, it removes unnecessary tags and spaces from the data and standardizes the string format. This converts the data into a format that is easy to analyze. The output is the preprocessed data.

[0542] Step 3:

[0543] The server analyzes the preprocessed data using a generative AI model to generate summary information. As input, it uses a tokenizer to tokenize the preprocessed text data. The tokenized data is input to the generative AI model to obtain summary information. Specifically, the generative AI model analyzes the text data, extracts important information, and generates a summary. The output is the generated summary information.

[0544] Step 4:

[0545] The server stores the generated summary information in the database. It uses the summary information generated in step 3 as input. Specific operations include converting the summary information into an appropriate format and storing it in the database. The output is confirmation data of the stored summary information.

[0546] Step 5:

[0547] When a user sends a request from their device, the server retrieves the stored summary information from the database and provides it to the user's device. The input is a request from the user. Specifically, the server sends a query to the database, retrieves the corresponding summary information, and sends it to the device. The output is the summary information displayed on the user's device.

[0548] Step 6:

[0549] The user's device collects user feedback and usage behavior from time to time and sends it to the server. The input includes user feedback and operation logs during usage. The output is the feedback data sent to the server.

[0550] Step 7:

[0551] The server uses the emotion engine to analyze the user's emotions. The input is the user's feedback data sent in step 6. Specifically, the emotion engine analyzes the feedback data and extracts the user's emotional state (positive, negative, etc.). The output is the analyzed user's emotion data.

[0552] Step 8:

[0553] The server selects and serves the most appropriate advertisement based on the results of the user's sentiment analysis. The inputs are the sentiment analysis results from step 7 and the advertisement information stored in the database. Specifically, the server selects the advertisement that is most suitable for the user based on the sentiment analysis results and sends it to the terminal. The output is the most appropriate advertisement that is displayed on the user's terminal.

[0554] This allows users to not only efficiently obtain information about politicians, but also receive advertisements that are most appropriate for their emotions.

[0555] 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.

[0556] 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.

[0557] 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.

[0558] [Third embodiment]

[0559] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0560] 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.

[0561] 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).

[0562] 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.

[0563] 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.

[0564] 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).

[0565] 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.

[0566] 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.

[0567] 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.

[0568] 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.

[0569] 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.

[0570] 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."

[0571] The present invention relates to a system for efficiently collecting, analyzing, and providing information about politicians. This system is composed of a server, a terminal, a generative AI model, a database, etc.

[0572] 1. Data Collection

[0573] The server first collects data about politicians through an API on the Internet, including basic information about the politicians, their past performance, statements in parliament, campaign promises, and ideology.

[0574] 2. Data Preprocessing

[0575] The server preprocesses the collected data. Specifically, it removes unnecessary tags and spaces from the data and standardizes the string format. This preprocessing makes the data easier to analyze.

[0576] 3. Data analysis using generative AI

[0577] The server then analyzes the preprocessed data with a generative AI model, which tokenizes the preprocessed text and generates a summary that succinctly summarizes the politician's key data.

[0578] 4. Data storage and provision

[0579] The generated summary information is stored in a database by the server. In response to a user request, the server retrieves information from this database and provides it to the terminal via an API. The user can access the summary information through the terminal and quickly obtain information that is relevant to them.

[0580] 5. User Access and Feedback

[0581] Users access the API endpoint using their devices to obtain the generated summary information. The obtained information is displayed on the device in a format that is easy for users to understand. Furthermore, by adding a feedback function, opinions and feedback provided by users can be collected and analyzed on the server to help improve the system.

[0582] Specific examples

[0583] This section explains the flow for obtaining information about a specific politician (e.g., ID: 12345) and generating a summary. In this case, the server first collects detailed information about politician ID: 12345 from the API. The collected data is then preprocessed and summary information is generated using a generative AI model. The generated summary information is stored in a database and returned to the device when the user submits a request. This series of processes allows the user to easily understand the politician's basic information and past achievements.

[0584] This system will enable voters to efficiently obtain information about politicians and eliminate information imbalances, thereby increasing the fairness of elections and promoting election campaigns that reflect the will of the people.

[0585] The processing flow will be explained below.

[0586] Step 1:

[0587] The server collects data about politicians through an API on the Internet by sending a request for a specific politician to the API and receiving the returned data in JSON format.

[0588] Step 2:

[0589] The server preprocesses the collected data, specifically removing unnecessary tags and whitespace from the data and standardizing the string format, which makes subsequent analysis easier.

[0590] Step 3:

[0591] The server analyzes the preprocessed data using a generative AI model. For this analysis, the preprocessed text is tokenized using a tokenizer and the tokens are input into the generative AI model. The AI ​​then generates summary information.

[0592] Step 4:

[0593] The server stores the generated summary information in a database, which includes basic information about the politician, their past achievements, and campaign promises.

[0594] Step 5:

[0595] The server retrieves the stored summary information from the database in response to a user request and provides the retrieved summary information to the user via the API.

[0596] Step 6:

[0597] A user accesses the API endpoint using a device and requests summary information about a specific politician. The device receives a response from the server and displays the summary information on the screen.

[0598] Step 7:

[0599] Based on the provided summary information, users can understand basic information about politicians, their past achievements, campaign promises, etc. If necessary, they can use the feedback function to send opinions that will help improve the system to the server.

[0600] Through this series of steps, the server, terminal, and user work together to efficiently collect, analyze, and provide information about politicians.

[0601] Example 1

[0602] 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."

[0603] Conventional politician information gathering systems lack the ability to efficiently collect, preprocess, and analyze massive amounts of data and easily provide it to users. As a result, information imbalances arise, and users are unable to quickly access the information on politicians they need. Furthermore, there is an insufficient mechanism for incorporating user feedback into system improvements, making it difficult to improve the quality of the system.

[0604] 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.

[0605] In this invention, the server includes means for collecting data from the Internet, means for deleting unnecessary information from the collected data and standardizing the format, means for analyzing the preprocessed data using a generative AI model to generate summary information, means for saving the generated summary information in a database, means for providing the saved summary information in response to a user request, and means for collecting feedback from users and using it to improve the system. This enables efficient data collection, analysis, and provision, allowing users to quickly obtain the politician information they need, and enabling system improvements based on user feedback.

[0606] "Internet data" refers to any information accessible through the internet, often obtained through APIs.

[0607] "Nonessential information" refers to data that is not important or useful for a particular data analysis or purpose.

[0608] "Unifying the format" refers to the process of arranging the collected data into a consistent structure so that it can be easily analyzed and processed.

[0609] A "generative AI model" is an artificial intelligence model that generates a specific output based on given input data. A natural language processing model is typically used.

[0610] "Summary information" refers to information that has been compiled concisely and clearly by extracting only the important points from detailed data.

[0611] A "database" is a system designed to allow the efficient retrieval, storage, and updating of stored data.

[0612] A "request" refers to a request or inquiry made by a user to a server.

[0613] "Feedback" refers to opinions and impressions provided by users after using the system, and is information used to improve the system.

[0614] This invention is a system that efficiently collects, preprocesses, analyzes, and provides information about politicians to users. This system mainly uses a server, a terminal, a generative AI model, and a database.

[0615] First, the server collects data from the Internet. Specifically, the server obtains data about politicians through an API on the Internet. For example, this includes basic information about politicians, their past achievements, statements in parliament, campaign promises, and ideology.

[0616] The server then preprocesses the collected data, removing unnecessary information and standardizing the format. For example, it uses Python's Pandas and regular expression libraries to remove unnecessary tags and whitespace, and ensure consistent string formatting.

[0617] The server then analyzes the preprocessed data using a generative AI model, such as OpenAI's GPT-3, which tokenizes the preprocessed text and extracts key points to generate a summary.

[0618] The generated summary information is stored in a database by the server. The database is a relational database management system such as PostgreSQL. When a user makes a request, the server retrieves the necessary summary information from the database and provides it to the terminal via the API.

[0619] Users can access the API endpoint using their devices to obtain the generated summary information. The obtained information is displayed on the device in a format that is easy for users to understand. In addition, the system has a feedback function that collects user opinions and feedback, which will be used to improve the system.

[0620] As a concrete example, we will explain the flow for obtaining information about a specific politician (e.g., ID: 12345) and generating a summary. In this case, the server first collects detailed information about politician ID: 12345 from the API. Then, it preprocesses the collected data and generates summary information using a generative AI model. This summary information is stored in a database and is returned to the device when the user submits a request.

[0621] Examples of prompts include:

[0622] "summarize the following text about the politician: 'Politician's statements and promises... (preprocessed data)'"

[0623] "SELECT FROM politician_summary WHERE politician_id = 12345;"

[0624] This system allows users to quickly access important information about politicians, helping them make decisions efficiently. Furthermore, the system will be improved based on user feedback, further enhancing its quality.

[0625] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0626] Step 1:

[0627] The server collects data about politicians through an API on the Internet. Specifically, the server sends a request to a specific API endpoint and retrieves detailed information by specifying the politician's ID. The input of this process is the politician's ID, and the output is the retrieved detailed information.

[0628] Step 2:

[0629] The server preprocesses the collected data. Specifically, it removes unnecessary tags and whitespace from the data and standardizes the string format. The input of this process is the raw data obtained, and the output is the preprocessed data. Python's Pandas and regular expression libraries are used to remove unnecessary elements and convert the data into a consistent format.

[0630] Step 3:

[0631] The server sends the preprocessed data to a generative AI model (e.g., GPT-3), which tokenizes the provided text and generates a summary. The input of this process is the preprocessed text data, and the output is the generated summary.

[0632] Step 4:

[0633] The server stores the generated summary information in a database. The database uses a relational database management system (e.g., PostgreSQL) that allows efficient searching, storage, and updating. The input of this process is the generated summary information, and the output is the summary information stored in the database.

[0634] Step 5:

[0635] The server receives requests from users and provides the stored summary information. A user uses a device to access the API endpoint and request summary information for a specific politician. The input of this process is the user request, and the output is the summary information according to the request.

[0636] Step 6:

[0637] The user accesses the API endpoint using a terminal and retrieves the generated summary information, which is then displayed on the user's terminal. The input of this process is the summary information provided by the server, and the output is the summary information displayed on the terminal.

[0638] Step 7:

[0639] Users send their opinions and thoughts to the server through the feedback function. The server collects this feedback and uses it to improve the system. The input of this process is the user feedback, and the output is the analyzed feedback information.

[0640] This series of processes enables efficient collection, analysis, and provision of information about politicians, resulting in a system that allows users to quickly obtain the information they need.

[0641] (Application example 1)

[0642] 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."

[0643] Conventional political information systems require complicated information collection, analysis, and provision, making it difficult for users to quickly and easily obtain the information they require. Furthermore, the devices and methods for viewing information in real time were limited, resulting in an inadequate user experience. Furthermore, there was a lack of systems that allowed users to intuitively search for information using voice input or touch operations.

[0644] 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.

[0645] In this invention, the server includes means for collecting data on politicians, means for preprocessing the collected data, means for analyzing the preprocessed data using a generative AI model and generating summary information, means for saving the generated summary information in a database, means for providing the saved summary information in response to a user request, means for allowing the user to view information displayed on the smart device, and means for the user to search for information on politicians using voice input or touch operation. This allows users to quickly and easily obtain the information they need about politicians and to view the information in real time using intuitive operations.

[0646] "Data on politicians" refers to basic information about politicians, their past achievements, statements in parliament, campaign promises, beliefs, and other related information.

[0647] "Means of collection" refers to devices or software for obtaining data about politicians using APIs on the Internet, etc.

[0648] "Preprocessing means" refers to a device or software for removing unnecessary elements from collected data and standardizing the data format.

[0649] A "generative AI model" refers to an artificial intelligence model that uses natural language processing technology to analyze text data and generate summary information and related information.

[0650] "Means for generating summary information" refers to a device or software that analyzes preprocessed data using a generative AI model and generates information that succinctly summarizes the key points.

[0651] "Means for storing in a database" refers to a storage device or software for storing the generated summary information and retrieving it when necessary.

[0652] The "means for providing" refers to a device or software for obtaining summary information from a database in response to a user request and transmitting the information to a user terminal.

[0653] "Smart Device" refers to smartphones, smart glasses, tablets and other internet-enabled portable information terminals.

[0654] "Voice input" refers to a means by which a user can give instructions to a device using voice recognition technology.

[0655] "Touch operation" refers to the means by which a user issues commands using the touchscreen of a device.

[0656] The present invention relates to a system for efficiently collecting, analyzing, and providing information about politicians. This system includes a server, a terminal, and a specific generative AI model.

[0657] 1. Data Collection

[0658] The server first collects data about politicians through an API on the Internet, including basic information about the politician, past achievements, statements in parliament, campaign promises, and ideology. For example, the server collects information through an API request using an ID number that identifies a specific politician.

[0659] 2. Data Preprocessing

[0660] The server then preprocesses the collected data, specifically removing unnecessary elements from the data and standardizing the string format, making the data easier to analyze.

[0661] 3. Summary information generation

[0662] The pre-processed data is then analyzed by a generative AI model, which uses natural language processing techniques to summarize the text data. The pre-processed text is tokenized and a summary is generated that succinctly summarizes the key points.

[0663] 4. Data storage and provision

[0664] The generated summary information is stored in a database by the server. In response to a user request, the server retrieves information from this database and provides it to the terminal via an API. If the terminal is a smart device (smart glasses or tablet), the user can search for information using voice input or touch operation.

[0665] 5. User Access

[0666] Users access the API endpoint using their device to retrieve the generated summary information, which is then displayed on the device in a format that is easy for users to understand.

[0667] Specific examples

[0668] This section explains the flow for obtaining information about a specific politician (e.g., ID: 12345) and generating a summary. In this case, the server first collects detailed information about politician ID: 12345 from the API. The collected data is then preprocessed and summary information is generated using a generative AI model. The generated summary information is stored in a database and returned to the device when the user submits a request. This series of processes allows the user to easily understand the politician's basic information and past achievements.

[0669] Prompt Sentence Examples

[0670] Below are some example prompts that users can use to request information using smart glasses:

[0671] A user puts on the smart glasses and requests information about a particular politician, for example, by saying "Show me information about politician ID 12345."

[0672] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0673] Step 1:

[0674] The server collects data about politicians using an API on the Internet. As input, it receives an ID number that identifies a specific politician and sends an API request. As output, it obtains detailed data such as the politician's basic information, past achievements, statements in parliament, campaign promises, and ideology.

[0675] Step 2:

[0676] The server pre-processes the collected data. As input, it receives the raw data from the API, removes unnecessary elements (e.g., HTML tags and extra spaces), and standardizes the string format. As output, it obtains pre-processed data that is easier to parse.

[0677] Step 3:

[0678] The server analyzes the preprocessed data using a generative AI model. As input, it receives the preprocessed text data, tokenizes it, and analyzes it. As output, it generates a summary of the politician's key points.

[0679] Step 4:

[0680] The server stores the generated summary information in a database. As input, it receives summary information from the generative AI model and stores it in the database. As output, it provides a database that is organized in a way that can respond to user requests.

[0681] Step 5:

[0682] A user accesses the server's API endpoint using a device and requests summary information. As input, the user sends a request about a specific politician (e.g., politician ID: 12345) using voice input or touch operation. As output, the user receives the summary information provided by the server on the device.

[0683] Step 6:

[0684] The terminal displays the received summary information. As input, it receives the summary information sent from the server and converts it into a format that is easy to display visually. As output, it displays it on the display in a format that is easy for the user to understand.

[0685] Step 7:

[0686] The user reviews the displayed information and, if necessary, asks additional questions or requests by voice or touch. As input, a new request or feedback is sent to the device. As output, a new request is generated to the server, and the information corresponding to the request is again collected, preprocessed, analyzed, and provided.

[0687] 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.

[0688] This invention relates to a system that efficiently collects, analyzes, and provides information about politicians, and also combines it with an emotion engine that recognizes the user's emotions. This system is composed of a server, a terminal, a generative AI model, a database, an emotion engine, etc.

[0689] 1. Data Collection

[0690] The server first collects data about politicians through an API on the Internet, including basic information about the politicians, their past performance, statements in parliament, campaign promises, and ideology.

[0691] 2. Data Preprocessing

[0692] The server preprocesses the collected data. Specifically, it removes unnecessary tags and spaces from the data and standardizes the string format. This preprocessing makes the data easier to analyze.

[0693] 3. Data analysis using generative AI

[0694] The server then analyzes the preprocessed data using a generative AI model. To do this, the preprocessed text is tokenized using a tokenizer and the tokens are input into the generative AI model, which then generates summary information.

[0695] 4. Data storage and provision

[0696] The generated summary information is stored in a database by the server. In response to a user request, the server retrieves information from this database and provides it to the terminal via an API. The user can access the summary information through the terminal and quickly obtain information that is relevant to them.

[0697] 5. Emotional Analysis of Users by Emotion Engine

[0698] The server also includes an emotion engine that recognizes the user's emotions. The emotion engine monitors the user's feedback and behavior during use, and analyzes emotions in real time. The analysis results are stored in a database and the presentation of summary information is adjusted based on the user's emotional state.

[0699] Specific examples

[0700] This section explains the process for obtaining information about a specific politician (e.g., ID: 12345) and generating a summary. In this case, the server collects detailed information about politician ID: 12345 from the API. The collected data is then preprocessed and summary information is generated using a generative AI model. The generated summary information is stored in a database and returned to the device when the user submits a request. Furthermore, when the user views the summary information, the server uses an emotion engine to analyze the user's emotions in real time and optimizes the presentation method based on the results. This series of processes not only allows the user to concisely grasp the politician's basic information and past performance, but also allows them to receive information optimally presented according to their emotions.

[0701] This system allows voters to efficiently obtain information about politicians and eliminate information imbalances. Furthermore, the emotion engine improves users' understanding and sense of satisfaction, thereby enhancing the fairness of elections.

[0702] The processing flow will be explained below.

[0703] This invention combines a system for efficiently collecting, analyzing, and providing information about politicians with an emotion engine that recognizes user emotions. This system is composed of a server, terminals, a generative AI model, a database, and an emotion engine.

[0704] Step 1:

[0705] The server first collects data about politicians through an API on the internet, which involves sending requests to specific API endpoints and receiving the returned data in JSON format.

[0706] Step 2:

[0707] The server preprocesses the collected data, which includes removing unnecessary tags and whitespace from the data and standardizing string formats, making the data easier to analyze.

[0708] Step 3:

[0709] The server analyzes the preprocessed data using a generative AI model. For this analysis, the preprocessed text is tokenized using a tokenizer and the tokens are input to the generative AI model. The generative AI model generates summary information from the tokenized text.

[0710] Step 4:

[0711] The server stores the generated summary information in a database, which includes the process of storing the summary information in a database and indexing the information for efficient retrieval.

[0712] Step 5:

[0713] The server retrieves the stored summary information from the database in response to a user request. This retrieval process involves searching the database based on the user request and extracting the relevant summary information as a search result.

[0714] Step 6:

[0715] The server provides the acquired summary information to the device via an API, allowing the user to access the summary information through the device and quickly obtain information about the politicians they need.

[0716] Step 7:

[0717] The device displays the summary information retrieved from the API to the user in a format that is easy for the user to understand, such as text, graphs, or images.

[0718] Step 8:

[0719] The server uses an emotion engine to monitor user feedback and behavior during use and analyze emotions in real time. For this analysis, it analyzes textual feedback and collects and analyzes device usage history data.

[0720] Step 9:

[0721] Based on the analysis results, the server adjusts the presentation of summary information according to the user's emotional state: for example, if the user is excited, it displays information in a clear and concise manner, while if the user is relaxed, it provides detailed information.

[0722] Step 10:

[0723] The user provides feedback through the terminal, which includes opinions and impressions about the provided summary information, and the server collects and stores the feedback in a database.

[0724] This system efficiently obtains information about politicians and presents information according to the user's emotions, thereby eliminating information imbalances and promoting fair election campaigns.

[0725] Example 2

[0726] 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."

[0727] In modern society, the amount of information about politicians is enormous, making it difficult for voters to grasp the overall picture. Furthermore, organizing and summarizing the collected information is time-consuming, and current systems do not provide information that takes into account the user's emotions. Therefore, there is a need for a system that can quickly provide appropriate information to users and present information in a way that suits their emotional state.

[0728] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting data on politicians, means for preprocessing the collected data, means for analyzing the preprocessed data using a generative AI model and generating summary information, means for saving the generated summary information in a database, and means for recognizing user emotions and optimizing the presentation method. This makes it possible to provide information on politicians to users quickly and efficiently, and further to present information optimally according to the user's emotions.

[0729] A "politician" is a public official or person who is running for or elected to public office or who holds a political role.

[0730] A "data collection tool" is a system or process for obtaining specific information from the Internet or other sources.

[0731] "Data preprocessing means" refers to a system or process for removing unnecessary elements from collected data and standardizing the data format.

[0732] A "generative AI model" is an artificial intelligence model that learns from large amounts of data and performs various tasks (e.g., summary generation, question answering).

[0733] A "summary generator" is a system or process for generating summary information from preprocessed data using a generative AI model.

[0734] "Database storage means" means a system or process for storing the generated summary information in a structured format in a database.

[0735] "Providing means" refers to a system or process for retrieving and providing information stored in a database in response to a user request.

[0736] An "emotion recognizer" is a system or process for analyzing a user's feedback and behavior to identify the user's emotional state.

[0737] A "presentation optimizer" is a system or process for adjusting the presentation of information based on the user's emotional state obtained by the emotion recognizer.

[0738] This invention is a system that efficiently collects, analyzes, and provides information about politicians, and also combines it with an emotion engine that recognizes the user's emotions. This system is composed of a server, a terminal, a generative AI model, a database, an emotion engine, etc.

[0739] The server first collects data about politicians through an API on the Internet. This data includes basic information about the politician, their past achievements, statements in parliament, campaign promises, and ideology. For example, information about politician ID: 12345 can be collected from a URL such as "https: / / api.example.com / politician / 12345."

[0740] Next, the server preprocesses the collected data. During this process, unnecessary tags and whitespace are removed and the string format is standardized. This preprocessing makes the data easier to analyze. For example, if HTML tags or special characters are included, they are removed and the date format is standardized to "YYYY-MM-DD".

[0741] The data is then analyzed using a generative AI model. The server tokenizes the preprocessed data using a tokenizer and inputs the tokens into a generative AI model. A large-scale language model (e.g., GPT-3) can be used as the generative AI model. This model is used to summarize the text and generate summary information. An example of a prompt sentence is, "Please summarize the basic information about politician ID: 12345."

[0742] The generated summary information is stored in a database by the server. This database typically uses a relational database such as SQL. When a user requests information through their device, the server retrieves the required information from the database and provides it to the device via an API. The user can then access the summary information using their device and obtain the information quickly.

[0743] Furthermore, the server uses an emotion engine to recognize the user's emotions. This emotion engine monitors and analyzes user feedback and usage behavior in real time. For example, it collects user click logs and page visit times and performs emotion analysis. The analysis results are stored in a database and the way summary information is presented is adjusted based on the user's emotional state. For example, detailed information is provided to users with positive emotions, and concise information is provided to users with negative emotions.

[0744] As a concrete example, we will explain the flow of obtaining information about a specific politician (e.g., ID: 12345) and generating a summary. In this case, the server collects detailed information about politician ID: 12345 from an API. The collected data is then preprocessed and summary information is generated using a generative AI model. The generated summary information is stored in a database and returned to the device when the user submits a request. Furthermore, when the user views the summary information, the server uses an emotion engine to analyze the user's emotions in real time and optimizes the presentation method based on the results. This series of processes not only allows the user to concisely grasp the politician's basic information and past performance, but also allows them to receive information that is optimally presented according to their emotions.

[0745] The system described above allows voters to efficiently obtain information about politicians and eliminate information imbalances. Furthermore, the emotion engine improves users' understanding and sense of satisfaction, potentially enhancing the fairness of elections.

[0746] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0747] Step 1:

[0748] Initializing and sending data collection

[0749] The server sets an interval to collect data about politicians using a pre-configured API endpoint. For example, it sets a timer to send an API request every hour. The server sends the API request to the URL "https: / / api.example.com / politician / 12345" and includes an API key or authentication token in the header, if necessary. The input at this point is the API request information, and the output is the response data from the API.

[0750] Step 2:

[0751] Data reception and preprocessing

[0752] The server receives a JSON-formatted response from the API. The received data includes basic information about politicians and their past achievements. This data is analyzed, unnecessary elements such as HTML tags and special characters are removed, and the format is standardized. For example, the date format is standardized to "YYYY-MM-DD." The input in this step is the API response data, and the output is clean data after preprocessing.

[0753] Step 3:

[0754] Data tokenization and summary generation

[0755] The server tokenizes the preprocessed text data using a tokenizer, which splits the sentence into words and phrases and generates an array of tokens. Next, the preprocessed data is input to a generative AI model (e.g., GPT-3) to generate summary information according to a prompt such as "Please summarize basic information about politician ID: 12345." The input in this step is the preprocessed data and the prompt, and the output is the generated summary information.

[0756] Step 4:

[0757] Save summary information

[0758] The server stores the generated summary information in a database. This process uses SQL queries to insert the summary information into the appropriate tables. The input to this step is the generated summary information, and the output is the summary information stored in the database.

[0759] Step 5:

[0760] Processing user requests and providing data

[0761] A user requests information about a particular politician through a terminal, for example, by submitting an information request through an application on the terminal or a web form. When the server receives this request, it retrieves the corresponding summary information from the database and returns it to the user terminal as a response in an appropriate format. The input in this step is the user request, and the output is the summary information provided to the user terminal.

[0762] Step 6:

[0763] User sentiment analysis and information presentation optimization

[0764] The server collects user feedback and behavioral data during use and analyzes it with an emotion engine. This engine analyzes data such as click logs and page visit times to identify the user's emotional state. For example, if there is a lot of negative feedback, it determines that the user is dissatisfied and changes the settings to provide more concise information. The input in this step is user behavior data, and the output is the emotion analysis results and adjustments to the information presentation method based on those results.

[0765] Combining these steps allows users to efficiently obtain detailed information about politicians and present it in the most relevant way based on their sentiment.

[0766] (Application example 2)

[0767] 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."

[0768] Conventional systems for collecting and analyzing information about politicians present information to users in a uniform manner, resulting in insufficient personalization based on the user's emotions and interests. Furthermore, when applied to advertising, this system suffers from the problem of reduced advertising effectiveness because it does not take into account the user's emotions. This makes it difficult to provide users with the information they desire quickly and appropriately, leading to information imbalances and lack of understanding.

[0769] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data on politicians, means for preprocessing the collected data, means for analyzing the preprocessed data using a generative AI model and generating summary information, means for saving the generated summary information in a database, means for providing the saved summary information in response to a user request, means for analyzing the user's emotions using an emotion engine that recognizes the user's emotions and adjusting the presentation method, and means for providing optimal advertisements based on the user's emotions. This makes it possible to present information and optimize advertisements taking into account the user's emotional state.

[0770] "Data on politicians" refers to information including basic information about politicians, past achievements, statements made in parliament, campaign promises, and ideology.

[0771] The "means of collection" refers to the means of obtaining data about politicians through APIs on the Internet, etc.

[0772] "Preprocessing means" refers to a means for removing unnecessary elements from collected data and standardizing the data format.

[0773] A "generative AI model" is an artificial intelligence model that analyzes tokenized text data using a tokenizer and generates summary information.

[0774] "Summary information" is concise information generated by a generative AI model based on data about politicians.

[0775] A "database" is a system for storing the generated summary information and providing the information in response to a user's request.

[0776] The "means for providing in response to a request from a user" refers to a means for providing summary information stored in a database to a terminal in response to a user request.

[0777] An "emotion engine" is software that recognizes and analyzes a user's emotions.

[0778] The "means for adjusting the presentation method" is a means for adjusting the method for presenting information to the user based on the analysis results of the emotion engine.

[0779] "Advertising" is marketing content that is provided in an optimal manner based on the user's emotions and interests.

[0780] This invention relates to a system that efficiently collects and analyzes information about politicians, and then recognizes users' emotions to present optimal advertisements. This system includes components such as a server, a terminal, a generative AI model, a database, and an emotion engine.

[0781] A specific embodiment is as follows.

[0782] 1. Data Collection

[0783] The server collects data about politicians through an API on the Internet, including basic information about the politicians, their past performance, statements in parliament, campaign promises, and beliefs.

[0784] 2. Data Preprocessing

[0785] The server preprocesses the collected data by removing unnecessary elements and standardizing the data format, making the data easier to analyze.

[0786] 3. Data analysis using generative AI models

[0787] The server inputs the preprocessed data into a generative AI model for analysis. This generative AI model uses a natural language processing tokenizer. The tokenizer tokenizes the text data and inputs it into the generative AI model to generate summary information. The generated summary information is stored in a database.

[0788] 4. Data provision

[0789] When a user sends a request from their terminal, the server retrieves the stored summary information from the database and provides it to the user's terminal, allowing the user to quickly access the information they need.

[0790] 5. Emotional Analysis of Users by Emotion Engine

[0791] The server analyzes the user's feedback and behavior during use using an emotion engine. The emotion engine monitors the user's emotional state in real time and stores the analysis results in a database. Based on this emotional data, the method of presenting information to the user is optimized.

[0792] 6. Providing optimal advertising

[0793] The server then presents the most appropriate advertisement based on the results of the user's emotion analysis. If the user's emotion is positive, the server provides more detailed information, and if the user's emotion is negative, the server provides less interesting information. In this way, advertisements are displayed that are tailored to the user's emotional state.

[0794] Specific examples

[0795] 1. Example prompt (input to the generative AI model):

[0796] "Please summarize the policies of the following politicians: Policy A is..."

[0797] 2. Example summary output from a generative AI model:

[0798] "Summary of Policy A: Policy A emphasizes social welfare..."

[0799] 3. Example of input for user sentiment analysis:

[0800] "Very interesting. I'd like to know more!"

[0801] 4. Example of user sentiment analysis results:

[0802] "emotion: positive"

[0803] This invention not only enables users to quickly and easily obtain information about politicians, but also allows them to receive optimal information and advertisements according to their emotions, which is expected to eliminate information imbalances and improve advertising effectiveness.

[0804] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0805] Step 1:

[0806] The server collects data about politicians through an API on the Internet. As input, it uses the API endpoint and politician ID. The data returned from the API includes basic information about the politician, past achievements, statements in parliament, campaign promises, and beliefs. The output is the collected data about the politician.

[0807] Step 2:

[0808] The server preprocesses the collected data. The data about politicians collected in step 1 is used as input for preprocessing. Specifically, it removes unnecessary tags and spaces from the data and standardizes the string format. This converts the data into a format that is easy to analyze. The output is the preprocessed data.

[0809] Step 3:

[0810] The server analyzes the preprocessed data using a generative AI model to generate summary information. As input, it uses a tokenizer to tokenize the preprocessed text data. The tokenized data is input to the generative AI model to obtain summary information. Specifically, the generative AI model analyzes the text data, extracts important information, and generates a summary. The output is the generated summary information.

[0811] Step 4:

[0812] The server stores the generated summary information in the database. It uses the summary information generated in step 3 as input. Specific operations include converting the summary information into an appropriate format and storing it in the database. The output is confirmation data of the stored summary information.

[0813] Step 5:

[0814] When a user sends a request from their device, the server retrieves the stored summary information from the database and provides it to the user's device. The input is a request from the user. Specifically, the server sends a query to the database, retrieves the corresponding summary information, and sends it to the device. The output is the summary information displayed on the user's device.

[0815] Step 6:

[0816] The user's device collects user feedback and usage behavior from time to time and sends it to the server. The input includes user feedback and operation logs during usage. The output is the feedback data sent to the server.

[0817] Step 7:

[0818] The server uses the emotion engine to analyze the user's emotions. The input is the user's feedback data sent in step 6. Specifically, the emotion engine analyzes the feedback data and extracts the user's emotional state (positive, negative, etc.). The output is the analyzed user's emotion data.

[0819] Step 8:

[0820] The server selects and serves the most appropriate advertisement based on the results of the user's sentiment analysis. The inputs are the sentiment analysis results from step 7 and the advertisement information stored in the database. Specifically, the server selects the advertisement that is most suitable for the user based on the sentiment analysis results and sends it to the terminal. The output is the most appropriate advertisement that is displayed on the user's terminal.

[0821] This allows users to not only efficiently obtain information about politicians, but also receive advertisements that are most appropriate for their emotions.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] [Fourth embodiment]

[0826] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0827] 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.

[0828] 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).

[0829] 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.

[0830] 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.

[0831] 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).

[0832] 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.

[0833] 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.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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."

[0839] The present invention relates to a system for efficiently collecting, analyzing, and providing information about politicians. This system is composed of a server, a terminal, a generative AI model, a database, etc.

[0840] 1. Data Collection

[0841] The server first collects data about politicians through an API on the Internet, including basic information about the politicians, their past performance, statements in parliament, campaign promises, and ideology.

[0842] 2. Data Preprocessing

[0843] The server preprocesses the collected data. Specifically, it removes unnecessary tags and spaces from the data and standardizes the string format. This preprocessing makes the data easier to analyze.

[0844] 3. Data analysis using generative AI

[0845] The server then analyzes the preprocessed data with a generative AI model, which tokenizes the preprocessed text and generates a summary that succinctly summarizes the politician's key data.

[0846] 4. Data storage and provision

[0847] The generated summary information is stored in a database by the server. In response to a user request, the server retrieves information from this database and provides it to the terminal via an API. The user can access the summary information through the terminal and quickly obtain information that is relevant to them.

[0848] 5. User Access and Feedback

[0849] Users access the API endpoint using their devices to obtain the generated summary information. The obtained information is displayed on the device in a format that is easy for users to understand. Furthermore, by adding a feedback function, opinions and feedback provided by users can be collected and analyzed on the server to help improve the system.

[0850] Specific examples

[0851] This section explains the flow for obtaining information about a specific politician (e.g., ID: 12345) and generating a summary. In this case, the server first collects detailed information about politician ID: 12345 from the API. The collected data is then preprocessed and summary information is generated using a generative AI model. The generated summary information is stored in a database and returned to the device when the user submits a request. This series of processes allows the user to easily understand the politician's basic information and past achievements.

[0852] This system will enable voters to efficiently obtain information about politicians and eliminate information imbalances, thereby increasing the fairness of elections and promoting election campaigns that reflect the will of the people.

[0853] The processing flow will be explained below.

[0854] Step 1:

[0855] The server collects data about politicians through an API on the Internet by sending a request for a specific politician to the API and receiving the returned data in JSON format.

[0856] Step 2:

[0857] The server preprocesses the collected data, specifically removing unnecessary tags and whitespace from the data and standardizing the string format, which makes subsequent analysis easier.

[0858] Step 3:

[0859] The server analyzes the preprocessed data using a generative AI model. For this analysis, the preprocessed text is tokenized using a tokenizer and the tokens are input into the generative AI model. The AI ​​then generates summary information.

[0860] Step 4:

[0861] The server stores the generated summary information in a database, which includes basic information about the politician, their past achievements, and campaign promises.

[0862] Step 5:

[0863] The server retrieves the stored summary information from the database in response to a user request and provides the retrieved summary information to the user via the API.

[0864] Step 6:

[0865] A user accesses the API endpoint using a device and requests summary information about a specific politician. The device receives a response from the server and displays the summary information on the screen.

[0866] Step 7:

[0867] Based on the provided summary information, users can understand basic information about politicians, their past achievements, campaign promises, etc. If necessary, they can use the feedback function to send opinions that will help improve the system to the server.

[0868] Through this series of steps, the server, terminal, and user work together to efficiently collect, analyze, and provide information about politicians.

[0869] Example 1

[0870] 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."

[0871] Conventional politician information gathering systems lack the ability to efficiently collect, preprocess, and analyze massive amounts of data and easily provide it to users. As a result, information imbalances arise, and users are unable to quickly access the information on politicians they need. Furthermore, there is an insufficient mechanism for incorporating user feedback into system improvements, making it difficult to improve the quality of the system.

[0872] 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.

[0873] In this invention, the server includes means for collecting data from the Internet, means for deleting unnecessary information from the collected data and standardizing the format, means for analyzing the preprocessed data using a generative AI model to generate summary information, means for saving the generated summary information in a database, means for providing the saved summary information in response to a user request, and means for collecting feedback from users and using it to improve the system. This enables efficient data collection, analysis, and provision, allowing users to quickly obtain the politician information they need, and enabling system improvements based on user feedback.

[0874] "Internet data" refers to any information accessible through the internet, often obtained through APIs.

[0875] "Nonessential information" refers to data that is not important or useful for a particular data analysis or purpose.

[0876] "Unifying the format" refers to the process of arranging the collected data into a consistent structure so that it can be easily analyzed and processed.

[0877] A "generative AI model" is an artificial intelligence model that generates a specific output based on given input data. A natural language processing model is typically used.

[0878] "Summary information" refers to information that has been compiled concisely and clearly by extracting only the important points from detailed data.

[0879] A "database" is a system designed to allow the efficient retrieval, storage, and updating of stored data.

[0880] A "request" refers to a request or inquiry made by a user to a server.

[0881] "Feedback" refers to opinions and impressions provided by users after using the system, and is information used to improve the system.

[0882] This invention is a system that efficiently collects, preprocesses, analyzes, and provides information about politicians to users. This system mainly uses a server, a terminal, a generative AI model, and a database.

[0883] First, the server collects data from the Internet. Specifically, the server obtains data about politicians through an API on the Internet. For example, this includes basic information about politicians, their past achievements, statements in parliament, campaign promises, and ideology.

[0884] The server then preprocesses the collected data, removing unnecessary information and standardizing the format. For example, it uses Python's Pandas and regular expression libraries to remove unnecessary tags and whitespace, and ensure consistent string formatting.

[0885] The server then analyzes the preprocessed data using a generative AI model, such as OpenAI's GPT-3, which tokenizes the preprocessed text and extracts key points to generate a summary.

[0886] The generated summary information is stored in a database by the server. The database is a relational database management system such as PostgreSQL. When a user makes a request, the server retrieves the necessary summary information from the database and provides it to the terminal via the API.

[0887] Users can access the API endpoint using their devices to obtain the generated summary information. The obtained information is displayed on the device in a format that is easy for users to understand. In addition, the system has a feedback function that collects user opinions and feedback, which will be used to improve the system.

[0888] As a concrete example, we will explain the flow for obtaining information about a specific politician (e.g., ID: 12345) and generating a summary. In this case, the server first collects detailed information about politician ID: 12345 from the API. Then, it preprocesses the collected data and generates summary information using a generative AI model. This summary information is stored in a database and is returned to the device when the user submits a request.

[0889] Examples of prompts include:

[0890] "summarize the following text about the politician: 'Politician's statements and promises... (preprocessed data)'"

[0891] "SELECT FROM politician_summary WHERE politician_id = 12345;"

[0892] This system allows users to quickly access important information about politicians, helping them make decisions efficiently. Furthermore, the system will be improved based on user feedback, further enhancing its quality.

[0893] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0894] Step 1:

[0895] The server collects data about politicians through an API on the Internet. Specifically, the server sends a request to a specific API endpoint and retrieves detailed information by specifying the politician's ID. The input of this process is the politician's ID, and the output is the retrieved detailed information.

[0896] Step 2:

[0897] The server preprocesses the collected data. Specifically, it removes unnecessary tags and whitespace from the data and standardizes the string format. The input of this process is the raw data obtained, and the output is the preprocessed data. Python's Pandas and regular expression libraries are used to remove unnecessary elements and convert the data into a consistent format.

[0898] Step 3:

[0899] The server sends the preprocessed data to a generative AI model (e.g., GPT-3), which tokenizes the provided text and generates a summary. The input of this process is the preprocessed text data, and the output is the generated summary.

[0900] Step 4:

[0901] The server stores the generated summary information in a database. The database uses a relational database management system (e.g., PostgreSQL) that allows efficient searching, storage, and updating. The input of this process is the generated summary information, and the output is the summary information stored in the database.

[0902] Step 5:

[0903] The server receives requests from users and provides the stored summary information. A user uses a device to access the API endpoint and request summary information for a specific politician. The input of this process is the user request, and the output is the summary information according to the request.

[0904] Step 6:

[0905] The user accesses the API endpoint using a terminal and retrieves the generated summary information, which is then displayed on the user's terminal. The input of this process is the summary information provided by the server, and the output is the summary information displayed on the terminal.

[0906] Step 7:

[0907] Users send their opinions and thoughts to the server through the feedback function. The server collects this feedback and uses it to improve the system. The input of this process is the user feedback, and the output is the analyzed feedback information.

[0908] This series of processes enables efficient collection, analysis, and provision of information about politicians, resulting in a system that allows users to quickly obtain the information they need.

[0909] (Application example 1)

[0910] 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."

[0911] Conventional political information systems require complicated information collection, analysis, and provision, making it difficult for users to quickly and easily obtain the information they require. Furthermore, the devices and methods for viewing information in real time were limited, resulting in an inadequate user experience. Furthermore, there was a lack of systems that allowed users to intuitively search for information using voice input or touch operations.

[0912] 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.

[0913] In this invention, the server includes means for collecting data on politicians, means for preprocessing the collected data, means for analyzing the preprocessed data using a generative AI model and generating summary information, means for saving the generated summary information in a database, means for providing the saved summary information in response to a user request, means for allowing the user to view information displayed on the smart device, and means for the user to search for information on politicians using voice input or touch operation. This allows users to quickly and easily obtain the information they need about politicians and to view the information in real time using intuitive operations.

[0914] "Data on politicians" refers to basic information about politicians, their past achievements, statements in parliament, campaign promises, beliefs, and other related information.

[0915] "Means of collection" refers to devices or software for obtaining data about politicians using APIs on the Internet, etc.

[0916] "Preprocessing means" refers to a device or software for removing unnecessary elements from collected data and standardizing the data format.

[0917] A "generative AI model" refers to an artificial intelligence model that uses natural language processing technology to analyze text data and generate summary information and related information.

[0918] "Means for generating summary information" refers to a device or software that analyzes preprocessed data using a generative AI model and generates information that succinctly summarizes the key points.

[0919] "Means for storing in a database" refers to a storage device or software for storing the generated summary information and retrieving it when necessary.

[0920] The "means for providing" refers to a device or software for obtaining summary information from a database in response to a user request and transmitting the information to a user terminal.

[0921] "Smart Device" refers to smartphones, smart glasses, tablets and other internet-enabled portable information terminals.

[0922] "Voice input" refers to a means by which a user can give instructions to a device using voice recognition technology.

[0923] "Touch operation" refers to the means by which a user issues commands using the touchscreen of a device.

[0924] The present invention relates to a system for efficiently collecting, analyzing, and providing information about politicians. This system includes a server, a terminal, and a specific generative AI model.

[0925] 1. Data Collection

[0926] The server first collects data about politicians through an API on the Internet, including basic information about the politician, past achievements, statements in parliament, campaign promises, and ideology. For example, the server collects information through an API request using an ID number that identifies a specific politician.

[0927] 2. Data Preprocessing

[0928] The server then preprocesses the collected data, specifically removing unnecessary elements from the data and standardizing the string format, making the data easier to analyze.

[0929] 3. Summary information generation

[0930] The pre-processed data is then analyzed by a generative AI model, which uses natural language processing techniques to summarize the text data. The pre-processed text is tokenized and a summary is generated that succinctly summarizes the key points.

[0931] 4. Data storage and provision

[0932] The generated summary information is stored in a database by the server. In response to a user request, the server retrieves information from this database and provides it to the terminal via an API. If the terminal is a smart device (smart glasses or tablet), the user can search for information using voice input or touch operation.

[0933] 5. User Access

[0934] Users access the API endpoint using their device to retrieve the generated summary information, which is then displayed on the device in a format that is easy for users to understand.

[0935] Specific examples

[0936] This section explains the flow for obtaining information about a specific politician (e.g., ID: 12345) and generating a summary. In this case, the server first collects detailed information about politician ID: 12345 from the API. The collected data is then preprocessed and summary information is generated using a generative AI model. The generated summary information is stored in a database and returned to the device when the user submits a request. This series of processes allows the user to easily understand the politician's basic information and past achievements.

[0937] Prompt Sentence Examples

[0938] Below are some example prompts that users can use to request information using smart glasses:

[0939] A user puts on the smart glasses and requests information about a particular politician, for example, by saying "Show me information about politician ID 12345."

[0940] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0941] Step 1:

[0942] The server collects data about politicians using an API on the Internet. As input, it receives an ID number that identifies a specific politician and sends an API request. As output, it obtains detailed data such as the politician's basic information, past achievements, statements in parliament, campaign promises, and ideology.

[0943] Step 2:

[0944] The server pre-processes the collected data. As input, it receives the raw data from the API, removes unnecessary elements (e.g., HTML tags and extra spaces), and standardizes the string format. As output, it obtains pre-processed data that is easier to parse.

[0945] Step 3:

[0946] The server analyzes the preprocessed data using a generative AI model. As input, it receives the preprocessed text data, tokenizes it, and analyzes it. As output, it generates a summary of the politician's key points.

[0947] Step 4:

[0948] The server stores the generated summary information in a database. As input, it receives summary information from the generative AI model and stores it in the database. As output, it provides a database that is organized in a way that can respond to user requests.

[0949] Step 5:

[0950] A user accesses the server's API endpoint using a device and requests summary information. As input, the user sends a request about a specific politician (e.g., politician ID: 12345) using voice input or touch operation. As output, the user receives the summary information provided by the server on the device.

[0951] Step 6:

[0952] The terminal displays the received summary information. As input, it receives the summary information sent from the server and converts it into a format that is easy to display visually. As output, it displays it on the display in a format that is easy for the user to understand.

[0953] Step 7:

[0954] The user reviews the displayed information and, if necessary, asks additional questions or requests by voice or touch. As input, a new request or feedback is sent to the device. As output, a new request is generated to the server, and the information corresponding to the request is again collected, preprocessed, analyzed, and provided.

[0955] 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.

[0956] This invention relates to a system that efficiently collects, analyzes, and provides information about politicians, and also combines it with an emotion engine that recognizes the user's emotions. This system is composed of a server, a terminal, a generative AI model, a database, an emotion engine, etc.

[0957] 1. Data Collection

[0958] The server first collects data about politicians through an API on the Internet, including basic information about the politicians, their past performance, statements in parliament, campaign promises, and ideology.

[0959] 2. Data Preprocessing

[0960] The server preprocesses the collected data. Specifically, it removes unnecessary tags and spaces from the data and standardizes the string format. This preprocessing makes the data easier to analyze.

[0961] 3. Data analysis using generative AI

[0962] The server then analyzes the preprocessed data using a generative AI model. To do this, the preprocessed text is tokenized using a tokenizer and the tokens are input into the generative AI model, which then generates summary information.

[0963] 4. Data storage and provision

[0964] The generated summary information is stored in a database by the server. In response to a user request, the server retrieves information from this database and provides it to the terminal via an API. The user can access the summary information through the terminal and quickly obtain information that is relevant to them.

[0965] 5. Emotional Analysis of Users by Emotion Engine

[0966] The server also includes an emotion engine that recognizes the user's emotions. The emotion engine monitors the user's feedback and behavior during use, and analyzes emotions in real time. The analysis results are stored in a database and the presentation of summary information is adjusted based on the user's emotional state.

[0967] Specific examples

[0968] This section explains the process for obtaining information about a specific politician (e.g., ID: 12345) and generating a summary. In this case, the server collects detailed information about politician ID: 12345 from the API. The collected data is then preprocessed and summary information is generated using a generative AI model. The generated summary information is stored in a database and returned to the device when the user submits a request. Furthermore, when the user views the summary information, the server uses an emotion engine to analyze the user's emotions in real time and optimizes the presentation method based on the results. This series of processes not only allows the user to concisely grasp the politician's basic information and past performance, but also allows them to receive information optimally presented according to their emotions.

[0969] This system allows voters to efficiently obtain information about politicians and eliminate information imbalances. Furthermore, the emotion engine improves users' understanding and sense of satisfaction, thereby enhancing the fairness of elections.

[0970] The processing flow will be explained below.

[0971] This invention combines a system for efficiently collecting, analyzing, and providing information about politicians with an emotion engine that recognizes user emotions. This system is composed of a server, terminals, a generative AI model, a database, and an emotion engine.

[0972] Step 1:

[0973] The server first collects data about politicians through an API on the internet, which involves sending requests to specific API endpoints and receiving the returned data in JSON format.

[0974] Step 2:

[0975] The server preprocesses the collected data, which includes removing unnecessary tags and whitespace from the data and standardizing string formats, making the data easier to analyze.

[0976] Step 3:

[0977] The server analyzes the preprocessed data using a generative AI model. For this analysis, the preprocessed text is tokenized using a tokenizer and the tokens are input to the generative AI model. The generative AI model generates summary information from the tokenized text.

[0978] Step 4:

[0979] The server stores the generated summary information in a database, which includes the process of storing the summary information in a database and indexing the information for efficient retrieval.

[0980] Step 5:

[0981] The server retrieves the stored summary information from the database in response to a user request. This retrieval process involves searching the database based on the user request and extracting the relevant summary information as a search result.

[0982] Step 6:

[0983] The server provides the acquired summary information to the device via an API, allowing the user to access the summary information through the device and quickly obtain information about the politicians they need.

[0984] Step 7:

[0985] The device displays the summary information retrieved from the API to the user in a format that is easy for the user to understand, such as text, graphs, or images.

[0986] Step 8:

[0987] The server uses an emotion engine to monitor user feedback and behavior during use and analyze emotions in real time. For this analysis, it analyzes textual feedback and collects and analyzes device usage history data.

[0988] Step 9:

[0989] Based on the analysis results, the server adjusts the presentation of summary information according to the user's emotional state: for example, if the user is excited, it displays information in a clear and concise manner, while if the user is relaxed, it provides detailed information.

[0990] Step 10:

[0991] The user provides feedback through the terminal, which includes opinions and impressions about the provided summary information, and the server collects and stores the feedback in a database.

[0992] This system efficiently obtains information about politicians and presents information according to the user's emotions, thereby eliminating information imbalances and promoting fair election campaigns.

[0993] Example 2

[0994] 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."

[0995] In modern society, the amount of information about politicians is enormous, making it difficult for voters to grasp the overall picture. Furthermore, organizing and summarizing the collected information is time-consuming, and current systems do not provide information that takes into account the user's emotions. Therefore, there is a need for a system that can quickly provide appropriate information to users and present information in a way that suits their emotional state.

[0996] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting data on politicians, means for preprocessing the collected data, means for analyzing the preprocessed data using a generative AI model and generating summary information, means for saving the generated summary information in a database, and means for recognizing user emotions and optimizing the presentation method. This makes it possible to provide information on politicians to users quickly and efficiently, and further to present information optimally according to the user's emotions.

[0997] A "politician" is a public official or person who is running for or elected to public office or who holds a political role.

[0998] A "data collection tool" is a system or process for obtaining specific information from the Internet or other sources.

[0999] "Data preprocessing means" refers to a system or process for removing unnecessary elements from collected data and standardizing the data format.

[1000] A "generative AI model" is an artificial intelligence model that learns from large amounts of data and performs various tasks (e.g., summary generation, question answering).

[1001] A "summary generator" is a system or process for generating summary information from preprocessed data using a generative AI model.

[1002] "Database storage means" means a system or process for storing the generated summary information in a structured format in a database.

[1003] "Providing means" refers to a system or process for retrieving and providing information stored in a database in response to a user request.

[1004] An "emotion recognizer" is a system or process for analyzing a user's feedback and behavior to identify the user's emotional state.

[1005] A "presentation optimizer" is a system or process for adjusting the presentation of information based on the user's emotional state obtained by the emotion recognizer.

[1006] This invention is a system that efficiently collects, analyzes, and provides information about politicians, and also combines it with an emotion engine that recognizes the user's emotions. This system is composed of a server, a terminal, a generative AI model, a database, an emotion engine, etc.

[1007] The server first collects data about politicians through an API on the Internet. This data includes basic information about the politician, their past achievements, statements in parliament, campaign promises, and ideology. For example, information about politician ID: 12345 can be collected from a URL such as "https: / / api.example.com / politician / 12345."

[1008] Next, the server preprocesses the collected data. During this process, unnecessary tags and whitespace are removed and the string format is standardized. This preprocessing makes the data easier to analyze. For example, if HTML tags or special characters are included, they are removed and the date format is standardized to "YYYY-MM-DD".

[1009] The data is then analyzed using a generative AI model. The server tokenizes the preprocessed data using a tokenizer and inputs the tokens into a generative AI model. A large-scale language model (e.g., GPT-3) can be used as the generative AI model. This model is used to summarize the text and generate summary information. An example of a prompt sentence is, "Please summarize the basic information about politician ID: 12345."

[1010] The generated summary information is stored in a database by the server. This database typically uses a relational database such as SQL. When a user requests information through their device, the server retrieves the required information from the database and provides it to the device via an API. The user can then access the summary information using their device and obtain the information quickly.

[1011] Furthermore, the server uses an emotion engine to recognize the user's emotions. This emotion engine monitors and analyzes user feedback and usage behavior in real time. For example, it collects user click logs and page visit times and performs emotion analysis. The analysis results are stored in a database and the way summary information is presented is adjusted based on the user's emotional state. For example, detailed information is provided to users with positive emotions, and concise information is provided to users with negative emotions.

[1012] As a concrete example, we will explain the flow of obtaining information about a specific politician (e.g., ID: 12345) and generating a summary. In this case, the server collects detailed information about politician ID: 12345 from an API. The collected data is then preprocessed and summary information is generated using a generative AI model. The generated summary information is stored in a database and returned to the device when the user submits a request. Furthermore, when the user views the summary information, the server uses an emotion engine to analyze the user's emotions in real time and optimizes the presentation method based on the results. This series of processes not only allows the user to concisely grasp the politician's basic information and past performance, but also allows them to receive information that is optimally presented according to their emotions.

[1013] The system described above allows voters to efficiently obtain information about politicians and eliminate information imbalances. Furthermore, the emotion engine improves users' understanding and sense of satisfaction, potentially enhancing the fairness of elections.

[1014] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1015] Step 1:

[1016] Initializing and sending data collection

[1017] The server sets an interval to collect data about politicians using a pre-configured API endpoint. For example, it sets a timer to send an API request every hour. The server sends the API request to the URL "https: / / api.example.com / politician / 12345" and includes an API key or authentication token in the header, if necessary. The input at this point is the API request information, and the output is the response data from the API.

[1018] Step 2:

[1019] Data reception and preprocessing

[1020] The server receives a JSON-formatted response from the API. The received data includes basic information about politicians and their past achievements. This data is analyzed, unnecessary elements such as HTML tags and special characters are removed, and the format is standardized. For example, the date format is standardized to "YYYY-MM-DD." The input in this step is the API response data, and the output is clean data after preprocessing.

[1021] Step 3:

[1022] Data tokenization and summary generation

[1023] The server tokenizes the preprocessed text data using a tokenizer, which splits the sentence into words and phrases and generates an array of tokens. Next, the preprocessed data is input to a generative AI model (e.g., GPT-3) to generate summary information according to a prompt such as "Please summarize basic information about politician ID: 12345." The input in this step is the preprocessed data and the prompt, and the output is the generated summary information.

[1024] Step 4:

[1025] Save summary information

[1026] The server stores the generated summary information in a database. This process uses SQL queries to insert the summary information into the appropriate tables. The input to this step is the generated summary information, and the output is the summary information stored in the database.

[1027] Step 5:

[1028] Processing user requests and providing data

[1029] A user requests information about a particular politician through a terminal, for example, by submitting an information request through an application on the terminal or a web form. When the server receives this request, it retrieves the corresponding summary information from the database and returns it to the user terminal as a response in an appropriate format. The input in this step is the user request, and the output is the summary information provided to the user terminal.

[1030] Step 6:

[1031] User sentiment analysis and information presentation optimization

[1032] The server collects user feedback and behavioral data during use and analyzes it with an emotion engine. This engine analyzes data such as click logs and page visit times to identify the user's emotional state. For example, if there is a lot of negative feedback, it determines that the user is dissatisfied and changes the settings to provide more concise information. The input in this step is user behavior data, and the output is the emotion analysis results and adjustments to the information presentation method based on those results.

[1033] Combining these steps allows users to efficiently obtain detailed information about politicians and present it in the most relevant way based on their sentiment.

[1034] (Application example 2)

[1035] 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."

[1036] Conventional systems for collecting and analyzing information about politicians present information to users in a uniform manner, resulting in insufficient personalization based on the user's emotions and interests. Furthermore, when applied to advertising, this system suffers from the problem of reduced advertising effectiveness because it does not take into account the user's emotions. This makes it difficult to provide users with the information they desire quickly and appropriately, leading to information imbalances and lack of understanding.

[1037] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data on politicians, means for preprocessing the collected data, means for analyzing the preprocessed data using a generative AI model and generating summary information, means for saving the generated summary information in a database, means for providing the saved summary information in response to a user request, means for analyzing the user's emotions using an emotion engine that recognizes the user's emotions and adjusting the presentation method, and means for providing optimal advertisements based on the user's emotions. This makes it possible to present information and optimize advertisements taking into account the user's emotional state.

[1038] "Data on politicians" refers to information including basic information about politicians, past achievements, statements made in parliament, campaign promises, and ideology.

[1039] The "means of collection" refers to the means of obtaining data about politicians through APIs on the Internet, etc.

[1040] "Preprocessing means" refers to a means for removing unnecessary elements from collected data and standardizing the data format.

[1041] A "generative AI model" is an artificial intelligence model that analyzes tokenized text data using a tokenizer and generates summary information.

[1042] "Summary information" is concise information generated by a generative AI model based on data about politicians.

[1043] A "database" is a system for storing the generated summary information and providing the information in response to a user's request.

[1044] The "means for providing in response to a request from a user" refers to a means for providing summary information stored in a database to a terminal in response to a user request.

[1045] An "emotion engine" is software that recognizes and analyzes a user's emotions.

[1046] The "means for adjusting the presentation method" is a means for adjusting the method for presenting information to the user based on the analysis results of the emotion engine.

[1047] "Advertising" is marketing content that is provided in an optimal manner based on the user's emotions and interests.

[1048] This invention relates to a system that efficiently collects and analyzes information about politicians, and then recognizes users' emotions to present optimal advertisements. This system includes components such as a server, a terminal, a generative AI model, a database, and an emotion engine.

[1049] A specific embodiment is as follows.

[1050] 1. Data Collection

[1051] The server collects data about politicians through an API on the Internet, including basic information about the politicians, their past performance, statements in parliament, campaign promises, and beliefs.

[1052] 2. Data Preprocessing

[1053] The server preprocesses the collected data by removing unnecessary elements and standardizing the data format, making the data easier to analyze.

[1054] 3. Data analysis using generative AI models

[1055] The server inputs the preprocessed data into a generative AI model for analysis. This generative AI model uses a natural language processing tokenizer. The tokenizer tokenizes the text data and inputs it into the generative AI model to generate summary information. The generated summary information is stored in a database.

[1056] 4. Data provision

[1057] When a user sends a request from their terminal, the server retrieves the stored summary information from the database and provides it to the user's terminal, allowing the user to quickly access the information they need.

[1058] 5. Emotional Analysis of Users by Emotion Engine

[1059] The server analyzes the user's feedback and behavior during use using an emotion engine. The emotion engine monitors the user's emotional state in real time and stores the analysis results in a database. Based on this emotional data, the method of presenting information to the user is optimized.

[1060] 6. Providing optimal advertising

[1061] The server then presents the most appropriate advertisement based on the results of the user's emotion analysis. If the user's emotion is positive, the server provides more detailed information, and if the user's emotion is negative, the server provides less interesting information. In this way, advertisements are displayed that are tailored to the user's emotional state.

[1062] Specific examples

[1063] 1. Example prompt (input to the generative AI model):

[1064] "Please summarize the policies of the following politicians: Policy A is..."

[1065] 2. Example summary output from a generative AI model:

[1066] "Summary of Policy A: Policy A emphasizes social welfare..."

[1067] 3. Example of input for user sentiment analysis:

[1068] "Very interesting. I'd like to know more!"

[1069] 4. Example of user sentiment analysis results:

[1070] "emotion: positive"

[1071] This invention not only enables users to quickly and easily obtain information about politicians, but also allows them to receive optimal information and advertisements according to their emotions, which is expected to eliminate information imbalances and improve advertising effectiveness.

[1072] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1073] Step 1:

[1074] The server collects data about politicians through an API on the Internet. As input, it uses the API endpoint and politician ID. The data returned from the API includes basic information about the politician, past achievements, statements in parliament, campaign promises, and beliefs. The output is the collected data about the politician.

[1075] Step 2:

[1076] The server preprocesses the collected data. The data about politicians collected in step 1 is used as input for preprocessing. Specifically, it removes unnecessary tags and spaces from the data and standardizes the string format. This converts the data into a format that is easy to analyze. The output is the preprocessed data.

[1077] Step 3:

[1078] The server analyzes the preprocessed data using a generative AI model to generate summary information. As input, it uses a tokenizer to tokenize the preprocessed text data. The tokenized data is input to the generative AI model to obtain summary information. Specifically, the generative AI model analyzes the text data, extracts important information, and generates a summary. The output is the generated summary information.

[1079] Step 4:

[1080] The server stores the generated summary information in the database. It uses the summary information generated in step 3 as input. Specific operations include converting the summary information into an appropriate format and storing it in the database. The output is confirmation data of the stored summary information.

[1081] Step 5:

[1082] When a user sends a request from their device, the server retrieves the stored summary information from the database and provides it to the user's device. The input is a request from the user. Specifically, the server sends a query to the database, retrieves the corresponding summary information, and sends it to the device. The output is the summary information displayed on the user's device.

[1083] Step 6:

[1084] The user's device collects user feedback and usage behavior from time to time and sends it to the server. The input includes user feedback and operation logs during usage. The output is the feedback data sent to the server.

[1085] Step 7:

[1086] The server uses the emotion engine to analyze the user's emotions. The input is the user's feedback data sent in step 6. Specifically, the emotion engine analyzes the feedback data and extracts the user's emotional state (positive, negative, etc.). The output is the analyzed user's emotion data.

[1087] Step 8:

[1088] The server selects and serves the most appropriate advertisement based on the results of the user's sentiment analysis. The inputs are the sentiment analysis results from step 7 and the advertisement information stored in the database. Specifically, the server selects the advertisement that is most suitable for the user based on the sentiment analysis results and sends it to the terminal. The output is the most appropriate advertisement that is displayed on the user's terminal.

[1089] This allows users to not only efficiently obtain information about politicians, but also receive advertisements that are most appropriate for their emotions.

[1090] 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.

[1091] 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.

[1092] 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.

[1093] 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.

[1094] 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.

[1095] 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.

[1096] 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).

[1097] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1098] 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."

[1099] 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.

[1100] 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).

[1101] 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.

[1102] 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.

[1103] 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.

[1104] 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.

[1105] 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.

[1106] 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.

[1107] 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.

[1108] 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.

[1109] 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.

[1110] 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.

[1111] The following is further disclosed regarding the above embodiment.

[1112] (Claim 1)

[1113] a means of collecting data on politicians;

[1114] means for pre-processing the collected data;

[1115] A means for analyzing the preprocessed data using a generative AI model to generate summary information;

[1116] means for storing the generated summary information in a database;

[1117] A system including means for providing stored summary information upon request from a user.

[1118] (Claim 2)

[1119] The system according to claim 1, wherein the collecting means obtains data on politicians through an API on the Internet.

[1120] (Claim 3)

[1121] 2. The system according to claim 1, wherein the preprocessing means removes unnecessary elements from the collected data and standardizes the data format.

[1122] (Claim 4)

[1123] 10. The system of claim 1, wherein the analyzing means uses a generative AI model to tokenize the data and generate summary information.

[1124] (Claim 5)

[1125] 10. The system of claim 1, wherein the means for providing provides the summary information through a user-accessible API endpoint.

[1126] (Claim 6)

[1127] 10. The system of claim 1, further comprising means for collecting and storing user feedback in a database.

[1128] "Example 1"

[1129] (Claim 1)

[1130] means for collecting data on the Internet;

[1131] A means of removing unnecessary information from the collected data and standardizing the format;

[1132] A means for analyzing the preprocessed data using a generative AI model to generate summary information;

[1133] means for storing the generated summary information in a database;

[1134] means for providing the stored summary information in response to a request from a user;

[1135] A system that includes a means of collecting feedback from users to help improve the system.

[1136] (Claim 2)

[1137] 2. The system according to claim 1, wherein the collecting means acquires data through an API on the Internet.

[1138] (Claim 3)

[1139] 2. The system according to claim 1, wherein the preprocessing means removes unnecessary elements from the collected data and standardizes the data format.

[1140] "Application Example 1"

[1141] (Claim 1)

[1142] a means of collecting data on politicians;

[1143] means for pre-processing the collected data;

[1144] A means for analyzing the preprocessed data using a generative AI model to generate summary information;

[1145] means for storing the generated summary information in a database;

[1146] means for providing the stored summary information in response to a request from a user;

[1147] A means by which a user can view information displayed on a smart device;

[1148] A way for users to search for information about politicians using voice input or touch operations,

[1149] A system including:

[1150] (Claim 2)

[1151] The system according to claim 1, wherein the collecting means obtains data on politicians through an API on the Internet.

[1152] (Claim 3)

[1153] 2. The system according to claim 1, wherein the preprocessing means removes unnecessary elements from the collected data and standardizes the data format.

[1154] "Example 2: Combining Emotion Engines"

[1155] (Claim 1)

[1156] a means of collecting data on politicians;

[1157] means for pre-processing the collected data;

[1158] A means for analyzing the preprocessed data using a generative AI model to generate summary information;

[1159] means for storing the generated summary information in a database;

[1160] means for providing the stored summary information in response to a request from a user;

[1161] A means for recognizing user emotions and optimizing presentation methods;

[1162] A system including:

[1163] (Claim 2)

[1164] The system according to claim 1, wherein the collecting means obtains data on politicians through an API on the Internet.

[1165] (Claim 3)

[1166] 2. The system according to claim 1, wherein the preprocessing means removes unnecessary elements from the collected data and standardizes the data format.

[1167] "Application example 2 when combining emotion engines"

[1168] (Claim 1)

[1169] a means of collecting data on politicians;

[1170] means for pre-processing the collected data;

[1171] A means for analyzing the preprocessed data using a generative AI model to generate summary information;

[1172] means for storing the generated summary information in a database;

[1173] means for providing the stored summary information in response to a request from a user;

[1174] A means for analyzing a user's emotions using an emotion engine that recognizes the user's emotions and adjusting the presentation method;

[1175] A means for providing optimal advertisements based on user emotions;

[1176] A system including:

[1177] (Claim 2)

[1178] The system according to claim 1, wherein the collecting means obtains data on politicians through an API on the Internet.

[1179] (Claim 3)

[1180] 2. The system according to claim 1, wherein the preprocessing means removes unnecessary elements from the collected data and standardizes the data format. [Explanation of symbols]

[1181] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means of collecting data on politicians; means for pre-processing the collected data; A means for analyzing the preprocessed data using a generative AI model to generate summary information; means for storing the generated summary information in a database; A system including means for providing stored summary information upon request from a user.

2. The system according to claim 1, wherein the collecting means acquires data on politicians through an API on the Internet.

3. 2. The system according to claim 1, wherein the preprocessing means removes unnecessary elements from the collected data and standardizes the data format.

4. 10. The system of claim 1, wherein the analyzing means uses a generative AI model to tokenize the data and generate summary information.

5. The system of claim 1 , wherein the means for providing provides the summary information through a user-accessible API endpoint.

6. 10. The system of claim 1, further comprising means for collecting and storing user feedback in a database.

Images