System

Abstract

An object of the system according to the embodiment is to enable a voter to find a politician matching his / her interest and directly talk online.SOLUTION: A system includes an analysis unit, a proposal unit, and an interaction unit. The analysis unit analyzes the profile of the politician. The proposal part makes a proposal matching the interest of the voter on the basis of the data analyzed by the analysis part. The dialog unit allows the voter to have a direct online dialog with the politician proposed by the proposal unit.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] Conventional technology has made it difficult for voters to find politicians whose interests match theirs, and has not ensured sufficient transparency and effectiveness in political participation.

[0005] The system according to the embodiment aims to enable voters to find politicians who match their interests and to interact with them directly online. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, a proposal unit, and a dialogue unit. The analysis unit analyzes the profiles of politicians. The proposal unit makes proposals that match the interests of voters based on the data analyzed by the analysis unit. The dialogue unit allows voters to directly dialogue online with politicians proposed by the proposal unit. [Effects of the Invention]

[0007] The system according to the embodiment allows voters to find politicians who align with their interests and interact directly with them online. [Brief explanation of the drawings]

[0008] [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. DETAILED DESCRIPTION OF THE INVENTION

[0009] 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.

[0010] First, the terms used in the following description will be explained.

[0011] 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, the 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), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] 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.

[0013] 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.

[0014] 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), and Bluetooth (registered trademark).

[0015] 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."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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).

[0019] 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.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. 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 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. 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.

[0022] 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.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A system according to an embodiment of the present invention identifies the most suitable politician for voters and enables direct online dialogue. This system uses AI to individually analyze politicians' profiles and make recommendations tailored to their individual interests, helping them make satisfying political choices. Voters can also directly interact with politicians through an online platform and obtain information about their policies and proposals. For example, AI collects and analyzes detailed data on politicians, such as their backgrounds, policies, and statements. This allows the AI ​​to identify politicians who match the voter's interests. The AI ​​then makes recommendations tailored to the voter's interests. For example, if a voter is interested in environmental issues, the AI ​​can suggest politicians who focus on environmental policies. Furthermore, voters can directly interact with politicians through the online platform. For example, when a voter enters a question, politicians can respond to that question. This allows voters to directly obtain information about politicians' policies and proposals. This system promotes more transparent and effective political participation. This system supports voters' satisfying political choices and strengthens the value of democracy. For example, voters can find politicians who match their interests and engage in direct dialogue with them to make satisfying political choices. Politicians can also hear the opinions of voters directly, allowing them to propose policies that better meet the needs of voters.

[0029] A politician proposal system according to an embodiment includes an analysis unit, a proposal unit, and a dialogue unit. The analysis unit analyzes politicians' profiles. For example, the analysis unit collects detailed data such as politicians' careers, policies, and statements, and analyzes the data using AI. For example, the analysis unit can analyze politicians' past statements and policy proposals to understand the politician's position. The analysis unit can also use AI to analyze politicians' profiles in detail. The proposal unit makes proposals that match voters' interests based on the data analyzed by the analysis unit. For example, if a voter is interested in environmental issues, the proposal unit can propose politicians who are focusing on environmental policies. The proposal unit can also use AI to identify politicians that match the voter's interests. The dialogue unit provides a function that allows voters to directly interact online with politicians proposed by the proposal unit. For example, the dialogue unit can enable politicians to answer questions entered by voters. The dialogue unit can also use AI to support dialogue between voters and politicians. This allows the politician proposal system according to an embodiment to find the most suitable politician for a voter and enable direct online dialogue.

[0030] The politician proposal system is equipped with an understanding unit that understands voters' interests. The understanding unit understands voters' interests. For example, the understanding unit analyzes information entered by voters to identify their interests. The understanding unit can also use AI to understand voters' interests in detail. For example, if a voter is interested in environmental issues, the understanding unit can identify their interests based on that information. This allows the understanding unit to understand voters' interests and make more appropriate proposals.

[0031] The politician suggestion system is equipped with a routing unit that analyzes voters' questions and routes them to the appropriate politician. The routing unit analyzes voters' questions and routes them to the appropriate politician. For example, the routing unit analyzes questions entered by voters and routes them to the appropriate politician based on their content. The routing unit can also use AI to analyze voters' questions in detail and route them to the most appropriate politician. For example, if a voter enters a question about environmental issues, the routing unit can route them to a politician who is knowledgeable about environmental policy. This allows the routing unit to route voters' questions to the appropriate politician, enabling efficient dialogue.

[0032] The politician proposal system includes an information provision unit that provides detailed information about each politician. The information provision unit provides detailed information about each politician. For example, the information provision unit provides detailed information such as the politician's career, policies, and statements. The information provision unit can also use AI to collect and provide detailed information about each politician. For example, the information provision unit can collect politicians' past statements and policy proposals and provide that information to voters. In this way, by providing detailed information about each politician, the information provision unit enables voters to make more informed choices.

[0033] The analysis unit can collect data on politicians' careers, policies, and statements, and analyze it using AI. For example, the analysis unit collects data on politicians' careers, policies, and statements, and analyzes it using AI. For example, the analysis unit collects politicians' past statements and policy proposals, and inputs that data into AI for analysis. The analysis unit can also use AI to analyze detailed data on politicians' careers and policies. For example, the analysis unit can analyze a politician's past statements to understand what position the politician is taking. This allows the analysis unit to collect and analyze detailed data on politicians, enabling more accurate analysis.

[0034] The proposal unit can propose politicians that match the interests of voters. For example, the proposal unit proposes politicians that match the interests of voters. For example, if a voter is interested in environmental issues, the proposal unit will propose politicians who are focusing on environmental policies. The proposal unit can also use AI to identify politicians that match the interests of voters. For example, the proposal unit can use AI to analyze the interests of voters and propose the most suitable politician based on that information. This allows the proposal unit to make more appropriate proposals by proposing politicians that match the interests of voters.

[0035] The dialogue unit can provide voters with the ability to directly interact with politicians through an online platform. For example, the dialogue unit can enable voters to enter questions and politicians to respond to those questions. The dialogue unit can also use AI to support dialogue between voters and politicians. For example, the dialogue unit can use AI to analyze voters' questions and provide appropriate answers based on the content of those questions. In this way, the dialogue unit enables voters to interact directly with politicians through an online platform, enabling more transparent and effective political participation.

[0036] The analysis unit can improve the accuracy of the analysis by referring to the politician's past election results during the analysis. The analysis unit can improve the accuracy of the analysis by referring to the politician's past election results during the analysis, for example. For example, the analysis unit may use AI to analyze the politician's past election results and analyze fluctuations in approval ratings. The analysis unit may also use AI to evaluate the acceptability of the politician's policies based on past election results. The analysis unit may also use AI to analyze the effectiveness of the politician's election strategy by referring to the politician's past election results. In this way, the analysis unit improves the accuracy of the analysis by referring to the politician's past election results.

[0037] The analysis unit can analyze the politician's social media activity during analysis and reflect his / her most recent statements and actions. For example, the analysis unit can analyze the politician's social media activity during analysis and reflect his / her most recent statements and actions. For example, the analysis unit can use AI to analyze the politician's latest tweets and analyze the trends in statements. The analysis unit can also use AI to analyze the politician's Facebook (registered trademark) posts and analyze the content of interactions with supporters. The analysis unit can also use AI to analyze the politician's Instagram (registered trademark) activity and evaluate the impact of visual content. This allows the analysis unit to reflect the politician's most recent statements and actions, enabling more accurate analysis.

[0038] The analysis unit can collect information on a politician's opponents during analysis and perform a comparative analysis. For example, the analysis unit can collect information on a politician's opponents during analysis and perform a comparative analysis. For example, the analysis unit can use AI to collect the policies of opponents and perform a comparative analysis. The analysis unit can also use AI to collect statements made by opponents and analyze differences in their positions with the politician. The analysis unit can also use AI to collect election results of opponents and compare support rates. In this way, the analysis unit can perform a more comprehensive analysis by collecting and comparing information on opponents.

[0039] The analysis unit can take into account the geographical range of a politician's activities when conducting the analysis. For example, the analysis unit can perform the analysis by taking into account the geographical range of a politician's activities when conducting the analysis. For example, the analysis unit can have the AI ​​focus its analysis on the politician's local activities. The analysis unit can also have the AI ​​perform its analysis by taking into account the politician's national range of activities. The analysis unit can also perform its analysis by including the politician's international activities. In this way, the analysis unit can perform a more accurate analysis by taking into account the geographical range of a politician's activities.

[0040] The analysis unit can improve the accuracy of the analysis by referring to the politician's related bills and voting history during the analysis. For example, the analysis unit can improve the accuracy of the analysis by referring to the politician's related bills and voting history during the analysis. For example, the analysis unit can have AI analyze the politician's past bill submission history. The analysis unit can also have AI refer to the politician's voting history to evaluate the consistency of policies. The analysis unit can also have AI analyze the politician's bill support rate and evaluate the influence of policies. In this way, the analysis unit can improve the accuracy of the analysis by referring to the politician's related bills and voting history.

[0041] The analysis unit can take into account the politician's media exposure during analysis. For example, the analysis unit can use AI to analyze the number of times a politician appears on television and evaluate the level of media exposure. The analysis unit can also use AI to analyze the number of times a politician is featured in a newspaper article and evaluate the level of media exposure. The analysis unit can also use AI to analyze the politician's online media exposure and evaluate their influence. This allows the analysis unit to take into account the politician's media exposure, enabling more accurate analysis.

[0042] When making a proposal, the proposal unit can refer to the voter's past voting history to make the most appropriate proposal. When making a proposal, the proposal unit can refer to the voter's past voting history to make the most appropriate proposal. For example, the proposal unit uses AI to analyze the voter's past voting history and propose policies that interest them. The proposal unit can also use AI to suggest politicians from political parties that the voter supports based on the voter's voting history. The proposal unit can also use AI to refer to the voter's voting history and propose politicians who have policies that the voter has supported in the past. This enables the proposal unit to make more appropriate proposals by referring to the voter's past voting history.

[0043] The proposal unit can adjust the level of detail of the proposal based on the priority of the voter's interests when making a proposal. For example, the proposal unit adjusts the level of detail of the proposal based on the priority of the voter's interests when making a proposal. For example, if the voter is strongly interested in environmental issues, the proposal unit can make a detailed proposal regarding environmental policy. Furthermore, if the voter is interested in economic policy, the proposal unit can make a detailed proposal regarding economic policy. Furthermore, if the voter is interested in education policy, the proposal unit can make a detailed proposal regarding education policy. In this way, the proposal unit can adjust the level of detail of the proposal based on the priority of the voter's interests, thereby enabling more appropriate proposals.

[0044] The proposal unit can customize proposals by taking into account the voter's regional characteristics when making a proposal. For example, the proposal unit customizes proposals by taking into account the voter's regional characteristics when making a proposal. For example, the proposal unit may use AI to consider the characteristics of the region where the voter lives and propose policies related to the region. The proposal unit may also use AI to consider the economic situation in the voter's region and propose economic policies. The proposal unit may also use AI to consider the environmental situation in the voter's region and propose environmental policies. This enables the proposal unit to make more appropriate proposals by taking into account the voter's regional characteristics.

[0045] The proposal unit can customize proposals based on the voter's occupation and lifestyle when making a proposal. For example, the proposal unit customizes proposals based on the voter's occupation and lifestyle when making a proposal. For example, the proposal unit uses AI to consider the voter's occupation and propose policies related to the occupation. The proposal unit can also use AI to consider the voter's lifestyle and propose policies related to the lifestyle. The proposal unit can also use AI to comprehensively consider the voter's occupation and lifestyle and make optimal proposals. This enables the proposal unit to customize proposals based on the voter's occupation and lifestyle, enabling more appropriate proposals.

[0046] The suggestion unit can analyze the voter's social media activity at the time of proposal and suggest relevant politicians. For example, the suggestion unit analyzes the voter's social media activity at the time of proposal and suggest relevant politicians. For example, the suggestion unit uses AI to analyze the content of the voter's social media posts and suggest politicians who have policies that interest them. The suggestion unit can also use AI to suggest relevant politicians based on the activity of the voter's friends on social media. The suggestion unit can also use AI to analyze the voter's social media check-in information and suggest politicians that are relevant to the region. This enables the suggestion unit to suggest more appropriate politicians by analyzing the voter's social media activity.

[0047] The proposal unit can improve the proposal method by reflecting voters' past feedback when making a proposal. For example, the proposal unit improves the proposal method by reflecting voters' past feedback when making a proposal. For example, the proposal unit uses AI to analyze voters' past feedback and improve the proposal method. The proposal unit can also customize the proposal content based on voter feedback. The proposal unit can also use AI to refer to voter feedback and improve the accuracy of the proposal. In this way, the proposal unit improves the accuracy of the proposal method by reflecting voters' past feedback.

[0048] The dialogue unit can provide the optimal answer by referring to the politician's past dialogue history during a dialogue. For example, the dialogue unit can provide the optimal answer by referring to the politician's past dialogue history during a dialogue. For example, the dialogue unit can use AI to analyze the politician's past dialogue history and provide the optimal answer. The dialogue unit can also provide answers to similar questions based on the politician's past dialogue history. The dialogue unit can also maintain consistency in answers by using AI to refer to the politician's past dialogue history. This allows the dialogue unit to provide more appropriate answers by referring to the politician's past dialogue history.

[0049] The dialogue unit can provide relevant additional information based on the content of the voter's question during the dialogue. For example, the dialogue unit can use AI to analyze the content of the voter's question and provide relevant policy information. The dialogue unit can also use AI to provide relevant news articles based on the content of the voter's question. The dialogue unit can also use AI to refer to the content of the voter's question and provide relevant statistical data. This allows the dialogue unit to provide relevant additional information based on the content of the voter's question, enabling more appropriate dialogue.

[0050] The dialogue unit can analyze the progress of the dialogue in real time during a dialogue and follow up at the appropriate time. For example, the dialogue unit can analyze the progress of the dialogue in real time during a dialogue and follow up at the appropriate time. For example, the dialogue unit can have AI analyze the progress of the dialogue in real time and follow up at the appropriate time. The dialogue unit can also have AI suggest the next question based on the progress of the dialogue. The dialogue unit can also have AI refer to the progress of the dialogue and keep the flow of the dialogue smooth. This makes it possible for the dialogue unit to follow up at the appropriate time by analyzing the progress of the dialogue in real time.

[0051] The dialogue unit can select the optimal dialogue method by taking into account the voter's device information during dialogue. For example, the dialogue unit selects the optimal dialogue method by taking into account the voter's device information during dialogue. For example, if the voter is using a smartphone, the dialogue unit can provide a dialogue method that suits the screen size. Furthermore, if the voter is using a tablet, the dialogue unit can also provide a dialogue method that is optimized for a large screen. Furthermore, if the voter is using a PC, the dialogue unit can also provide a dialogue method that includes detailed information. This allows the dialogue unit to have a more appropriate dialogue by taking into account the voter's device information.

[0052] The dialogue unit can make the dialogue content multilingual in accordance with the voter's language setting during the dialogue. For example, the dialogue unit can automatically set the dialogue language based on the language setting of the voter's device during the dialogue. The dialogue unit can also provide a language switching function when the voter uses multiple languages. Furthermore, if the voter selects a specific language, the dialogue unit can provide the dialogue in that language. This allows the dialogue unit to make the dialogue content multilingual in accordance with the voter's language setting, enabling more appropriate dialogue.

[0053] The dialogue unit can improve the dialogue method by reflecting voters' past feedback during the dialogue. For example, the dialogue unit improves the dialogue method by reflecting voters' past feedback during the dialogue. For example, the dialogue unit uses AI to analyze voters' past feedback and improve the dialogue method. The dialogue unit can also customize the dialogue content based on voter feedback. The dialogue unit can also use AI to refer to voter feedback and improve the accuracy of the dialogue. In this way, the dialogue unit improves the accuracy of the dialogue method by reflecting voters' past feedback.

[0054] The identification unit can refer to the voter's past voting history to identify their interests when identifying voters. For example, the identification unit can use AI to analyze the voter's past voting history and identify policies that the voter is interested in when identifying voters. The identification unit can also use AI to identify the policies of political parties that the voter supports based on the voter's voting history. The identification unit can also use AI to refer to the voter's voting history and identify policies that the voter supported in the past. This enables the identification unit to identify more appropriate interests by referring to the voter's past voting history.

[0055] The identification unit can analyze the voter's social media activity at the time of identification and reflect their latest interests. For example, the identification unit can analyze the voter's social media activity at the time of identification and reflect their latest interests. For example, the identification unit can use AI to analyze the content of the voter's posts on social media and identify their latest interests. The identification unit can also use AI to analyze the voter's check-in information on social media and identify places of interest. The identification unit can also use AI to identify the voter's latest interests by referring to the activities of the voter's friends on social media. This enables the identification unit to reflect the voter's latest interests by analyzing the voter's social media activity.

[0056] The identification unit can identify the voter's interests by taking into account the voter's regional characteristics when identifying the voter. For example, the identification unit can identify the voter's interests by taking into account the voter's regional characteristics when identifying the voter. For example, the identification unit can use AI to consider the characteristics of the region where the voter lives and identify interests related to the region. The identification unit can also use AI to consider the voter's regional economic situation and identify interests related to economic policy. The identification unit can also use AI to consider the voter's regional environmental situation and identify interests related to environmental policy. This enables the identification unit to identify more appropriate interests by taking into account the voter's regional characteristics.

[0057] The identification unit can identify interests based on the voter's occupation and lifestyle when identifying the voter. For example, the identification unit can identify interests based on the voter's occupation and lifestyle when identifying the voter. For example, the identification unit can use AI to consider the voter's occupation and identify interests related to the occupation. The identification unit can also use AI to consider the voter's lifestyle and identify interests related to the lifestyle. The identification unit can also use AI to comprehensively consider the voter's occupation and lifestyle and identify the most appropriate interests. This enables the identification unit to identify interests based on the voter's occupation and lifestyle, enabling more appropriate identification of interests.

[0058] The identification unit can improve the method of identifying interests by reflecting voters' past feedback when identifying voters' interests. For example, the identification unit can improve the method of identifying interests by reflecting voters' past feedback when identifying voters' interests. For example, the identification unit can have AI analyze voters' past feedback and improve the method of identifying interests. The identification unit can also have AI customize the method of identifying interests based on voter feedback. The identification unit can also have AI refer to voter feedback and improve the accuracy of identifying interests. In this way, the identification unit can improve the accuracy of the method of identifying voters' interests by reflecting voters' past feedback.

[0059] The identification unit can select the optimal identification method by taking into consideration the voter's device information when identifying voters. For example, the identification unit can select the optimal identification method by taking into consideration the voter's device information when identifying voters. For example, if the voter is using a smartphone, the identification unit can provide an identification method that matches the screen size. Furthermore, if the voter is using a tablet, the identification unit can provide an identification method that is optimized for a large screen. Furthermore, if the voter is using a computer, the identification unit can provide an identification method that includes detailed information. This allows the identification unit to identify voters' interests more appropriately by taking into consideration the voter's device information.

[0060] The routing unit can perform optimal routing based on the politician's area of ​​expertise when routing. For example, the routing unit performs optimal routing based on the politician's area of ​​expertise when routing. For example, the routing unit uses AI to take the politician's area of ​​expertise into consideration and route questions related to that area. The routing unit can also select the optimal respondent based on the politician's area of ​​expertise. The routing unit can also use AI to refer to the politician's area of ​​expertise and improve the accuracy of the question. This allows the routing unit to perform optimal routing based on the politician's area of ​​expertise, enabling more appropriate answers.

[0061] The routing unit can refer to the politician's past answer history when routing to perform optimal routing. For example, the routing unit can refer to the politician's past answer history when routing to perform optimal routing. For example, the routing unit uses AI to analyze the politician's past answer history and perform optimal routing. The routing unit can also use AI to select respondents to similar questions based on the politician's past answer history. The routing unit can also use AI to refer to the politician's past answer history to maintain consistency in answers. This allows the routing unit to perform more appropriate routing by referring to the politician's past answer history.

[0062] The routing unit can take into account the voter's regional characteristics when routing. For example, the routing unit uses AI to take into account the characteristics of the area where the voter lives and route questions related to the area. The routing unit can also use AI to take into account the economic situation in the voter's area and route questions related to economic policy. The routing unit can also use AI to take into account the environmental situation in the voter's area and route questions related to environmental policy. This allows the routing unit to take into account the voter's regional characteristics and perform more appropriate routing.

[0063] The routing unit can perform optimal routing based on the voter's occupation and lifestyle when routing. For example, the routing unit performs optimal routing based on the voter's occupation and lifestyle when routing. For example, the routing unit uses AI to consider the voter's occupation and route questions related to the occupation. The routing unit can also use AI to consider the voter's lifestyle and route questions related to the lifestyle. The routing unit can also perform optimal routing by using AI to comprehensively consider the voter's occupation and lifestyle. This allows the routing unit to perform optimal routing based on the voter's occupation and lifestyle, enabling more appropriate answers.

[0064] The routing unit can analyze the voter's social media activity during routing and route them to relevant politicians. For example, the routing unit analyzes the voter's social media activity during routing and routes them to relevant politicians. For example, the routing unit uses AI to analyze the content of the voter's social media posts and route them to politicians who have policies that interest them. The routing unit can also use AI to route them to relevant politicians based on the activity of the voter's friends on social media. The routing unit can also use AI to analyze the voter's social media check-in information and route them to politicians related to the region. This enables the routing unit to perform more appropriate routing by analyzing the voter's social media activity.

[0065] The routing unit can improve the routing method by reflecting voters' past feedback when routing. For example, the routing unit improves the routing method by reflecting voters' past feedback when routing. For example, the routing unit uses AI to analyze voters' past feedback and improve the routing method. The routing unit can also customize the routing content based on voter feedback. The routing unit can also use AI to refer to voter feedback and improve the accuracy of routing. In this way, the routing unit improves the accuracy of the routing method by reflecting voters' past feedback.

[0066] The information provision unit can improve the accuracy of the information when providing information by referring to the politician's past election results. The information provision unit, for example, improves the accuracy of the information when providing information by referring to the politician's past election results. For example, the information provision unit uses AI to analyze the politician's past election results and reflect changes in approval ratings in the information it provides. The information provision unit can also use AI to evaluate the acceptability of the politician's policies based on past election results and provide the information it provides. The information provision unit can also use AI to refer to past election results and reflect the effectiveness of the politician's election strategy in the information it provides. In this way, the information provision unit improves the accuracy of the information by referring to the politician's past election results.

[0067] The information provision unit can analyze the politician's social media activity and reflect the latest information when providing information. For example, the information provision unit can analyze the politician's social media activity and reflect the latest information when providing information. For example, the information provision unit can use AI to analyze the politician's latest tweets and reflect the politician's speaking trends in the information provided. The information provision unit can also use AI to analyze the politician's Facebook posts and reflect the content of interactions with supporters in the information provided. The information provision unit can also use AI to analyze the politician's Instagram activity and reflect the influence of visual content in the information provided. This enables the information provision unit to reflect the latest information by analyzing the politician's social media activity.

[0068] The information provision unit can provide information on a politician's opposing candidates when providing information, and provide comparative information. For example, the information provision unit can use AI to collect the policies of opposing candidates and provide comparative information when providing information. The information provision unit can also use AI to collect statements by opposing candidates and provide information on differences in their positions with the politician. The information provision unit can also use AI to collect election results for opposing candidates and provide information on a comparison of support rates. This allows the information provision unit to provide more comprehensive information by providing information on opposing candidates.

[0069] The information provision unit can select the optimal information provision method by taking into consideration the voter's device information when providing information. For example, the information provision unit selects the optimal information provision method by taking into consideration the voter's device information when providing information. For example, if the voter is using a smartphone, the information provision unit can provide an information provision method that matches the screen size. Furthermore, if the voter is using a tablet, the information provision unit can also provide an information provision method that is optimized for a large screen. Furthermore, if the voter is using a PC, the information provision unit can also provide an information provision method that includes detailed information. This enables the information provision unit to provide more appropriate information by taking into consideration the voter's device information.

[0070] The information provision unit can make the information content multilingual in accordance with the voter's language setting when providing information. For example, the information provision unit can automatically set the language in which information is provided based on the language setting of the voter's device when providing information. The information provision unit can also provide a language switching function when a voter uses multiple languages. Furthermore, if a voter selects a specific language, the information provision unit can provide information in that language. This allows the information provision unit to make the information content multilingual in accordance with the voter's language setting, thereby enabling more appropriate information to be provided.

[0071] The information provision unit can improve the information provision method by reflecting voters' past feedback when providing information. For example, the information provision unit improves the information provision method by reflecting voters' past feedback when providing information. For example, the information provision unit uses AI to analyze voters' past feedback and improves the information provision method. The information provision unit can also customize the content of the information provided by AI based on voter feedback. The information provision unit can also improve the accuracy of the information provision by having AI refer to voter feedback. In this way, the information provision unit improves the accuracy of the information provision method by reflecting voters' past feedback.

[0072] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0073] The proposal unit not only suggests politicians who match the interests of voters, but can also visually display the proposed politician's past policy achievements and statements. For example, the proposal unit can display a politician's past policy proposals in graphs and charts, providing information in a format that is visually easy for voters to understand. The proposal unit can also display the politician's statements as a keyword cloud, allowing voters to grasp their main interests at a glance. Furthermore, the proposal unit can simulate the impact of a politician's policies and visually display the results. In this way, the proposal unit helps voters make more informed choices.

[0074] The identification unit can not only identify voters' interests but also track changes in voters' interests in real time. For example, the identification unit can analyze voters' activities on online platforms to detect changes in their interests. The identification unit can also analyze voters' posts on social media to identify changes in their interests in real time. Furthermore, the identification unit can analyze the frequency and content of voters' viewing of news articles to identify changes in their interests. This enables the identification unit to respond quickly to changes in voters' interests and make more appropriate suggestions.

[0075] The routing unit not only analyzes voters' questions and routes them to the appropriate politicians, but also provides additional relevant information based on the content of the question. For example, the routing unit analyzes the content of voters' questions and provides relevant policy information or news articles. The routing unit can also provide relevant statistical data or research results based on the content of voters' questions. Furthermore, the routing unit can provide records of past parliamentary debates related to the content of voters' questions. In this way, the routing unit helps voters have more informed conversations.

[0076] The information provision unit not only provides detailed information about each politician, but can also evaluate and display the reliability of the information. For example, the information provision unit can evaluate the reliability of a politician's statements and policy proposals and display a reliability score. The information provision unit can also evaluate the reliability of a politician's information sources and preferentially display information from highly reliable sources. Furthermore, the information provision unit can fact-check a politician's statements and policy proposals and display the results. In this way, the information provision unit supports voters in making choices based on highly reliable information.

[0077] The analysis department not only collects and analyzes data on politicians' careers, policies, and statements, but can also analyze politicians' networks and evaluate their influence. For example, the analysis department can analyze a politician's personal connections and evaluate their relationships with influential people. The analysis department can also analyze a politician's network of supporters and collaborators and evaluate their influence. Furthermore, the analysis department can analyze a politician's network of followers and supporters on social media and evaluate their influence. This allows the analysis department to comprehensively evaluate a politician's influence and enable more accurate analysis.

[0078] The dialogue unit not only provides voters with the ability to directly interact with politicians through an online platform, but also analyzes the progress of the dialogue in real time and can follow up at the appropriate time. For example, the dialogue unit uses AI to analyze the progress of the dialogue in real time and follow up at the appropriate time. The dialogue unit can also use AI to suggest the next question based on the progress of the dialogue. The dialogue unit can also refer to the progress of the dialogue to keep the flow of the dialogue smooth. This allows the dialogue unit to analyze the progress of the dialogue in real time and follow up at the appropriate time.

[0079] The processing flow of the first embodiment will be briefly explained below.

[0080] Step 1: The analysis unit analyzes the politician's profile. For example, the analysis unit collects detailed data such as the politician's career, policies, and statements, and analyzes it using AI. The analysis unit analyzes the politician's past statements and policy proposals to understand the politician's position. AI can also be used to perform detailed analysis of the politician's profile. Step 2: The proposal unit makes proposals that match the voter's interests based on the data analyzed by the analysis unit. For example, if a voter is interested in environmental issues, the proposal unit can suggest politicians who are focusing on environmental policies. AI can also be used to identify politicians who match the voter's interests. Step 3: The dialogue unit provides a function for voters to directly interact online with the politicians proposed by the proposal unit. For example, the dialogue unit can enable voters to enter questions and politicians to respond to them. It can also use AI to support the dialogue between voters and politicians.

[0081] (Example 2) A system according to an embodiment of the present invention identifies the most suitable politician for voters and enables direct online dialogue. This system uses AI to individually analyze politicians' profiles and make recommendations tailored to their individual interests, helping them make satisfying political choices. Voters can also directly interact with politicians through an online platform and obtain information about their policies and proposals. For example, AI collects and analyzes detailed data on politicians, such as their backgrounds, policies, and statements. This allows the AI ​​to identify politicians who match the voter's interests. The AI ​​then makes recommendations tailored to the voter's interests. For example, if a voter is interested in environmental issues, the AI ​​can suggest politicians who focus on environmental policies. Furthermore, voters can directly interact with politicians through the online platform. For example, when a voter enters a question, politicians can respond to that question. This allows voters to directly obtain information about politicians' policies and proposals. This system promotes more transparent and effective political participation. This system supports voters' satisfying political choices and strengthens the value of democracy. For example, voters can find politicians who match their interests and engage in direct dialogue with them to make satisfying political choices. Politicians can also hear the opinions of voters directly, allowing them to propose policies that better meet the needs of voters.

[0082] A politician proposal system according to an embodiment includes an analysis unit, a proposal unit, and a dialogue unit. The analysis unit analyzes politicians' profiles. For example, the analysis unit collects detailed data such as politicians' careers, policies, and statements, and analyzes the data using AI. For example, the analysis unit can analyze politicians' past statements and policy proposals to understand the politician's position. The analysis unit can also use AI to analyze politicians' profiles in detail. The proposal unit makes proposals that match voters' interests based on the data analyzed by the analysis unit. For example, if a voter is interested in environmental issues, the proposal unit can propose politicians who are focusing on environmental policies. The proposal unit can also use AI to identify politicians that match the voter's interests. The dialogue unit provides a function that allows voters to directly interact online with politicians proposed by the proposal unit. For example, the dialogue unit can enable politicians to answer questions entered by voters. The dialogue unit can also use AI to support dialogue between voters and politicians. This allows the politician proposal system according to an embodiment to find the most suitable politician for a voter and enable direct online dialogue.

[0083] The politician proposal system is equipped with an understanding unit that understands voters' interests. The understanding unit understands voters' interests. For example, the understanding unit analyzes information entered by voters to identify their interests. The understanding unit can also use AI to understand voters' interests in detail. For example, if a voter is interested in environmental issues, the understanding unit can identify their interests based on that information. This allows the understanding unit to understand voters' interests and make more appropriate proposals.

[0084] The politician suggestion system is equipped with a routing unit that analyzes voters' questions and routes them to the appropriate politician. The routing unit analyzes voters' questions and routes them to the appropriate politician. For example, the routing unit analyzes questions entered by voters and routes them to the appropriate politician based on their content. The routing unit can also use AI to analyze voters' questions in detail and route them to the most appropriate politician. For example, if a voter enters a question about environmental issues, the routing unit can route them to a politician who is knowledgeable about environmental policy. This allows the routing unit to route voters' questions to the appropriate politician, enabling efficient dialogue.

[0085] The politician proposal system includes an information provision unit that provides detailed information about each politician. The information provision unit provides detailed information about each politician. For example, the information provision unit provides detailed information such as the politician's career, policies, and statements. The information provision unit can also use AI to collect and provide detailed information about each politician. For example, the information provision unit can collect politicians' past statements and policy proposals and provide that information to voters. In this way, by providing detailed information about each politician, the information provision unit enables voters to make more informed choices.

[0086] The analysis unit can collect data on politicians' careers, policies, and statements, and analyze it using AI. For example, the analysis unit collects data on politicians' careers, policies, and statements, and analyzes it using AI. For example, the analysis unit collects politicians' past statements and policy proposals, and inputs that data into AI for analysis. The analysis unit can also use AI to analyze detailed data on politicians' careers and policies. For example, the analysis unit can analyze a politician's past statements to understand what position the politician is taking. This allows the analysis unit to collect and analyze detailed data on politicians, enabling more accurate analysis.

[0087] The proposal unit can propose politicians that match the interests of voters. For example, the proposal unit proposes politicians that match the interests of voters. For example, if a voter is interested in environmental issues, the proposal unit will propose politicians who are focusing on environmental policies. The proposal unit can also use AI to identify politicians that match the interests of voters. For example, the proposal unit can use AI to analyze the interests of voters and propose the most suitable politician based on that information. This allows the proposal unit to make more appropriate proposals by proposing politicians that match the interests of voters.

[0088] The dialogue unit can provide voters with the ability to directly interact with politicians through an online platform. For example, the dialogue unit can enable voters to enter questions and politicians to respond to those questions. The dialogue unit can also use AI to support dialogue between voters and politicians. For example, the dialogue unit can use AI to analyze voters' questions and provide appropriate answers based on the content of those questions. In this way, the dialogue unit enables voters to interact directly with politicians through an online platform, enabling more transparent and effective political participation.

[0089] The analysis unit can estimate voter sentiment and adjust the analysis method for politician profiles based on the estimated voter sentiment. For example, the analysis unit can estimate voter sentiment and adjust the analysis method for politician profiles based on the estimated voter sentiment. For example, if voters are feeling anxious, the analysis unit can have the AI ​​prioritize analyzing information about the politician's trustworthiness. Furthermore, if voters are excited, the analysis unit can also have the AI ​​focus on analyzing the politician's latest activities and statements. Furthermore, if voters are calm, the analysis unit can have the AI ​​analyze the politician's past policy performance in detail. This allows the analysis unit to adjust the analysis method based on voter sentiment, enabling more appropriate analysis. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI can be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0090] The analysis unit can improve the accuracy of the analysis by referring to the politician's past election results during the analysis. The analysis unit can improve the accuracy of the analysis by referring to the politician's past election results during the analysis, for example. For example, the analysis unit may use AI to analyze the politician's past election results and analyze fluctuations in approval ratings. The analysis unit may also use AI to evaluate the acceptability of the politician's policies based on past election results. The analysis unit may also use AI to analyze the effectiveness of the politician's election strategy by referring to the politician's past election results. In this way, the analysis unit improves the accuracy of the analysis by referring to the politician's past election results.

[0091] The analysis unit can analyze a politician's social media activity during analysis and reflect their most recent statements and actions. For example, the analysis unit can analyze a politician's social media activity during analysis and reflect their most recent statements and actions. For example, the analysis unit can use AI to analyze a politician's latest tweets and analyze their statement trends. The analysis unit can also use AI to analyze a politician's Facebook posts and analyze the content of their interactions with supporters. The analysis unit can also use AI to analyze a politician's Instagram activity and evaluate the impact of visual content. This allows the analysis unit to reflect a politician's most recent statements and actions, enabling more accurate analysis.

[0092] The analysis unit can collect information on a politician's opponents during analysis and perform a comparative analysis. For example, the analysis unit can collect information on a politician's opponents during analysis and perform a comparative analysis. For example, the analysis unit can use AI to collect the policies of opponents and perform a comparative analysis. The analysis unit can also use AI to collect statements made by opponents and analyze differences in their positions with the politician. The analysis unit can also use AI to collect election results of opponents and compare support rates. In this way, the analysis unit can perform a more comprehensive analysis by collecting and comparing information on opponents.

[0093] The analysis unit can estimate voter emotions and adjust the display method of the analysis results based on the estimated voter emotions. For example, the analysis unit can estimate voter emotions and adjust the display method of the analysis results based on the estimated voter emotions. For example, if the voter is feeling anxious, the analysis unit can provide a simple display method that gives a sense of security. If the voter is excited, the analysis unit can also provide a display method that includes detailed information. If the voter is calm, the analysis unit can also display detailed analysis results based on data. This allows the analysis unit to provide more appropriate information by adjusting the display method based on the voter's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI can be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0094] The analysis unit can take into account the geographical range of a politician's activities when conducting the analysis. For example, the analysis unit can perform the analysis by taking into account the geographical range of a politician's activities when conducting the analysis. For example, the analysis unit can have the AI ​​focus its analysis on the politician's local activities. The analysis unit can also have the AI ​​perform its analysis by taking into account the politician's national range of activities. The analysis unit can also perform its analysis by including the politician's international activities. In this way, the analysis unit can perform a more accurate analysis by taking into account the geographical range of a politician's activities.

[0095] The analysis unit can improve the accuracy of the analysis by referring to the politician's related bills and voting history during the analysis. For example, the analysis unit can improve the accuracy of the analysis by referring to the politician's related bills and voting history during the analysis. For example, the analysis unit can have AI analyze the politician's past bill submission history. The analysis unit can also have AI refer to the politician's voting history to evaluate the consistency of policies. The analysis unit can also have AI analyze the politician's bill support rate and evaluate the influence of policies. In this way, the analysis unit can improve the accuracy of the analysis by referring to the politician's related bills and voting history.

[0096] The analysis unit can take into account the politician's media exposure during analysis. For example, the analysis unit can use AI to analyze the number of times a politician appears on television and evaluate the level of media exposure. The analysis unit can also use AI to analyze the number of times a politician is featured in a newspaper article and evaluate the level of media exposure. The analysis unit can also use AI to analyze the politician's online media exposure and evaluate their influence. This allows the analysis unit to take into account the politician's media exposure, enabling more accurate analysis.

[0097] The suggestion unit can estimate the voter's emotions and adjust the way the proposal is expressed based on the estimated voter's emotions. The suggestion unit, for example, estimates the voter's emotions and adjusts the way the proposal is expressed based on the estimated voter's emotions. For example, if the voter is feeling anxious, the suggestion unit can make a proposal using an expression that gives a sense of security. Furthermore, if the voter is excited, the suggestion unit can make a proposal using an expression that includes detailed information. Furthermore, if the voter is calm, the suggestion unit can make a proposal using an objective expression based on data. In this way, the suggestion unit can adjust the way the proposal is expressed based on the voter's emotions, thereby enabling more appropriate proposals. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0098] When making a proposal, the proposal unit can refer to the voter's past voting history to make the most appropriate proposal. When making a proposal, the proposal unit can refer to the voter's past voting history to make the most appropriate proposal. For example, the proposal unit uses AI to analyze the voter's past voting history and propose policies that interest them. The proposal unit can also use AI to suggest politicians from political parties that the voter supports based on the voter's voting history. The proposal unit can also use AI to refer to the voter's voting history and propose politicians who have policies that the voter has supported in the past. This enables the proposal unit to make more appropriate proposals by referring to the voter's past voting history.

[0099] The proposal unit can adjust the level of detail of the proposal based on the priority of the voter's interests when making a proposal. For example, the proposal unit adjusts the level of detail of the proposal based on the priority of the voter's interests when making a proposal. For example, if the voter is strongly interested in environmental issues, the proposal unit can make a detailed proposal regarding environmental policy. Furthermore, if the voter is interested in economic policy, the proposal unit can make a detailed proposal regarding economic policy. Furthermore, if the voter is interested in education policy, the proposal unit can make a detailed proposal regarding education policy. In this way, the proposal unit can adjust the level of detail of the proposal based on the priority of the voter's interests, thereby enabling more appropriate proposals.

[0100] The proposal unit can customize proposals by taking into account the voter's regional characteristics when making a proposal. For example, the proposal unit customizes proposals by taking into account the voter's regional characteristics when making a proposal. For example, the proposal unit may use AI to consider the characteristics of the region where the voter lives and propose policies related to the region. The proposal unit may also use AI to consider the economic situation in the voter's region and propose economic policies. The proposal unit may also use AI to consider the environmental situation in the voter's region and propose environmental policies. This enables the proposal unit to make more appropriate proposals by taking into account the voter's regional characteristics.

[0101] The suggestion unit can estimate the voter's emotions and adjust the length of the proposal based on the estimated voter's emotions. The suggestion unit, for example, estimates the voter's emotions and adjusts the length of the proposal based on the estimated voter's emotions. For example, if the voter is feeling anxious, the suggestion unit can make a short, to-the-point proposal. Alternatively, if the voter is excited, the suggestion unit can make a longer proposal including detailed information. Alternatively, if the voter is calm, the suggestion unit can make a detailed proposal based on data. This allows the suggestion unit to adjust the length of the proposal based on the voter's emotions, thereby enabling more appropriate proposals. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0102] The proposal unit can customize proposals based on the voter's occupation and lifestyle when making a proposal. For example, the proposal unit customizes proposals based on the voter's occupation and lifestyle when making a proposal. For example, the proposal unit uses AI to consider the voter's occupation and propose policies related to the occupation. The proposal unit can also use AI to consider the voter's lifestyle and propose policies related to the lifestyle. The proposal unit can also use AI to comprehensively consider the voter's occupation and lifestyle and make optimal proposals. This enables the proposal unit to customize proposals based on the voter's occupation and lifestyle, enabling more appropriate proposals.

[0103] The suggestion unit can analyze the voter's social media activity at the time of proposal and suggest relevant politicians. For example, the suggestion unit analyzes the voter's social media activity at the time of proposal and suggest relevant politicians. For example, the suggestion unit uses AI to analyze the content of the voter's social media posts and suggest politicians who have policies that interest them. The suggestion unit can also use AI to suggest relevant politicians based on the activity of the voter's friends on social media. The suggestion unit can also use AI to analyze the voter's social media check-in information and suggest politicians that are relevant to the region. This enables the suggestion unit to suggest more appropriate politicians by analyzing the voter's social media activity.

[0104] The proposal unit can improve the proposal method by reflecting voters' past feedback when making a proposal. For example, the proposal unit improves the proposal method by reflecting voters' past feedback when making a proposal. For example, the proposal unit uses AI to analyze voters' past feedback and improve the proposal method. The proposal unit can also customize the proposal content based on voter feedback. The proposal unit can also use AI to refer to voter feedback and improve the accuracy of the proposal. In this way, the proposal unit improves the accuracy of the proposal method by reflecting voters' past feedback.

[0105] The dialogue unit can estimate the voter's emotions and adjust the dialogue progress method based on the estimated voter's emotions. For example, the dialogue unit can estimate the voter's emotions and adjust the dialogue progress method based on the estimated voter's emotions. For example, if the voter is feeling anxious, the dialogue unit can provide a dialogue progress method that gives a sense of security. Furthermore, if the voter is excited, the dialogue unit can provide a dialogue progress method that includes detailed information. Furthermore, if the voter is calm, the dialogue unit can provide an objective dialogue progress method based on data. This allows the dialogue unit to adjust the dialogue progress method based on the voter's emotions, thereby enabling a more appropriate dialogue. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0106] The dialogue unit can provide the optimal answer by referring to the politician's past dialogue history during a dialogue. For example, the dialogue unit can provide the optimal answer by referring to the politician's past dialogue history during a dialogue. For example, the dialogue unit can use AI to analyze the politician's past dialogue history and provide the optimal answer. The dialogue unit can also provide answers to similar questions based on the politician's past dialogue history. The dialogue unit can also maintain consistency in answers by using AI to refer to the politician's past dialogue history. This allows the dialogue unit to provide more appropriate answers by referring to the politician's past dialogue history.

[0107] The dialogue unit can provide relevant additional information based on the content of the voter's question during the dialogue. For example, the dialogue unit can use AI to analyze the content of the voter's question and provide relevant policy information. The dialogue unit can also use AI to provide relevant news articles based on the content of the voter's question. The dialogue unit can also use AI to refer to the content of the voter's question and provide relevant statistical data. This allows the dialogue unit to provide relevant additional information based on the content of the voter's question, enabling more appropriate dialogue.

[0108] The dialogue unit can analyze the progress of the dialogue in real time during a dialogue and follow up at the appropriate time. For example, the dialogue unit can analyze the progress of the dialogue in real time during a dialogue and follow up at the appropriate time. For example, the dialogue unit can have AI analyze the progress of the dialogue in real time and follow up at the appropriate time. The dialogue unit can also have AI suggest the next question based on the progress of the dialogue. The dialogue unit can also have AI refer to the progress of the dialogue and keep the flow of the dialogue smooth. This makes it possible for the dialogue unit to follow up at the appropriate time by analyzing the progress of the dialogue in real time.

[0109] The dialogue unit can estimate the voter's emotions and determine the priority of dialogues based on the estimated voter's emotions. For example, the dialogue unit can estimate the voter's emotions and determine the priority of dialogues based on the estimated voter's emotions. For example, if the voter is feeling anxious, the dialogue unit can prioritize dialogues that provide a sense of security. Furthermore, if the voter is excited, the dialogue unit can also prioritize dialogues that include detailed information. Furthermore, if the voter is calm, the dialogue unit can also prioritize objective dialogues based on data. This allows the dialogue unit to determine the priority of dialogues based on the voter's emotions, thereby enabling more appropriate dialogues. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0110] The dialogue unit can select the optimal dialogue method by taking into account the voter's device information during dialogue. For example, the dialogue unit selects the optimal dialogue method by taking into account the voter's device information during dialogue. For example, if the voter is using a smartphone, the dialogue unit can provide a dialogue method that suits the screen size. Furthermore, if the voter is using a tablet, the dialogue unit can also provide a dialogue method that is optimized for a large screen. Furthermore, if the voter is using a PC, the dialogue unit can also provide a dialogue method that includes detailed information. This allows the dialogue unit to have a more appropriate dialogue by taking into account the voter's device information.

[0111] The dialogue unit can make the dialogue content multilingual in accordance with the voter's language setting during the dialogue. For example, the dialogue unit can automatically set the dialogue language based on the language setting of the voter's device during the dialogue. The dialogue unit can also provide a language switching function when the voter uses multiple languages. Furthermore, if the voter selects a specific language, the dialogue unit can provide the dialogue in that language. This allows the dialogue unit to make the dialogue content multilingual in accordance with the voter's language setting, enabling more appropriate dialogue.

[0112] The dialogue unit can improve the dialogue method by reflecting voters' past feedback during the dialogue. For example, the dialogue unit improves the dialogue method by reflecting voters' past feedback during the dialogue. For example, the dialogue unit uses AI to analyze voters' past feedback and improve the dialogue method. The dialogue unit can also customize the dialogue content based on voter feedback. The dialogue unit can also use AI to refer to voter feedback and improve the accuracy of the dialogue. In this way, the dialogue unit improves the accuracy of the dialogue method by reflecting voters' past feedback.

[0113] The assessment unit can estimate the voter's emotions and adjust the method for assessing the voter's interests based on the estimated voter's emotions. For example, the assessment unit can estimate the voter's emotions and adjust the method for assessing the voter's interests based on the estimated voter's emotions. For example, if the voter is feeling anxious, the assessment unit can provide a method for assessing the voter's interests that provides a sense of security. If the voter is excited, the assessment unit can also provide a method for assessing the voter's interests that includes detailed information. If the voter is calm, the assessment unit can also provide an objective method for assessing the voter's interests based on data. This allows the assessment unit to adjust the method for assessing the voter's interests based on the voter's emotions, thereby enabling more appropriate assessment of the voter's interests. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0114] The identification unit can refer to the voter's past voting history to identify their interests when identifying voters. For example, the identification unit can use AI to analyze the voter's past voting history and identify policies that the voter is interested in when identifying voters. The identification unit can also use AI to identify the policies of political parties that the voter supports based on the voter's voting history. The identification unit can also use AI to refer to the voter's voting history and identify policies that the voter supported in the past. This enables the identification unit to identify more appropriate interests by referring to the voter's past voting history.

[0115] The identification unit can analyze the voter's social media activity at the time of identification and reflect their latest interests. For example, the identification unit can analyze the voter's social media activity at the time of identification and reflect their latest interests. For example, the identification unit can use AI to analyze the content of the voter's posts on social media and identify their latest interests. The identification unit can also use AI to analyze the voter's check-in information on social media and identify places of interest. The identification unit can also use AI to identify the voter's latest interests by referring to the activities of the voter's friends on social media. This enables the identification unit to reflect the voter's latest interests by analyzing the voter's social media activity.

[0116] The identification unit can identify the voter's interests by taking into account the voter's regional characteristics when identifying the voter. For example, the identification unit can identify the voter's interests by taking into account the voter's regional characteristics when identifying the voter. For example, the identification unit can use AI to consider the characteristics of the region where the voter lives and identify interests related to the region. The identification unit can also use AI to consider the voter's regional economic situation and identify interests related to economic policy. The identification unit can also use AI to consider the voter's regional environmental situation and identify interests related to environmental policy. This enables the identification unit to identify more appropriate interests by taking into account the voter's regional characteristics.

[0117] The grasping unit can estimate the voter's emotions and determine the priority of the voter's interests based on the estimated voter's emotions. For example, the grasping unit can estimate the voter's emotions and determine the priority of the voter's interests based on the estimated voter's emotions. For example, if the voter is feeling anxious, the grasping unit can prioritize interests that provide a sense of security. Furthermore, if the voter is excited, the grasping unit can prioritize interests that include detailed information. Furthermore, if the voter is calm, the grasping unit can prioritize objective interests based on data. This enables the grasping unit to determine the priority of the voter's interests based on the voter's emotions, thereby enabling more appropriate grasping of the voter's interests. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0118] The identification unit can identify interests based on the voter's occupation and lifestyle when identifying the voter. For example, the identification unit can identify interests based on the voter's occupation and lifestyle when identifying the voter. For example, the identification unit can use AI to consider the voter's occupation and identify interests related to the occupation. The identification unit can also use AI to consider the voter's lifestyle and identify interests related to the lifestyle. The identification unit can also use AI to comprehensively consider the voter's occupation and lifestyle and identify the most appropriate interests. This enables the identification unit to identify interests based on the voter's occupation and lifestyle, enabling more appropriate identification of interests.

[0119] The identification unit can improve the method of identifying interests by reflecting voters' past feedback when identifying voters' interests. For example, the identification unit can improve the method of identifying interests by reflecting voters' past feedback when identifying voters' interests. For example, the identification unit can have AI analyze voters' past feedback and improve the method of identifying interests. The identification unit can also have AI customize the method of identifying interests based on voter feedback. The identification unit can also have AI refer to voter feedback and improve the accuracy of identifying interests. In this way, the identification unit can improve the accuracy of the method of identifying voters' interests by reflecting voters' past feedback.

[0120] The identification unit can select the optimal identification method by taking into consideration the voter's device information when identifying voters. For example, the identification unit can select the optimal identification method by taking into consideration the voter's device information when identifying voters. For example, if the voter is using a smartphone, the identification unit can provide an identification method that matches the screen size. Furthermore, if the voter is using a tablet, the identification unit can provide an identification method that is optimized for a large screen. Furthermore, if the voter is using a computer, the identification unit can provide an identification method that includes detailed information. This allows the identification unit to identify voters' interests more appropriately by taking into consideration the voter's device information.

[0121] The routing unit can estimate voter emotions and adjust the question routing method based on the estimated voter emotions. For example, the routing unit can estimate voter emotions and adjust the question routing method based on the estimated voter emotions. For example, if the voter is feeling anxious, the routing unit can provide a routing method that gives a sense of security. If the voter is excited, the routing unit can also provide a routing method that includes detailed information. If the voter is calm, the routing unit can also provide an objective routing method based on data. This allows the routing unit to adjust the question routing method based on the voter emotions, thereby enabling more appropriate routing. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0122] The routing unit can perform optimal routing based on the politician's area of ​​expertise when routing. For example, the routing unit performs optimal routing based on the politician's area of ​​expertise when routing. For example, the routing unit uses AI to take the politician's area of ​​expertise into consideration and route questions related to that area. The routing unit can also select the optimal respondent based on the politician's area of ​​expertise. The routing unit can also use AI to refer to the politician's area of ​​expertise and improve the accuracy of the question. This allows the routing unit to perform optimal routing based on the politician's area of ​​expertise, enabling more appropriate answers.

[0123] The routing unit can refer to the politician's past answer history when routing to perform optimal routing. For example, the routing unit can refer to the politician's past answer history when routing to perform optimal routing. For example, the routing unit uses AI to analyze the politician's past answer history and perform optimal routing. The routing unit can also use AI to select respondents to similar questions based on the politician's past answer history. The routing unit can also use AI to refer to the politician's past answer history to maintain consistency in answers. This allows the routing unit to perform more appropriate routing by referring to the politician's past answer history.

[0124] The routing unit can take into account the voter's regional characteristics when routing. For example, the routing unit uses AI to take into account the characteristics of the area where the voter lives and route questions related to the area. The routing unit can also use AI to take into account the economic situation in the voter's area and route questions related to economic policy. The routing unit can also use AI to take into account the environmental situation in the voter's area and route questions related to environmental policy. This allows the routing unit to take into account the voter's regional characteristics and perform more appropriate routing.

[0125] The routing unit can estimate voter emotions and prioritize questions based on the estimated voter emotions. For example, the routing unit estimates voter emotions and prioritizes questions based on the estimated voter emotions. For example, if a voter is feeling anxious, the routing unit prioritizes questions that provide a sense of security. If a voter is excited, the routing unit can also prioritize questions that include detailed information. If a voter is calm, the routing unit can also prioritize objective questions based on data. This allows the routing unit to prioritize questions based on voter emotions, enabling more appropriate routing. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI can be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0126] The routing unit can perform optimal routing based on the voter's occupation and lifestyle when routing. For example, the routing unit performs optimal routing based on the voter's occupation and lifestyle when routing. For example, the routing unit uses AI to consider the voter's occupation and route questions related to the occupation. The routing unit can also use AI to consider the voter's lifestyle and route questions related to the lifestyle. The routing unit can also perform optimal routing by using AI to comprehensively consider the voter's occupation and lifestyle. This allows the routing unit to perform optimal routing based on the voter's occupation and lifestyle, enabling more appropriate answers.

[0127] The routing unit can analyze the voter's social media activity during routing and route them to relevant politicians. For example, the routing unit analyzes the voter's social media activity during routing and routes them to relevant politicians. For example, the routing unit uses AI to analyze the content of the voter's social media posts and route them to politicians who have policies that interest them. The routing unit can also use AI to route them to relevant politicians based on the activity of the voter's friends on social media. The routing unit can also use AI to analyze the voter's social media check-in information and route them to politicians related to the region. This enables the routing unit to perform more appropriate routing by analyzing the voter's social media activity.

[0128] The routing unit can improve the routing method by reflecting voters' past feedback when routing. For example, the routing unit improves the routing method by reflecting voters' past feedback when routing. For example, the routing unit uses AI to analyze voters' past feedback and improve the routing method. The routing unit can also customize the routing content based on voter feedback. The routing unit can also use AI to refer to voter feedback and improve the accuracy of routing. In this way, the routing unit improves the accuracy of the routing method by reflecting voters' past feedback.

[0129] The information provision unit can estimate the voter's emotions and adjust the method of providing information based on the estimated voter's emotions. For example, the information provision unit can estimate the voter's emotions and adjust the method of providing information based on the estimated voter's emotions. For example, if the voter is feeling anxious, the information provision unit can provide an information provision method that gives a sense of security. Furthermore, if the voter is excited, the information provision unit can provide an information provision method that includes detailed information. Furthermore, if the voter is calm, the information provision unit can provide an objective information provision method based on data. This allows the information provision unit to adjust the method of providing information based on the voter's emotions, thereby providing more appropriate information. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0130] The information provision unit can improve the accuracy of the information when providing information by referring to the politician's past election results. The information provision unit, for example, improves the accuracy of the information when providing information by referring to the politician's past election results. For example, the information provision unit uses AI to analyze the politician's past election results and reflect changes in approval ratings in the information it provides. The information provision unit can also use AI to evaluate the acceptability of the politician's policies based on past election results and provide the information it provides. The information provision unit can also use AI to refer to past election results and reflect the effectiveness of the politician's election strategy in the information it provides. In this way, the information provision unit improves the accuracy of the information by referring to the politician's past election results.

[0131] The information provision unit can analyze the politician's social media activity and reflect the latest information when providing information. For example, the information provision unit can analyze the politician's social media activity and reflect the latest information when providing information. For example, the information provision unit can use AI to analyze the politician's latest tweets and reflect the politician's speaking trends in the information provided. The information provision unit can also use AI to analyze the politician's Facebook posts and reflect the content of interactions with supporters in the information provided. The information provision unit can also use AI to analyze the politician's Instagram activity and reflect the influence of visual content in the information provided. This enables the information provision unit to reflect the latest information by analyzing the politician's social media activity.

[0132] The information provision unit can provide information on a politician's opposing candidates when providing information, and provide comparative information. For example, the information provision unit can use AI to collect the policies of opposing candidates and provide comparative information when providing information. The information provision unit can also use AI to collect statements by opposing candidates and provide information on differences in their positions with the politician. The information provision unit can also use AI to collect election results for opposing candidates and provide information on a comparison of support rates. This allows the information provision unit to provide more comprehensive information by providing information on opposing candidates.

[0133] The information provision unit can estimate voter emotions and determine the priority of information provision based on the estimated voter emotions. The information provision unit, for example, estimates voter emotions and determines the priority of information provision based on the estimated voter emotions. For example, if a voter is feeling anxious, the information provision unit can prioritize providing information that gives a sense of security. Furthermore, if a voter is excited, the information provision unit can prioritize providing detailed information. Furthermore, if a voter is calm, the information provision unit can prioritize providing objective information based on data. This enables the information provision unit to determine the priority of information provision based on the voter's emotions, thereby providing more appropriate information. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0134] The information provision unit can select the optimal information provision method by taking into consideration the voter's device information when providing information. For example, the information provision unit selects the optimal information provision method by taking into consideration the voter's device information when providing information. For example, if the voter is using a smartphone, the information provision unit can provide an information provision method that matches the screen size. Furthermore, if the voter is using a tablet, the information provision unit can also provide an information provision method that is optimized for a large screen. Furthermore, if the voter is using a PC, the information provision unit can also provide an information provision method that includes detailed information. This enables the information provision unit to provide more appropriate information by taking into consideration the voter's device information.

[0135] The information provision unit can make the information content multilingual in accordance with the voter's language setting when providing information. For example, the information provision unit can automatically set the language in which information is provided based on the language setting of the voter's device when providing information. The information provision unit can also provide a language switching function when a voter uses multiple languages. Furthermore, if a voter selects a specific language, the information provision unit can provide information in that language. This allows the information provision unit to make the information content multilingual in accordance with the voter's language setting, thereby enabling more appropriate information to be provided.

[0136] The information provision unit can improve the information provision method by reflecting voters' past feedback when providing information. For example, the information provision unit improves the information provision method by reflecting voters' past feedback when providing information. For example, the information provision unit uses AI to analyze voters' past feedback and improves the information provision method. The information provision unit can also customize the content of the information provided by AI based on voter feedback. The information provision unit can also improve the accuracy of the information provision by having AI refer to voter feedback. In this way, the information provision unit improves the accuracy of the information provision method by reflecting voters' past feedback. === Hard Collateral 1-1 === Each of the multiple elements, including the analysis unit, suggestion unit, dialogue unit, understanding unit, routing unit, and information provision unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the analysis unit is realized by at least one of the smart device 14 and the data processing device 12. For example, the analysis unit can collect politicians' statements using the camera 42 and microphone 38B of the smart device 14 and analyze them using the control unit 46A. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and uses AI to identify and suggest politicians who match the voters' interests. The dialogue unit is realized, for example, by the control unit 46A of the smart device 14 and supports online dialogue between voters and politicians. The understanding unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes voters' input information and identifies their interests. The routing unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes voters' questions and routes them to appropriate politicians. The information providing unit is realized by, for example, the control unit 46A of the smart device 14, and provides detailed information about each politician. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned analysis unit, suggestion unit, dialogue unit, understanding unit, routing unit, and information provision unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is realized by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit can collect politicians' statements using the camera 42 and microphone 238 of the smart glasses 214 and analyze them using the control unit 46A. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and uses AI to identify and suggest politicians who match the voters' interests. The dialogue unit is realized, for example, by the control unit 46A of the smart glasses 214 and supports online dialogue between voters and politicians. The understanding unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes voters' input information and identifies their interests. The routing unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes voters' questions and routes them to appropriate politicians. The information providing unit is realized by, for example, the control unit 46A of the smart glasses 214, and provides detailed information about each politician. === Hard Collateral 1-3 === Each of the multiple elements, including the analysis unit, suggestion unit, dialogue unit, understanding unit, routing unit, and information provision unit, is realized, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the analysis unit is realized by at least one of the headset terminal 314 and the data processing device 12. For example, the analysis unit can collect politicians' statements using the camera 42 and microphone 238 of the headset terminal 314 and analyze them using the control unit 46A. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and uses AI to identify and suggest politicians who match the voters' interests. The dialogue unit is realized, for example, by the control unit 46A of the headset terminal 314 and supports online dialogue between voters and politicians. The understanding unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes voters' input information and identifies their interests. The routing unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes voters' questions and routes them to appropriate politicians. The information providing unit is realized by, for example, the control unit 46A of the headset type terminal 314, and provides detailed information about each politician. === Hard Collateral 1-4 === Each of the multiple elements, including the analysis unit, suggestion unit, dialogue unit, understanding unit, routing unit, and information provision unit, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the analysis unit is realized by at least one of the robot 414 and the data processing device 12. For example, the analysis unit can collect politicians' statements using the camera 42 and microphone 238 of the robot 414 and analyze them using the control unit 46A. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and uses AI to identify and suggest politicians who match the voters' interests. The dialogue unit is realized, for example, by the control unit 46A of the robot 414 and supports online dialogue between voters and politicians. The understanding unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes voters' input information and identifies their interests. The routing unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes voters' questions and routes them to appropriate politicians. The information providing unit is realized by, for example, the control unit 46A of the robot 414, and provides detailed information about each politician.

[0137] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0138] The proposal unit not only suggests politicians who match the interests of voters, but can also visually display the proposed politician's past policy achievements and statements. For example, the proposal unit can display a politician's past policy proposals in graphs and charts, providing information in a format that is visually easy for voters to understand. The proposal unit can also display the politician's statements as a keyword cloud, allowing voters to grasp their main interests at a glance. Furthermore, the proposal unit can simulate the impact of a politician's policies and visually display the results. In this way, the proposal unit helps voters make more informed choices.

[0139] The identification unit can not only identify voters' interests but also track changes in voters' interests in real time. For example, the identification unit can analyze voters' activities on online platforms to detect changes in their interests. The identification unit can also analyze voters' posts on social media to identify changes in their interests in real time. Furthermore, the identification unit can analyze the frequency and content of voters' viewing of news articles to identify changes in their interests. This enables the identification unit to respond quickly to changes in voters' interests and make more appropriate suggestions.

[0140] The routing unit not only analyzes voters' questions and routes them to the appropriate politicians, but also provides additional relevant information based on the content of the question. For example, the routing unit analyzes the content of voters' questions and provides relevant policy information or news articles. The routing unit can also provide relevant statistical data or research results based on the content of voters' questions. Furthermore, the routing unit can provide records of past parliamentary debates related to the content of voters' questions. In this way, the routing unit helps voters have more informed conversations.

[0141] The information provision unit not only provides detailed information about each politician, but can also evaluate and display the reliability of the information. For example, the information provision unit can evaluate the reliability of a politician's statements and policy proposals and display a reliability score. The information provision unit can also evaluate the reliability of a politician's information sources and preferentially display information from highly reliable sources. Furthermore, the information provision unit can fact-check a politician's statements and policy proposals and display the results. In this way, the information provision unit supports voters in making choices based on highly reliable information.

[0142] The analysis department not only collects and analyzes data on politicians' careers, policies, and statements, but can also analyze politicians' networks and evaluate their influence. For example, the analysis department can analyze a politician's personal connections and evaluate their relationships with influential people. The analysis department can also analyze a politician's network of supporters and collaborators and evaluate their influence. Furthermore, the analysis department can analyze a politician's network of followers and supporters on social media and evaluate their influence. This allows the analysis department to comprehensively evaluate a politician's influence and enable more accurate analysis.

[0143] The proposal unit can estimate the voter's emotions and adjust the way the proposal is expressed based on the estimated voter's emotions. For example, if the voter is feeling anxious, the proposal unit can make the proposal using an expression that gives a sense of security. Also, if the voter is excited, the proposal unit can make the proposal using an expression that includes detailed information. Also, if the voter is calm, the proposal unit can make the proposal using an objective expression based on data. In this way, the proposal unit can make more appropriate proposals by adjusting the way the proposal is expressed based on the voter's emotions.

[0144] The dialogue unit not only provides voters with the ability to directly interact with politicians through an online platform, but also analyzes the progress of the dialogue in real time and can follow up at the appropriate time. For example, the dialogue unit uses AI to analyze the progress of the dialogue in real time and follow up at the appropriate time. The dialogue unit can also use AI to suggest the next question based on the progress of the dialogue. The dialogue unit can also refer to the progress of the dialogue to keep the flow of the dialogue smooth. This allows the dialogue unit to analyze the progress of the dialogue in real time and follow up at the appropriate time.

[0145] The analysis unit can estimate voter sentiment and adjust the analysis method for politician profiles based on the estimated voter sentiment. For example, if voters are feeling anxious, the analysis unit can have the AI ​​prioritize analyzing information about the politician's trustworthiness. Alternatively, if voters are excited, the analysis unit can have the AI ​​focus on analyzing the politician's latest activities and statements. Alternatively, if voters are calm, the analysis unit can have the AI ​​analyze the politician's past policy performance in detail. This allows the analysis unit to adjust its analysis method based on voter sentiment, enabling more appropriate analysis.

[0146] The proposal unit can estimate the voter's emotions and adjust the length of the proposal based on the estimated voter's emotions. For example, if the voter is feeling anxious, the proposal unit can make a short, to-the-point proposal. If the voter is excited, the proposal unit can also make a longer proposal with detailed information. If the voter is calm, the proposal unit can also make a detailed proposal based on data. This allows the proposal unit to make more appropriate proposals by adjusting the length of the proposal based on the voter's emotions.

[0147] The dialogue unit can estimate voter emotions and prioritize dialogues based on the estimated voter emotions. For example, if a voter is feeling anxious, the dialogue unit can prioritize dialogues that provide a sense of security. Also, if a voter is excited, the dialogue unit can prioritize dialogues that include detailed information. Also, if a voter is calm, the dialogue unit can prioritize objective dialogues based on data. This allows the dialogue unit to prioritize dialogues based on voter emotions, enabling more appropriate dialogues.

[0148] The processing flow of the second embodiment will be briefly explained below.

[0149] Step 1: The analysis unit analyzes the politician's profile. For example, the analysis unit collects detailed data such as the politician's career, policies, and statements, and analyzes it using AI. The analysis unit analyzes the politician's past statements and policy proposals to understand the politician's position. AI can also be used to perform detailed analysis of the politician's profile. Step 2: The proposal unit makes proposals that match the voter's interests based on the data analyzed by the analysis unit. For example, if a voter is interested in environmental issues, the proposal unit can suggest politicians who are focusing on environmental policies. AI can also be used to identify politicians who match the voter's interests. Step 3: The dialogue unit provides a function for voters to directly interact online with the politicians proposed by the proposal unit. For example, the dialogue unit can enable voters to enter questions and politicians to respond to them. It can also use AI to support the dialogue between voters and politicians.

[0150] 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.

[0151] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). 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 speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. 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. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0152] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0153] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0154] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0155] 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.

[0156] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0157] 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.

[0158] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0159] 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 user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0164] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0165] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0166] 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.

[0167] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0168] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0169] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0170] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0171] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0172] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0173] 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.

[0174] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0175] 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 user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0180] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0181] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0182] 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.

[0183] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0184] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0185] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0186] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0187] 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.

[0188] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0189] 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.

[0190] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0191] 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 image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0192] 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.

[0193] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the 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.

[0194] 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.

[0195] 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.

[0196] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0197] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0198] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0199] 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.

[0200] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0201] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0202] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0203] 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.

[0204] FIG. 9 illustrates 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 behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions 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.

[0205] 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.

[0206] 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).

[0207] 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 expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, 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 expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, 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.

[0208] 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."

[0209] 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.

[0210] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, 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. A processor also includes 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.

[0215] The hardware resource that executes the specific process 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 process may be a single processor.

[0216] 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.

[0217] 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.

[0218] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0219] 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.

[0220] 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.

[0221] [Explanation of symbols]

[0222] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. An analysis department that analyzes politicians' profiles, a proposal unit that makes proposals that match the interests of voters based on the data analyzed by the analysis unit; and a dialogue unit through which voters directly dialogue online with the politicians proposed by the proposal unit. A system characterized by:

2. Equipping the department with the task of understanding voter interests 2. The system of claim 1.

3. Equipped with a routing unit that analyzes voter questions and routes them to the appropriate politicians 2. The system of claim 1.

4. It has an information section that provides detailed information about each politician.

2. The system of claim 1.

5. The analysis unit Collect data on politicians' careers, policies, and statements and analyze it using AI 2. The system of claim 1.

6. The proposal unit Propose politicians who are aligned with voters' interests 2. The system of claim 1.

7. The dialogue unit Providing voters with the ability to interact directly with politicians through online platforms 2. The system of claim 1.

8. The analysis unit Estimate voter sentiment and adjust the analysis of politician profiles based on the estimated voter sentiment 2. The system of claim 1.

9. The analysis unit During analysis, refer to the politicians' past election results to improve the accuracy of the analysis.

2. The system of claim 1.

Images