system

Abstract

We provide the system. [Solution] A means of obtaining user value information through surveys, A means of acquiring and analyzing candidate information data, A means of calculating the degree of agreement by comparing user value information with candidate information, A means of presenting candidate information to users based on the degree of match, A means for users to make electronic donations based on the candidate information presented, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern democratic societies, many individuals have difficulty obtaining sufficient information to appropriately select candidates or political parties, resulting in a problem of sparse voting behavior. In particular, for those with low interest in politics and the younger generation, how to select and discard a vast amount of political information has become a major issue. Also, when the pledges of election candidates or political parties are confusing, or it is not easy to determine the degree of alignment with one's own values, rational voting behavior may be hindered.

Means for Solving the Problems

[0005] This invention provides a system that collects user value information through a questionnaire and analyzes information on candidate and political party pledges and achievements obtained from a database based on that information. This system analyzes candidate information using a generative model, compares and unifies the user's value information with the candidate information, and calculates the degree of agreement to present the candidate or political party that is most suitable for each individual user. Furthermore, by weighting areas of particular interest to the user and refining the calculation of the degree of agreement, the system enables users to make rational decisions in a short amount of time. This promotes user voting behavior and can lead to an increase in voter turnout.

[0006] A "survey" is a set of questions designed to gather information about users' values ​​and their opinions on policies.

[0007] "Values ​​information" refers to information about political interests and policies that users consider important, obtained from questionnaires they have answered.

[0008] "Candidate information" refers to information stored in the database about candidates and political parties, including their platform, past achievements, and social media ratings.

[0009] A "database" is a collection of information that stores candidate information and manages it in a searchable and retrievalable format.

[0010] A "generative model" is an artificial intelligence algorithm designed for data analysis and information generation.

[0011] "Agreement score" is a numerical value obtained by comparing the user's values ​​information with candidate information, indicating the degree to which the user's views align with those of the candidate or political party.

[0012] "Weighting" is a method of assigning a higher value to certain elements or conditions than to other elements. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] An example of an embodiment of the system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0016] In the following embodiments, a tagged processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, a tagged RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, a tagged storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0019] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

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

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] This invention is a system that assists users in selecting the most suitable candidate or political party, and its embodiments are described below. This system exchanges information among three parties: a terminal, a server, and a user.

[0035] First, the device presents the user with a questionnaire. The questionnaire includes questions about political values, policies of interest, and social issues that the user considers important. By answering this questionnaire, the user's values ​​information is generated. This values ​​information is sent from the device to a server and becomes the basic data for analysis.

[0036] The server collects information from its accumulated database, including each candidate's and party's pledges, past achievements, and social media ratings. This data is managed to keep it constantly up-to-date. The server then uses a generative model to analyze the candidate information and extract keywords related to each candidate's characteristics and policies.

[0037] The server's next step is to compare the user's values ​​information with the candidate's data. A matching algorithm is used to calculate the degree of agreement between the two. This calculation is weighted particularly towards policy areas that the user prioritizes, resulting in a more accurate match.

[0038] Finally, the terminal displays the matching score results sent from the server to the user. For example, a user who focuses on environmental issues might be presented with candidates who actively propose environmental policies with a high matching score. The displayed information includes the candidate's name, matching score, and reasons for recommendation, which the user can use to consider who to vote for.

[0039] This system allows users to efficiently acquire information and select candidates and political parties that best align with their values, thereby promoting rational voting behavior.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The device presents the user with a questionnaire. The questionnaire includes questions about the user's political values ​​and policy interests. By answering this questionnaire, the user's own value system is formed.

[0043] Step 2:

[0044] The device sends the user's response data to the server. The server stores the received data in preparation for analysis.

[0045] Step 3:

[0046] The server collects candidate information from a database. This information includes candidates' pledges, past achievements, and social media ratings. The server retrieves the latest data and keeps it constantly updated.

[0047] Step 4:

[0048] The server uses a generative model to analyze candidate information. This analysis extracts the characteristics and policy keywords of each candidate.

[0049] Step 5:

[0050] The server compares the user's values ​​information with candidate information. The server uses a matching algorithm to calculate the degree of match between the user and each candidate. In this process, the user's areas of focus are given particular weight.

[0051] Step 6:

[0052] The server sends the calculation results to the terminal. These results include the name of the candidate who best matches the user, the degree of match, and the reason for the recommendation.

[0053] Step 7:

[0054] The device displays the results it received to the user. The user then considers which candidate to vote for based on the information presented.

[0055] (Example 1)

[0056] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0057] Traditional election support systems have faced challenges in providing users with sufficient information to select candidates and political parties that best align with their values, making rational voting decisions difficult. Furthermore, collecting fair and reliable data from the vast amount of information available online and conducting analyses tailored to users' interests and values ​​is not easy.

[0058] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0059] In this invention, the server includes means for acquiring user value information through an information input device, means for acquiring and analyzing pledges and past achievements from candidate information sources, and means for comparing the user's value information with candidate information and calculating the degree of agreement. This makes it possible for users to easily obtain information on candidates and political parties that match their own values, thereby supporting rational voting behavior.

[0060] An "information input device" is a device that collects information about users' values ​​and transmits it to a server as structured data.

[0061] "User value information" refers to data that indicates the political values ​​and interests of users, and is collected through survey responses.

[0062] "Sources of candidate information" refer to databases and other information sources that hold information related to candidates, such as their pledges, past achievements, and evaluations.

[0063] A "campaign promise" is information that outlines the policy commitments and goals that a candidate presents during their election campaign.

[0064] "Past achievements" refers to information that shows the results and accomplishments a candidate has achieved through their political activities in the past.

[0065] A "generative model" is an artificial intelligence model used for data analysis, specifically for extracting keywords related to candidate characteristics and policies.

[0066] "Score of agreement" is an indicator that shows the compatibility between the user's value information and the candidate's information, and is calculated using an appropriate matching algorithm.

[0067] The system in this invention consists of a combination of an information input device, a server, and a user terminal. The information input device presents a questionnaire to the user and collects value information. The user answers the questionnaire, and that value information is transmitted from the information input device to the server.

[0068] The server is a high-performance computer with the ability to access a stored database. This database contains important information such as candidates' pledges and past achievements. The server retrieves the necessary information from this database and analyzes the data using a generative AI model. The generative AI model is used to extract candidate characteristics and relevant policy keywords.

[0069] The server then compares the user's values ​​information with the analyzed candidate information. A matching algorithm is applied, weighting key areas based on the user's interests and calculating the degree of match. Based on this degree of match, the server sends candidate information with a high degree of match to the user's terminal.

[0070] The user terminal displays the matching score results received from the server on the screen. By referring to the presented information, the user can obtain the information needed to select the candidate or political party that best matches their values.

[0071] Specific example

[0072] For example, if a user inputs value information such as "I am interested in renewable energy" into an information input device, the server will gather information on candidates with policies related to renewable energy from its database and analyze it with a generative AI model to generate a list of suitable candidates. The user can then use this list to make a rational decision about who to vote for.

[0073] Example of a prompt

[0074] "Who is the candidate whose values ​​best align with mine? I place great importance on environmental issues and renewable energy."

[0075] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0076] Step 1:

[0077] The device presents the user with a survey. The input includes the survey questions. The user answers these questions and generates their own values ​​information. Specifically, the user selects options for each question and enters comments as needed. As a result, the user's values ​​information is output on the device as structured data.

[0078] Step 2:

[0079] The terminal sends value information it generates to the server. The input includes value information generated by the user. The terminal performs secure communication and transmits the value information to the server. The output is the value information data received by the server.

[0080] Step 3:

[0081] The server calls the database to collect candidate information. Input includes candidate pledges, past performance, and relevant evaluation information retrieved from the database. The server automatically accesses the database and collects this data. The output is a dataset of candidate information stored within the server.

[0082] Step 4:

[0083] The server uses a generative AI model to analyze candidate information. The input includes a dataset of collected candidate information. The server applies the generative AI model to extract policy keywords and candidate characteristics. The output is the analyzed dataset.

[0084] Step 5:

[0085] The server compares the analyzed data with the user's values ​​information. The input includes the user's values ​​information and the analyzed candidate data. The server uses a matching algorithm to compare the data and calculate the degree of agreement. The output includes a numerical score of agreement and related information.

[0086] Step 6:

[0087] The server sends the match score results to the terminal. The input includes the calculated match score and associated candidate information. The server then sends these results back to the terminal. The output is a dataset for display on the user terminal.

[0088] Step 7:

[0089] The terminal displays the matching score results to the user. The input includes a dataset of matching scores and candidate information received from the server. The terminal visualizes this on the screen and displays it for the user to see. The output includes specific candidate information and their matching scores presented to the user.

[0090] (Application Example 1)

[0091] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0092] In current voting practices, it is difficult for voters to find candidates or political parties that align with their values ​​and interests, and the means to support those candidates are limited. This hinders rational voting and reduces the willingness to participate in political activities. In this situation, there is a need for a system that efficiently and accurately supports candidate selection and further promotes support for those candidates.

[0093] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0094] In this invention, the server includes means for acquiring user value information through questionnaires, means for acquiring and analyzing candidate information data, means for comparing the user's value information with the candidate information to calculate the degree of agreement, and means for the user to make electronic donations based on the presented candidate information. This makes it possible for users to not only choose the candidate or political party that best matches their values, but also to easily support that candidate, thereby promoting rational voting behavior.

[0095] A "survey" is a question-based method used to understand users' political values, interests, and the social issues they are concerned with.

[0096] "Values ​​information" refers to data that indicates users' political and social values, obtained through surveys.

[0097] "Candidate information" refers to information obtained from a database that includes the pledges, past achievements, and evaluations of political candidates and political parties.

[0098] "Analysis" is the process of thoroughly investigating candidate information and extracting keywords related to their characteristics and policies.

[0099] "Score of agreement" is an evaluation metric that compares user value information with candidate information to show how well the two match.

[0100] "Presentation" refers to the act of visually displaying candidate information to the user based on a calculated degree of similarity.

[0101] "Electronic donation" is a method of providing financial support online based on candidate information presented to the user.

[0102] The system for implementing this invention begins with the user answering a questionnaire via a terminal. The questionnaire includes questions designed to understand the user's political values ​​and social issues of interest. Once the user answers the questionnaire, the results are transmitted from the terminal to the server as value information.

[0103] Based on the received values ​​information, the server refers to a database of candidate information and collects each candidate's pledges, past achievements, and evaluations. This candidate information is analyzed using a generative AI model to extract keywords related to the candidates' characteristics and policies.

[0104] The server then compares the user's values ​​information with candidate information using a matching degree calculation algorithm. It assigns weights to policy areas that the user considers particularly important, and precisely calculates the degree of matching. Candidate information is then displayed on the terminal in order of highest matching degree.

[0105] Users can make electronic donations through their devices based on the highly matched candidates presented. Donations are processed through an electronic payment system, offering a variety of payment options.

[0106] For example, if a user indicates a particular interest in "environmental issues," the survey will include a prompt such as, "How interested are you in environmental policy?" After the user responds, the server will present candidates with a high degree of matching who have policies specifically focused on environmental issues. Smartphones and smart glasses are used throughout this entire process to enhance user convenience.

[0107] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0108] Step 1:

[0109] The user answers a survey via their device. The survey includes questions about political values ​​and social issues, generating the user's values ​​information. The input for this step is the user's answers, and the output is sent to the server as values ​​information.

[0110] Step 2:

[0111] The server collects candidate information from the database based on the received values ​​information. Candidate information includes pledges, past achievements, and evaluations. In this step, values ​​information is provided as input, and candidate information for analysis is output.

[0112] Step 3:

[0113] The server analyzes candidate information using a generation AI model. Here, keywords related to candidate characteristics and policies are extracted. The input in this step is candidate information, and the output is the policy keywords resulting from the analysis.

[0114] Step 4:

[0115] The server compares the user's values ​​information with the analysis results of the generated AI model and calculates the degree of agreement. In this process, specific policy areas are weighted. The input is the values ​​information and analysis results, and the output is the degree of agreement.

[0116] Step 5:

[0117] The server sends candidate information to the terminal in order of matching degree and presents it to the user. The input for this step is the matching degree, and the output is the presented candidate information.

[0118] Step 6:

[0119] Users make electronic donations via their terminal based on the presented candidate information. The input is candidate selection based on the degree of match, and the output is the completion of the donation through the electronic payment system.

[0120] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0121] This invention is a system that assists users in selecting the most suitable candidates and political parties, and is particularly characterized by its ability to recognize the user's emotions and utilize that data to provide even more accurate and personalized information. This system processes information among three parties: the terminal, the server, and the user.

[0122] First, the device displays a questionnaire to the user. The user then answers the presented questionnaire. At this time, the device has an emotion engine built in, which can analyze the user's emotions in real time. The results of this emotion analysis are added to the user's value information, improving the accuracy of the data.

[0123] The survey responses and sentiment analysis results are sent from the terminal to the server. The server receives this data and accesses a database to collect information such as the candidate's pledges, past achievements, and social media ratings. This data is frequently updated to ensure it remains up-to-date.

[0124] The server uses a generative model to analyze candidate information and extracts candidate characteristics and policy keywords based on the analysis results. It then matches the candidate information with a user profile that takes into account the user's values ​​and sentiment analysis results. This allows the server to calculate the degree of match between the user and each candidate. In calculating the degree of match, the sentiment expressed by the user in specific policy areas is also weighted.

[0125] The calculated match score is sent from the server to the terminal and presented to the user. The presentation includes the name of the candidate or party, the match score, and the reason for the recommendation, allowing the user to consider the options.

[0126] For example, if a user shows strong interest in a particular policy, and the emotion engine recognizes the user's emotions as positive at the time of their response, then candidates who focus on that policy will be suggested to the user with a high degree of agreement. This system allows users to conduct election campaigns based on their own values ​​and emotions, leading to a deeper understanding of the issues.

[0127] The following describes the processing flow.

[0128] Step 1:

[0129] The device displays a survey to the user. The survey consists of questions about political values ​​and policy interests, and the user answers these questions.

[0130] Step 2:

[0131] The emotion engine built into the device analyzes the user's emotions in real time while they are answering the survey. The emotion engine determines the emotional category, such as positive, negative, or neutral, by analyzing the user's voice tone, facial expressions, response speed, and other factors.

[0132] Step 3:

[0133] After a user completes a survey, their device sends the response data and analyzed sentiment data to a server. This data is then organized as information about the user's values.

[0134] Step 4:

[0135] The server accesses the database here to collect information such as candidates' pledges, past achievements, and social media ratings. The database is regularly updated to maintain the most up-to-date information.

[0136] Step 5:

[0137] The server uses a generative model to analyze the collected candidate information. This analysis extracts and lists the candidate's policy keywords and characteristics.

[0138] Step 6:

[0139] The server matches the user's values ​​information (including emotional data) with candidate information. The server uses a matching algorithm to calculate the degree of agreement between the user and each candidate. In this calculation, particular weight is given to policy areas in which the user has a strong emotional response.

[0140] Step 7:

[0141] The calculated match score is sent from the server to the terminal. The result includes each candidate's name, match score, and reason for recommendation.

[0142] Step 8:

[0143] The device displays the matching score results to the user. Based on the information presented, the user can consider which candidate they are more interested in. Personalized candidate suggestions are possible because the matching score takes into account the user's sentiment data.

[0144] (Example 2)

[0145] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0146] In elections and political choices, there is a challenge in accurately and effectively reflecting the emotions and values ​​of users. Traditional methods do not adequately consider users' emotions when providing information, resulting in a situation where it is difficult for users to choose the most suitable candidates or policies.

[0147] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0148] In this invention, the server includes means for analyzing the user's emotions and integrating the results with the user's values ​​information, means for obtaining and analyzing pledges and achievements from a data storage of candidate information, and means for analyzing candidate information using a generative model. This makes it possible to present personalized candidate information that reflects the user's emotions and values.

[0149] A "survey" is a series of questions presented to users to confirm their values ​​and opinions.

[0150] A "device" is a component of a machine or system designed to perform a specific function.

[0151] "Emotional analysis" is a technology that determines a user's psychological state based on their facial expressions, tone of voice, and other factors.

[0152] "Values ​​information" refers to data about users' beliefs and what they consider important.

[0153] "Candidate information" refers to various data about candidates who are the subject of elections or political choices.

[0154] A "generative model" is an algorithm used to make predictions and analyses for specific purposes or problems based on large amounts of data.

[0155] "Score of agreement" is a numerical value or indicator that shows the degree of compatibility between the user's value information and the analyzed candidate information.

[0156] This system is designed to help users select the most suitable candidates and political parties. In particular, it aims to provide more accurate information by analyzing users' emotions in real time and integrating that data with value-based information.

[0157] First, the device displays a survey to the user and accepts their responses. The survey includes questions such as which policies the user is interested in. At this time, the device is equipped with an emotion analysis engine that analyzes the user's facial expressions and tone of voice through the camera and microphone. The results of the emotion analysis are directly integrated into the user's values ​​information.

[0158] Next, the device sends the survey results and sentiment analysis data to the server. The server receives this data and collects candidate information (such as pledges, achievements, and social media ratings) stored in its database. This candidate information is frequently updated to ensure it is always up-to-date.

[0159] The server analyzes candidate information using a generative AI model, extracting its characteristics and policy keywords. The data obtained from this analysis is processed by the generative AI model, and the degree of match with the optimal candidate is calculated. The user's sentiment towards a specific policy area is also reflected as a weight in this match calculation.

[0160] For example, if a user expresses interest in environmental policy and the sentiment analysis engine detects positive emotions during their survey response, the system will recommend candidates who focus on environmental policy with a high degree of agreement. In this way, users can make more appropriate choices based on their own values ​​and emotions.

[0161] An example of a prompt might be, "Please explain how the emotional data analyzed in real time by a device equipped with an emotion engine influences user choices." This prompt provides detailed information about the system's operation and its intended purpose.

[0162] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0163] Step 1:

[0164] The device displays a survey to the user. The survey input consists of question information, which are comprehensive questions. The user answers based on these questions. The device uses its built-in camera and microphone to analyze the user's emotions in real time from their facial expressions and voice. This analysis generates emotion data, such as positive or negative, which is output along with the user's answers.

[0165] Step 2:

[0166] The terminal transmits the analyzed sentiment data and user survey response data to the server via communication means such as the internet. The server receives this input data and stores it in data storage. At this stage, the data format is also converted and shaped to a format suitable for analysis.

[0167] Step 3:

[0168] The server accesses data storage and collects data from candidate information, including pledges, past performance, and social media ratings. The collected data becomes input for analysis using a generative AI model. The server runs the generative AI model and extracts candidate characteristics and policy keywords. This result is output as analysis data.

[0169] Step 4:

[0170] The server compares user profiles, including sentiment data and survey response data, with analyzed candidate data to calculate the degree of match. Here, the user's sentiment towards a particular policy is considered as a weight for the degree of match. A set of match scores is output as a result of this calculation.

[0171] Step 5:

[0172] The server prepares candidate information to recommend to the user based on the match score. This information includes the candidate's name, match score, and reason for recommendation. The recommendation information is prioritized to reflect its importance to the user.

[0173] Step 6:

[0174] The server sends the prepared recommendation information to the terminal. The terminal receives this data and presents it visually to the user. The user can review the candidate information through lists and charts on the screen and make the best selection.

[0175] (Application Example 2)

[0176] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0177] It is difficult for viewers to efficiently select videos that match their interests and emotions from a vast amount of content. In particular, the lack of personalized suggestions based on emotions is a challenge in increasing viewer satisfaction.

[0178] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0179] In this invention, the server includes means for acquiring user preference information at the time of viewing, means for acquiring and analyzing relevant information from a data bank of viewing content, and means for comparing the user preference information with content information to calculate the relationship. This makes it possible to suggest personalized content that matches the viewer's emotions and preferences.

[0180] "User preference information" refers to information about the personal preferences and interests that viewers express in relation to the content they watch.

[0181] "Means of acquisition during viewing" refers to technologies for capturing and analyzing viewers' behavior and viewing records in real time as they play video content.

[0182] A "data bank of viewing content" is a collection of data containing a wide variety of videos and related information, which can be accessed according to the viewer's needs.

[0183] "Means for acquiring and analyzing relevant information" refers to methods for collecting information such as metadata and user reviews related to the content being viewed, and for analyzing patterns and trends based on that information.

[0184] A "means for calculating relevance" is an algorithm that compares a user's preference information with the characteristics of the content they watch and quantifies the degree of agreement.

[0185] "Personalized content suggestions" refers to selecting and presenting content that is best suited to each individual viewer based on an analysis of their past viewing history and emotions.

[0186] To realize this invention, a system is used that acquires and processes viewer preference information in real time when viewers watch video content. The system consists of a terminal such as a smartphone or tablet and a server that performs data analysis.

[0187] While the viewer is playing content, the device uses sensors such as cameras and microphones to collect the viewer's facial expressions and voice, and performs emotion analysis. This analysis uses emotion AI software such as "Affectiva." The preference information obtained as a result of the analysis is securely transmitted to and stored on a server using cloud technology such as "Firebase."

[0188] The server uses a generative AI model to analyze the received preference information by comparing it with the characteristic information of the content being viewed in the database. This calculates the relevance of personalized content based on the viewer's emotions and past viewing history, and extracts the most suitable video content. The information thus calculated is sent back to the device and presented to the viewer as a recommendation.

[0189] For example, if a viewer is watching an emotionally moving film and shedding tears, this emotion is analyzed and recognized in real time. Based on this, other emotionally moving films are recommended from the server to the user's device. This makes it possible to effectively suggest content that matches the viewer's preferences and mood.

[0190] An example of a prompt is, "How can we suggest emotional content based on the emotions a user expresses during an emotional or romantic scene?" By inputting this prompt into a generative AI model, appropriate content recommendations tailored to the viewer's emotions can be achieved.

[0191] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0192] Step 1:

[0193] The device detects when the viewer starts playing content and activates its sensors. The device uses its camera and microphone to collect the viewer's facial expressions and voice in real time and analyzes their emotions. This analysis generates data that indicates the viewer's current emotional state.

[0194] Step 2:

[0195] The device transmits the analyzed sentiment data and viewing history to the server via the network. The input consists of the sentiment analysis results and viewing history data, which the server uses to prepare to match with content metadata recorded in its database.

[0196] Step 3:

[0197] Based on the sentiment data received by the server, a generative AI model is applied to update the viewer's profile. The inputs are sentiment data, viewing history, and existing viewer profiles. Data calculations are performed on this data, and personalized preference data is output. This result enables more accurate content recommendations.

[0198] Step 4:

[0199] The server utilizes a generative model to compare viewing content with viewer profiles in the database. This process involves inputting updated viewer profiles and content metadata. The server calculates content relevance based on the viewer's preferences and emotions, and extracts and lists matching content.

[0200] Step 5:

[0201] The server generates a list of highly relevant content and sends the results to the terminal. The output is a list of recommended content based on the viewer's preferences, which is then passed to the terminal. The terminal receives this list and presents the results to the viewer through an intuitive interface.

[0202] Step 6:

[0203] The user selects the next content they wish to view from the presented content. This generates new data based on the user's selection, which is used to improve their profile for future viewing. This output data is then used in subsequent analysis processes.

[0204] Through these steps, it becomes possible to recommend the most suitable content based on the viewer's emotions and preferences.

[0205] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0206] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0207] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0208] [Second Embodiment]

[0209] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0210] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0211] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0212] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0213] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0214] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0215] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0216] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0217] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0218] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0219] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0220] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0221] This invention is a system that assists users in selecting the most suitable candidate or political party, and its embodiments are described below. This system exchanges information among three parties: a terminal, a server, and a user.

[0222] First, the device presents the user with a questionnaire. The questionnaire includes questions about political values, policies of interest, and social issues that the user considers important. By answering this questionnaire, the user's values ​​information is generated. This values ​​information is sent from the device to a server and becomes the basic data for analysis.

[0223] The server collects information from its accumulated database, including each candidate's and party's pledges, past achievements, and social media ratings. This data is managed to keep it constantly up-to-date. The server then uses a generative model to analyze the candidate information and extract keywords related to each candidate's characteristics and policies.

[0224] The server's next step is to compare the user's values ​​information with the candidate's data. A matching algorithm is used to calculate the degree of agreement between the two. This calculation is weighted particularly towards policy areas that the user prioritizes, resulting in a more accurate match.

[0225] Finally, the terminal displays the matching score results sent from the server to the user. For example, a user who focuses on environmental issues might be presented with candidates who actively propose environmental policies with a high matching score. The displayed information includes the candidate's name, matching score, and reasons for recommendation, which the user can use to consider who to vote for.

[0226] This system allows users to efficiently acquire information and select candidates and political parties that best align with their values, thereby promoting rational voting behavior.

[0227] The following describes the processing flow.

[0228] Step 1:

[0229] The device presents the user with a questionnaire. The questionnaire includes questions about the user's political values ​​and policy interests. By answering this questionnaire, the user's own value system is formed.

[0230] Step 2:

[0231] The device sends the user's response data to the server. The server stores the received data in preparation for analysis.

[0232] Step 3:

[0233] The server collects candidate information from a database. This information includes candidates' pledges, past achievements, and social media ratings. The server retrieves the latest data and keeps it constantly updated.

[0234] Step 4:

[0235] The server uses a generative model to analyze candidate information. This analysis extracts the characteristics and policy keywords of each candidate.

[0236] Step 5:

[0237] The server compares the user's values ​​information with candidate information. The server uses a matching algorithm to calculate the degree of match between the user and each candidate. In this process, the user's areas of focus are given particular weight.

[0238] Step 6:

[0239] The server sends the calculation results to the terminal. These results include the name of the candidate who best matches the user, the degree of match, and the reason for the recommendation.

[0240] Step 7:

[0241] The device displays the results it received to the user. The user then considers which candidate to vote for based on the information presented.

[0242] (Example 1)

[0243] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0244] Traditional election support systems have faced challenges in providing users with sufficient information to select candidates and political parties that best align with their values, making rational voting decisions difficult. Furthermore, collecting fair and reliable data from the vast amount of information available online and conducting analyses tailored to users' interests and values ​​is not easy.

[0245] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0246] In this invention, the server includes means for acquiring user value information through an information input device, means for acquiring and analyzing pledges and past achievements from candidate information sources, and means for comparing the user's value information with candidate information and calculating the degree of agreement. This makes it possible for users to easily obtain information on candidates and political parties that match their own values, thereby supporting rational voting behavior.

[0247] An "information input device" is a device that collects information about users' values ​​and transmits it to a server as structured data.

[0248] "User value information" refers to data that indicates the political values ​​and interests of users, and is collected through survey responses.

[0249] "Sources of candidate information" refer to databases and other information sources that hold information related to candidates, such as their pledges, past achievements, and evaluations.

[0250] A "campaign promise" is information that outlines the policy commitments and goals that a candidate presents during their election campaign.

[0251] "Past achievements" refers to information that shows the results and accomplishments a candidate has achieved through their political activities in the past.

[0252] A "generative model" is an artificial intelligence model used for data analysis, specifically for extracting keywords related to candidate characteristics and policies.

[0253] "Score of agreement" is an indicator that shows the compatibility between the user's value information and the candidate's information, and is calculated using an appropriate matching algorithm.

[0254] The system in this invention consists of a combination of an information input device, a server, and a user terminal. The information input device presents a questionnaire to the user and collects value information. The user answers the questionnaire, and that value information is transmitted from the information input device to the server.

[0255] The server is a high-performance computer with the ability to access a stored database. This database contains important information such as candidates' pledges and past achievements. The server retrieves the necessary information from this database and analyzes the data using a generative AI model. The generative AI model is used to extract candidate characteristics and relevant policy keywords.

[0256] The server then compares the user's values ​​information with the analyzed candidate information. A matching algorithm is applied, weighting key areas based on the user's interests and calculating the degree of match. Based on this degree of match, the server sends candidate information with a high degree of match to the user's terminal.

[0257] The user terminal displays the matching score results received from the server on the screen. By referring to the presented information, the user can obtain the information needed to select the candidate or political party that best matches their values.

[0258] Specific example

[0259] For example, if a user inputs value information such as "I am interested in renewable energy" into an information input device, the server will gather information on candidates with policies related to renewable energy from its database and analyze it with a generative AI model to generate a list of suitable candidates. The user can then use this list to make a rational decision about who to vote for.

[0260] Example of a prompt

[0261] "Who is the candidate whose values ​​best align with mine? I place great importance on environmental issues and renewable energy."

[0262] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0263] Step 1:

[0264] The device presents the user with a survey. The input includes the survey questions. The user answers these questions and generates their own values ​​information. Specifically, the user selects options for each question and enters comments as needed. As a result, the user's values ​​information is output on the device as structured data.

[0265] Step 2:

[0266] The terminal sends value information it generates to the server. The input includes value information generated by the user. The terminal performs secure communication and transmits the value information to the server. The output is the value information data received by the server.

[0267] Step 3:

[0268] The server calls the database to collect candidate information. Input includes candidate pledges, past performance, and relevant evaluation information retrieved from the database. The server automatically accesses the database and collects this data. The output is a dataset of candidate information stored within the server.

[0269] Step 4:

[0270] The server uses a generative AI model to analyze candidate information. The input includes a dataset of collected candidate information. The server applies the generative AI model to extract policy keywords and candidate characteristics. The output is the analyzed dataset.

[0271] Step 5:

[0272] The server compares the analyzed data with the user's values ​​information. The input includes the user's values ​​information and the analyzed candidate data. The server uses a matching algorithm to compare the data and calculate the degree of agreement. The output includes a numerical score of agreement and related information.

[0273] Step 6:

[0274] The server sends the match score results to the terminal. The input includes the calculated match score and associated candidate information. The server then sends these results back to the terminal. The output is a dataset for display on the user terminal.

[0275] Step 7:

[0276] The terminal displays the matching score results to the user. The input includes a dataset of matching scores and candidate information received from the server. The terminal visualizes this on the screen and displays it for the user to see. The output includes specific candidate information and their matching scores presented to the user.

[0277] (Application Example 1)

[0278] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0279] In the current voting behavior, there is a problem that it is difficult for users to find candidates or political parties that match their values and interests, and the means to support those candidates are limited. As a result, rational voting behavior is hindered, and the willingness to participate in political activities is also decreasing. In such a situation, a system that efficiently and accurately supports candidate selection and further promotes support actions is required.

[0280] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0281] In this invention, the server includes means for acquiring the user's value information through a questionnaire, means for acquiring and analyzing the data of candidate information, means for comparing the user's value information and candidate information to calculate the degree of match, and means for performing an electronic donation based on the candidate information presented by the user. As a result, not only can the user select the candidate or political party that best matches their values, but it also becomes possible to easily support that candidate, and it becomes possible to promote rational voting behavior.

[0282] A "questionnaire" is a means in the form of questions for grasping the user's political values, interests, and social issues of concern.

[0283] "Value information" is data indicating the political and social values of the user acquired through a questionnaire.

[0284] "Candidate information" is information obtained from a database including the manifestos, past achievements, and evaluations of political candidates and political parties.

[0285] "Analysis" refers to the process of thoroughly investigating candidate information and extracting keywords related to their characteristics and policies.

[0286] "Degree of match" is an evaluation index that compares the user's value information with candidate information and indicates the extent to which the two match.

[0287] "Presentation" refers to the act of visually displaying candidate information to the user based on the calculated degree of match.

[0288] "Electronic donation" is a means of providing financial support online based on the candidate information presented to the user.

[0289] The system for implementing this invention starts when the user first answers a questionnaire via a terminal. The questionnaire includes questions for understanding the user's political values and social issues of interest. When the user answers the questionnaire, the results are transmitted from the terminal to the server as value information.

[0290] Based on the received value information, the server refers to the database of candidate information and collects the pledges, past achievements, evaluations, etc. of each candidate. This candidate information is analyzed using a generative AI model, and keywords related to the candidate's characteristics and policies are extracted.

[0291] Next, the server compares the user's value information with the candidate information using a degree-of-match calculation algorithm. In particular, weights are assigned to the policy areas that the user values, and the degree of match is precisely calculated. The candidate information is displayed on the terminal in descending order of this degree of match.

[0292] Based on the presented candidates with a high degree of match, the user can make an electronic donation through the terminal. The donation operation is carried out via an electronic payment system, and various payment methods are available.

[0293] For example, if a user indicates a particular interest in "environmental issues," the survey will include a prompt such as, "How interested are you in environmental policy?" After the user responds, the server will present candidates with a high degree of matching who have policies specifically focused on environmental issues. Smartphones and smart glasses are used throughout this entire process to enhance user convenience.

[0294] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0295] Step 1:

[0296] The user answers a survey via their device. The survey includes questions about political values ​​and social issues, generating the user's values ​​information. The input for this step is the user's answers, and the output is sent to the server as values ​​information.

[0297] Step 2:

[0298] The server collects candidate information from the database based on the received values ​​information. Candidate information includes pledges, past achievements, and evaluations. In this step, values ​​information is provided as input, and candidate information for analysis is output.

[0299] Step 3:

[0300] The server analyzes candidate information using a generation AI model. Here, keywords related to candidate characteristics and policies are extracted. The input in this step is candidate information, and the output is the policy keywords resulting from the analysis.

[0301] Step 4:

[0302] The server compares the user's values ​​information with the analysis results of the generated AI model and calculates the degree of agreement. In this process, specific policy areas are weighted. The input is the values ​​information and analysis results, and the output is the degree of agreement.

[0303] Step 5:

[0304] The server transmits candidate information to the terminal in descending order of the degree of matching and presents it to the user. The input for this step is the degree of matching, and the output is the presented candidate information.

[0305] Step 6:

[0306] Based on the presented candidate information, the user makes an electronic donation via the terminal. The input is the candidate selection based on the degree of matching, and the output is the completion of the donation through the electronic payment system.

[0307] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion recognition model 59 and perform specific processing using the user's emotion.

[0308] The present invention is a system that supports a user in selecting an optimal candidate or political party. In particular, it is characterized by recognizing the user's emotion and using that data to provide more accurate personalized information. This system processes information among a terminal, a server, and a user.

[0309] First, the terminal displays a questionnaire to the user. The user answers the presented questionnaire. At this time, an emotion engine is incorporated in the terminal, and the user's emotion can be analyzed in real time. The result of this emotion analysis is added to the user's value information, improving the accuracy of the data.

[0310] The answers to the questionnaire and the results of the emotion analysis are transmitted from the terminal to the server. The server receives this, accesses the database, and collects information such as the manifestos of candidates, past achievements, and evaluations on SNS. These data are frequently updated to maintain the latest state.

[0311] The server uses a generative model to analyze candidate information and extracts candidate characteristics and policy keywords based on the analysis results. It then matches the candidate information with a user profile that takes into account the user's values ​​and sentiment analysis results. This allows the server to calculate the degree of match between the user and each candidate. In calculating the degree of match, the sentiment expressed by the user in specific policy areas is also weighted.

[0312] The calculated match score is sent from the server to the terminal and presented to the user. The presentation includes the name of the candidate or party, the match score, and the reason for the recommendation, allowing the user to consider the options.

[0313] For example, if a user shows strong interest in a particular policy, and the emotion engine recognizes the user's emotions as positive at the time of their response, then candidates who focus on that policy will be suggested to the user with a high degree of agreement. This system allows users to conduct election campaigns based on their own values ​​and emotions, leading to a deeper understanding of the issues.

[0314] The following describes the processing flow.

[0315] Step 1:

[0316] The device displays a survey to the user. The survey consists of questions about political values ​​and policy interests, and the user answers these questions.

[0317] Step 2:

[0318] The emotion engine built into the device analyzes the user's emotions in real time while they are answering the survey. The emotion engine determines the emotional category, such as positive, negative, or neutral, by analyzing the user's voice tone, facial expressions, response speed, and other factors.

[0319] Step 3:

[0320] After a user completes a survey, their device sends the response data and analyzed sentiment data to a server. This data is then organized as information about the user's values.

[0321] Step 4:

[0322] The server accesses the database here to collect information such as candidates' pledges, past achievements, and social media ratings. The database is regularly updated to maintain the most up-to-date information.

[0323] Step 5:

[0324] The server uses a generative model to analyze the collected candidate information. This analysis extracts and lists the candidate's policy keywords and characteristics.

[0325] Step 6:

[0326] The server matches the user's values ​​information (including emotional data) with candidate information. The server uses a matching algorithm to calculate the degree of agreement between the user and each candidate. In this calculation, particular weight is given to policy areas in which the user has a strong emotional response.

[0327] Step 7:

[0328] The calculated match score is sent from the server to the terminal. The result includes each candidate's name, match score, and reason for recommendation.

[0329] Step 8:

[0330] The device displays the matching score results to the user. Based on the information presented, the user can consider which candidate they are more interested in. Personalized candidate suggestions are possible because the matching score takes into account the user's sentiment data.

[0331] (Example 2)

[0332] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0333] In elections and political choices, there is a challenge in accurately and effectively reflecting the emotions and values ​​of users. Traditional methods do not adequately consider users' emotions when providing information, resulting in a situation where it is difficult for users to choose the most suitable candidates or policies.

[0334] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0335] In this invention, the server includes means for analyzing the user's emotions and integrating the results with the user's values ​​information, means for obtaining and analyzing pledges and achievements from a data storage of candidate information, and means for analyzing candidate information using a generative model. This makes it possible to present personalized candidate information that reflects the user's emotions and values.

[0336] A "survey" is a series of questions presented to users to confirm their values ​​and opinions.

[0337] A "device" is a component of a machine or system designed to perform a specific function.

[0338] "Emotional analysis" is a technology that determines a user's psychological state based on their facial expressions, tone of voice, and other factors.

[0339] "Values ​​information" refers to data about users' beliefs and what they consider important.

[0340] "Candidate information" refers to various data about candidates who are the subject of elections or political choices.

[0341] A "generative model" is an algorithm used to make predictions and analyses for specific purposes or problems based on large amounts of data.

[0342] "Score of agreement" is a numerical value or indicator that shows the degree of compatibility between the user's value information and the analyzed candidate information.

[0343] This system is designed to help users select the most suitable candidates and political parties. In particular, it aims to provide more accurate information by analyzing users' emotions in real time and integrating that data with value-based information.

[0344] First, the device displays a survey to the user and accepts their responses. The survey includes questions such as which policies the user is interested in. At this time, the device is equipped with an emotion analysis engine that analyzes the user's facial expressions and tone of voice through the camera and microphone. The results of the emotion analysis are directly integrated into the user's values ​​information.

[0345] Next, the device sends the survey results and sentiment analysis data to the server. The server receives this data and collects candidate information (such as pledges, achievements, and social media ratings) stored in its database. This candidate information is frequently updated to ensure it is always up-to-date.

[0346] The server analyzes candidate information using a generative AI model, extracting its characteristics and policy keywords. The data obtained from this analysis is processed by the generative AI model, and the degree of match with the optimal candidate is calculated. The user's sentiment towards a specific policy area is also reflected as a weight in this match calculation.

[0347] For example, if a user expresses interest in environmental policy and the sentiment analysis engine detects positive emotions during their survey response, the system will recommend candidates who focus on environmental policy with a high degree of agreement. In this way, users can make more appropriate choices based on their own values ​​and emotions.

[0348] An example of a prompt might be, "Please explain how the emotional data analyzed in real time by a device equipped with an emotion engine influences user choices." This prompt provides detailed information about the system's operation and its intended purpose.

[0349] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0350] Step 1:

[0351] The device displays a survey to the user. The survey input consists of question information, which are comprehensive questions. The user answers based on these questions. The device uses its built-in camera and microphone to analyze the user's emotions in real time from their facial expressions and voice. This analysis generates emotion data, such as positive or negative, which is output along with the user's answers.

[0352] Step 2:

[0353] The terminal transmits the analyzed sentiment data and user survey response data to the server via communication means such as the internet. The server receives this input data and stores it in data storage. At this stage, the data format is also converted and shaped to a format suitable for analysis.

[0354] Step 3:

[0355] The server accesses data storage and collects data from candidate information, including pledges, past performance, and social media ratings. The collected data becomes input for analysis using a generative AI model. The server runs the generative AI model and extracts candidate characteristics and policy keywords. This result is output as analysis data.

[0356] Step 4:

[0357] The server compares user profiles, including sentiment data and survey response data, with analyzed candidate data to calculate the degree of match. Here, the user's sentiment towards a particular policy is considered as a weight for the degree of match. A set of match scores is output as a result of this calculation.

[0358] Step 5:

[0359] The server prepares candidate information to recommend to the user based on the match score. This information includes the candidate's name, match score, and reason for recommendation. The recommendation information is prioritized to reflect its importance to the user.

[0360] Step 6:

[0361] The server sends the prepared recommendation information to the terminal. The terminal receives this data and presents it visually to the user. The user can review the candidate information through lists and charts on the screen and make the best selection.

[0362] (Application Example 2)

[0363] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0364] It is difficult for viewers to efficiently select videos that match their interests and emotions from a vast amount of content. In particular, the lack of personalized suggestions based on emotions is a challenge in increasing viewer satisfaction.

[0365] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0366] In this invention, the server includes means for acquiring user preference information at the time of viewing, means for acquiring and analyzing relevant information from a data bank of viewing content, and means for comparing the user preference information with content information to calculate the relationship. This makes it possible to suggest personalized content that matches the viewer's emotions and preferences.

[0367] "User preference information" refers to information about the personal preferences and interests that viewers express in relation to the content they watch.

[0368] "Means of acquisition during viewing" refers to technologies for capturing and analyzing viewers' behavior and viewing records in real time as they play video content.

[0369] A "data bank of viewing content" is a collection of data containing a wide variety of videos and related information, which can be accessed according to the viewer's needs.

[0370] "Means for acquiring and analyzing relevant information" refers to methods for collecting information such as metadata and user reviews related to the content being viewed, and for analyzing patterns and trends based on that information.

[0371] A "means for calculating relevance" is an algorithm that compares a user's preference information with the characteristics of the content they watch and quantifies the degree of agreement.

[0372] "Personalized content suggestions" refers to selecting and presenting content that is best suited to each individual viewer based on an analysis of their past viewing history and emotions.

[0373] To realize this invention, a system is used that acquires and processes viewer preference information in real time when viewers watch video content. The system consists of a terminal such as a smartphone or tablet and a server that performs data analysis.

[0374] While the viewer is playing content, the device uses sensors such as cameras and microphones to collect the viewer's facial expressions and voice, and performs emotion analysis. This analysis uses emotion AI software such as "Affectiva." The preference information obtained as a result of the analysis is securely transmitted to and stored on a server using cloud technology such as "Firebase."

[0375] The server uses a generative AI model to analyze the received preference information by comparing it with the characteristic information of the content being viewed in the database. This calculates the relevance of personalized content based on the viewer's emotions and past viewing history, and extracts the most suitable video content. The information thus calculated is sent back to the device and presented to the viewer as a recommendation.

[0376] For example, if a viewer is watching an emotionally moving film and shedding tears, this emotion is analyzed and recognized in real time. Based on this, other emotionally moving films are recommended from the server to the user's device. This makes it possible to effectively suggest content that matches the viewer's preferences and mood.

[0377] An example of a prompt is, "How can we suggest emotional content based on the emotions a user expresses during an emotional or romantic scene?" By inputting this prompt into a generative AI model, appropriate content recommendations tailored to the viewer's emotions can be achieved.

[0378] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0379] Step 1:

[0380] The device detects when the viewer starts playing content and activates its sensors. The device uses its camera and microphone to collect the viewer's facial expressions and voice in real time and analyzes their emotions. This analysis generates data that indicates the viewer's current emotional state.

[0381] Step 2:

[0382] The device transmits the analyzed sentiment data and viewing history to the server via the network. The input consists of the sentiment analysis results and viewing history data, which the server uses to prepare to match with content metadata recorded in its database.

[0383] Step 3:

[0384] Based on the sentiment data received by the server, a generative AI model is applied to update the viewer's profile. The inputs are sentiment data, viewing history, and existing viewer profiles. Data calculations are performed on this data, and personalized preference data is output. This result enables more accurate content recommendations.

[0385] Step 4:

[0386] The server utilizes a generative model to compare viewing content with viewer profiles in the database. This process involves inputting updated viewer profiles and content metadata. The server calculates content relevance based on the viewer's preferences and emotions, and extracts and lists matching content.

[0387] Step 5:

[0388] The server generates a list of highly relevant content and sends the results to the terminal. The output is a list of recommended content based on the viewer's preferences, which is then passed to the terminal. The terminal receives this list and presents the results to the viewer through an intuitive interface.

[0389] Step 6:

[0390] The user selects the next content they wish to view from the presented content. This generates new data based on the user's selection, which is used to improve their profile for future viewing. This output data is then used in subsequent analysis processes.

[0391] Through these steps, it becomes possible to recommend the most suitable content based on the viewer's emotions and preferences.

[0392] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0393] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0394] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0395] [Third Embodiment]

[0396] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0397] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0398] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0399] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0400] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0401] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0402] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0403] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0404] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0405] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0406] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0407] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0408] This invention is a system that assists users in selecting the most suitable candidate or political party, and its embodiments are described below. This system exchanges information among three parties: a terminal, a server, and a user.

[0409] First, the device presents the user with a questionnaire. The questionnaire includes questions about political values, policies of interest, and social issues that the user considers important. By answering this questionnaire, the user's values ​​information is generated. This values ​​information is sent from the device to a server and becomes the basic data for analysis.

[0410] The server collects information from its accumulated database, including each candidate's and party's pledges, past achievements, and social media ratings. This data is managed to keep it constantly up-to-date. The server then uses a generative model to analyze the candidate information and extract keywords related to each candidate's characteristics and policies.

[0411] The server's next step is to compare the user's values ​​information with the candidate's data. A matching algorithm is used to calculate the degree of agreement between the two. This calculation is weighted particularly towards policy areas that the user prioritizes, resulting in a more accurate match.

[0412] Finally, the terminal displays the matching score results sent from the server to the user. For example, a user who focuses on environmental issues might be presented with candidates who actively propose environmental policies with a high matching score. The displayed information includes the candidate's name, matching score, and reasons for recommendation, which the user can use to consider who to vote for.

[0413] This system allows users to efficiently acquire information and select candidates and political parties that best align with their values, thereby promoting rational voting behavior.

[0414] The following describes the processing flow.

[0415] Step 1:

[0416] The device presents the user with a questionnaire. The questionnaire includes questions about the user's political values ​​and policy interests. By answering this questionnaire, the user's own value system is formed.

[0417] Step 2:

[0418] The device sends the user's response data to the server. The server stores the received data in preparation for analysis.

[0419] Step 3:

[0420] The server collects candidate information from a database. This information includes candidates' pledges, past achievements, and social media ratings. The server retrieves the latest data and keeps it constantly updated.

[0421] Step 4:

[0422] The server uses a generative model to analyze candidate information. This analysis extracts the characteristics and policy keywords of each candidate.

[0423] Step 5:

[0424] The server compares the user's values ​​information with candidate information. The server uses a matching algorithm to calculate the degree of match between the user and each candidate. In this process, the user's areas of focus are given particular weight.

[0425] Step 6:

[0426] The server sends the calculation results to the terminal. These results include the name of the candidate who best matches the user, the degree of match, and the reason for the recommendation.

[0427] Step 7:

[0428] The device displays the results it received to the user. The user then considers which candidate to vote for based on the information presented.

[0429] (Example 1)

[0430] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0431] Traditional election support systems have faced challenges in providing users with sufficient information to select candidates and political parties that best align with their values, making rational voting decisions difficult. Furthermore, collecting fair and reliable data from the vast amount of information available online and conducting analyses tailored to users' interests and values ​​is not easy.

[0432] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0433] In this invention, the server includes means for acquiring user value information through an information input device, means for acquiring and analyzing pledges and past achievements from candidate information sources, and means for comparing the user's value information with candidate information and calculating the degree of agreement. This makes it possible for users to easily obtain information on candidates and political parties that match their own values, thereby supporting rational voting behavior.

[0434] An "information input device" is a device that collects information about users' values ​​and transmits it to a server as structured data.

[0435] "User value information" refers to data that indicates the political values ​​and interests of users, and is collected through survey responses.

[0436] "Sources of candidate information" refer to databases and other information sources that hold information related to candidates, such as their pledges, past achievements, and evaluations.

[0437] A "campaign promise" is information that outlines the policy commitments and goals that a candidate presents during their election campaign.

[0438] "Past achievements" refers to information that shows the results and accomplishments a candidate has achieved through their political activities in the past.

[0439] A "generative model" is an artificial intelligence model used for data analysis, specifically for extracting keywords related to candidate characteristics and policies.

[0440] "Score of agreement" is an indicator that shows the compatibility between the user's value information and the candidate's information, and is calculated using an appropriate matching algorithm.

[0441] The system in this invention consists of a combination of an information input device, a server, and a user terminal. The information input device presents a questionnaire to the user and collects value information. The user answers the questionnaire, and that value information is transmitted from the information input device to the server.

[0442] The server is a high-performance computer with the ability to access a stored database. This database contains important information such as candidates' pledges and past achievements. The server retrieves the necessary information from this database and analyzes the data using a generative AI model. The generative AI model is used to extract candidate characteristics and relevant policy keywords.

[0443] The server then compares the user's values ​​information with the analyzed candidate information. A matching algorithm is applied, weighting key areas based on the user's interests and calculating the degree of match. Based on this degree of match, the server sends candidate information with a high degree of match to the user's terminal.

[0444] The user terminal displays the matching score results received from the server on the screen. By referring to the presented information, the user can obtain the information needed to select the candidate or political party that best matches their values.

[0445] Specific example

[0446] For example, if a user inputs value information such as "I am interested in renewable energy" into an information input device, the server will gather information on candidates with policies related to renewable energy from its database and analyze it with a generative AI model to generate a list of suitable candidates. The user can then use this list to make a rational decision about who to vote for.

[0447] Example of a prompt

[0448] "Who is the candidate whose values ​​best align with mine? I place great importance on environmental issues and renewable energy."

[0449] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0450] Step 1:

[0451] The device presents the user with a survey. The input includes the survey questions. The user answers these questions and generates their own values ​​information. Specifically, the user selects options for each question and enters comments as needed. As a result, the user's values ​​information is output on the device as structured data.

[0452] Step 2:

[0453] The terminal sends value information it generates to the server. The input includes value information generated by the user. The terminal performs secure communication and transmits the value information to the server. The output is the value information data received by the server.

[0454] Step 3:

[0455] The server calls the database to collect candidate information. Input includes candidate pledges, past performance, and relevant evaluation information retrieved from the database. The server automatically accesses the database and collects this data. The output is a dataset of candidate information stored within the server.

[0456] Step 4:

[0457] The server uses a generative AI model to analyze candidate information. The input includes a dataset of collected candidate information. The server applies the generative AI model to extract policy keywords and candidate characteristics. The output is the analyzed dataset.

[0458] Step 5:

[0459] The server compares the analyzed data with the user's values ​​information. The input includes the user's values ​​information and the analyzed candidate data. The server uses a matching algorithm to compare the data and calculate the degree of agreement. The output includes a numerical score of agreement and related information.

[0460] Step 6:

[0461] The server sends the match score results to the terminal. The input includes the calculated match score and associated candidate information. The server then sends these results back to the terminal. The output is a dataset for display on the user terminal.

[0462] Step 7:

[0463] The terminal displays the matching score results to the user. The input includes a dataset of matching scores and candidate information received from the server. The terminal visualizes this on the screen and displays it for the user to see. The output includes specific candidate information and their matching scores presented to the user.

[0464] (Application Example 1)

[0465] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0466] In current voting practices, it is difficult for voters to find candidates or political parties that align with their values ​​and interests, and the means to support those candidates are limited. This hinders rational voting and reduces the willingness to participate in political activities. In this situation, there is a need for a system that efficiently and accurately supports candidate selection and further promotes support for those candidates.

[0467] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0468] In this invention, the server includes means for acquiring user value information through questionnaires, means for acquiring and analyzing candidate information data, means for comparing the user's value information with the candidate information to calculate the degree of agreement, and means for the user to make electronic donations based on the presented candidate information. This makes it possible for users to not only choose the candidate or political party that best matches their values, but also to easily support that candidate, thereby promoting rational voting behavior.

[0469] A "survey" is a question-based method used to understand users' political values, interests, and the social issues they are concerned with.

[0470] "Values ​​information" refers to data that indicates users' political and social values, obtained through surveys.

[0471] "Candidate information" refers to information obtained from a database that includes the pledges, past achievements, and evaluations of political candidates and political parties.

[0472] "Analysis" is the process of thoroughly investigating candidate information and extracting keywords related to their characteristics and policies.

[0473] "Score of agreement" is an evaluation metric that compares user value information with candidate information to show how well the two match.

[0474] "Presentation" refers to the act of visually displaying candidate information to the user based on a calculated degree of similarity.

[0475] "Electronic donation" is a method of providing financial support online based on candidate information presented to the user.

[0476] The system for implementing this invention begins with the user answering a questionnaire via a terminal. The questionnaire includes questions designed to understand the user's political values ​​and social issues of interest. Once the user answers the questionnaire, the results are transmitted from the terminal to the server as value information.

[0477] Based on the received values ​​information, the server refers to a database of candidate information and collects each candidate's pledges, past achievements, and evaluations. This candidate information is analyzed using a generative AI model to extract keywords related to the candidates' characteristics and policies.

[0478] The server then compares the user's values ​​information with candidate information using a matching degree calculation algorithm. It assigns weights to policy areas that the user considers particularly important, and precisely calculates the degree of matching. Candidate information is then displayed on the terminal in order of highest matching degree.

[0479] Users can make electronic donations through their devices based on the highly matched candidates presented. Donations are processed through an electronic payment system, offering a variety of payment options.

[0480] For example, if a user indicates a particular interest in "environmental issues," the survey will include a prompt such as, "How interested are you in environmental policy?" After the user responds, the server will present candidates with a high degree of matching who have policies specifically focused on environmental issues. Smartphones and smart glasses are used throughout this entire process to enhance user convenience.

[0481] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0482] Step 1:

[0483] The user answers a survey via their device. The survey includes questions about political values ​​and social issues, generating the user's values ​​information. The input for this step is the user's answers, and the output is sent to the server as values ​​information.

[0484] Step 2:

[0485] The server collects candidate information from the database based on the received values ​​information. Candidate information includes pledges, past achievements, and evaluations. In this step, values ​​information is provided as input, and candidate information for analysis is output.

[0486] Step 3:

[0487] The server analyzes candidate information using a generation AI model. Here, keywords related to candidate characteristics and policies are extracted. The input in this step is candidate information, and the output is the policy keywords resulting from the analysis.

[0488] Step 4:

[0489] The server compares the user's values ​​information with the analysis results of the generated AI model and calculates the degree of agreement. In this process, specific policy areas are weighted. The input is the values ​​information and analysis results, and the output is the degree of agreement.

[0490] Step 5:

[0491] The server sends candidate information to the terminal in order of matching degree and presents it to the user. The input for this step is the matching degree, and the output is the presented candidate information.

[0492] Step 6:

[0493] Users make electronic donations via their terminal based on the presented candidate information. The input is candidate selection based on the degree of match, and the output is the completion of the donation through the electronic payment system.

[0494] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0495] This invention is a system that assists users in selecting the most suitable candidates and political parties, and is particularly characterized by its ability to recognize the user's emotions and utilize that data to provide even more accurate and personalized information. This system processes information among three parties: the terminal, the server, and the user.

[0496] First, the device displays a questionnaire to the user. The user then answers the presented questionnaire. At this time, the device has an emotion engine built in, which can analyze the user's emotions in real time. The results of this emotion analysis are added to the user's value information, improving the accuracy of the data.

[0497] The survey responses and sentiment analysis results are sent from the terminal to the server. The server receives this data and accesses a database to collect information such as the candidate's pledges, past achievements, and social media ratings. This data is frequently updated to ensure it remains up-to-date.

[0498] The server uses a generative model to analyze candidate information and extracts candidate characteristics and policy keywords based on the analysis results. It then matches the candidate information with a user profile that takes into account the user's values ​​and sentiment analysis results. This allows the server to calculate the degree of match between the user and each candidate. In calculating the degree of match, the sentiment expressed by the user in specific policy areas is also weighted.

[0499] The calculated match score is sent from the server to the terminal and presented to the user. The presentation includes the name of the candidate or party, the match score, and the reason for the recommendation, allowing the user to consider the options.

[0500] For example, if a user shows strong interest in a particular policy, and the emotion engine recognizes the user's emotions as positive at the time of their response, then candidates who focus on that policy will be suggested to the user with a high degree of agreement. This system allows users to conduct election campaigns based on their own values ​​and emotions, leading to a deeper understanding of the issues.

[0501] The following describes the processing flow.

[0502] Step 1:

[0503] The device displays a survey to the user. The survey consists of questions about political values ​​and policy interests, and the user answers these questions.

[0504] Step 2:

[0505] The emotion engine built into the device analyzes the user's emotions in real time while they are answering the survey. The emotion engine determines the emotional category, such as positive, negative, or neutral, by analyzing the user's voice tone, facial expressions, response speed, and other factors.

[0506] Step 3:

[0507] After a user completes a survey, their device sends the response data and analyzed sentiment data to a server. This data is then organized as information about the user's values.

[0508] Step 4:

[0509] The server accesses the database here to collect information such as candidates' pledges, past achievements, and social media ratings. The database is regularly updated to maintain the most up-to-date information.

[0510] Step 5:

[0511] The server uses a generative model to analyze the collected candidate information. This analysis extracts and lists the candidate's policy keywords and characteristics.

[0512] Step 6:

[0513] The server matches the user's values ​​information (including emotional data) with candidate information. The server uses a matching algorithm to calculate the degree of agreement between the user and each candidate. In this calculation, particular weight is given to policy areas in which the user has a strong emotional response.

[0514] Step 7:

[0515] The calculated match score is sent from the server to the terminal. The result includes each candidate's name, match score, and reason for recommendation.

[0516] Step 8:

[0517] The device displays the matching score results to the user. Based on the information presented, the user can consider which candidate they are more interested in. Personalized candidate suggestions are possible because the matching score takes into account the user's sentiment data.

[0518] (Example 2)

[0519] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0520] In elections and political choices, there is a challenge in accurately and effectively reflecting the emotions and values ​​of users. Traditional methods do not adequately consider users' emotions when providing information, resulting in a situation where it is difficult for users to choose the most suitable candidates or policies.

[0521] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0522] In this invention, the server includes means for analyzing the user's emotions and integrating the results with the user's values ​​information, means for obtaining and analyzing pledges and achievements from a data storage of candidate information, and means for analyzing candidate information using a generative model. This makes it possible to present personalized candidate information that reflects the user's emotions and values.

[0523] A "survey" is a series of questions presented to users to confirm their values ​​and opinions.

[0524] A "device" is a component of a machine or system designed to perform a specific function.

[0525] "Emotional analysis" is a technology that determines a user's psychological state based on their facial expressions, tone of voice, and other factors.

[0526] "Values ​​information" refers to data about users' beliefs and what they consider important.

[0527] "Candidate information" refers to various data about candidates who are the subject of elections or political choices.

[0528] A "generative model" is an algorithm used to make predictions and analyses for specific purposes or problems based on large amounts of data.

[0529] "Score of agreement" is a numerical value or indicator that shows the degree of compatibility between the user's value information and the analyzed candidate information.

[0530] This system is designed to help users select the most suitable candidates and political parties. In particular, it aims to provide more accurate information by analyzing users' emotions in real time and integrating that data with value-based information.

[0531] First, the device displays a survey to the user and accepts their responses. The survey includes questions such as which policies the user is interested in. At this time, the device is equipped with an emotion analysis engine that analyzes the user's facial expressions and tone of voice through the camera and microphone. The results of the emotion analysis are directly integrated into the user's values ​​information.

[0532] Next, the device sends the survey results and sentiment analysis data to the server. The server receives this data and collects candidate information (such as pledges, achievements, and social media ratings) stored in its database. This candidate information is frequently updated to ensure it is always up-to-date.

[0533] The server analyzes candidate information using a generative AI model, extracting its characteristics and policy keywords. The data obtained from this analysis is processed by the generative AI model, and the degree of match with the optimal candidate is calculated. The user's sentiment towards a specific policy area is also reflected as a weight in this match calculation.

[0534] For example, if a user expresses interest in environmental policy and the sentiment analysis engine detects positive emotions during their survey response, the system will recommend candidates who focus on environmental policy with a high degree of agreement. In this way, users can make more appropriate choices based on their own values ​​and emotions.

[0535] An example of a prompt might be, "Please explain how the emotional data analyzed in real time by a device equipped with an emotion engine influences user choices." This prompt provides detailed information about the system's operation and its intended purpose.

[0536] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0537] Step 1:

[0538] The device displays a survey to the user. The survey input consists of question information, which are comprehensive questions. The user answers based on these questions. The device uses its built-in camera and microphone to analyze the user's emotions in real time from their facial expressions and voice. This analysis generates emotion data, such as positive or negative, which is output along with the user's answers.

[0539] Step 2:

[0540] The terminal transmits the analyzed sentiment data and user survey response data to the server via communication means such as the internet. The server receives this input data and stores it in data storage. At this stage, the data format is also converted and shaped to a format suitable for analysis.

[0541] Step 3:

[0542] The server accesses data storage and collects data from candidate information, including pledges, past performance, and social media ratings. The collected data becomes input for analysis using a generative AI model. The server runs the generative AI model and extracts candidate characteristics and policy keywords. This result is output as analysis data.

[0543] Step 4:

[0544] The server compares user profiles, including sentiment data and survey response data, with analyzed candidate data to calculate the degree of match. Here, the user's sentiment towards a particular policy is considered as a weight for the degree of match. A set of match scores is output as a result of this calculation.

[0545] Step 5:

[0546] The server prepares candidate information to recommend to the user based on the match score. This information includes the candidate's name, match score, and reason for recommendation. The recommendation information is prioritized to reflect its importance to the user.

[0547] Step 6:

[0548] The server sends the prepared recommendation information to the terminal. The terminal receives this data and presents it visually to the user. The user can review the candidate information through lists and charts on the screen and make the best selection.

[0549] (Application Example 2)

[0550] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0551] It is difficult for viewers to efficiently select videos that match their interests and emotions from a vast amount of content. In particular, the lack of personalized suggestions based on emotions is a challenge in increasing viewer satisfaction.

[0552] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0553] In this invention, the server includes means for acquiring user preference information at the time of viewing, means for acquiring and analyzing relevant information from a data bank of viewing content, and means for comparing the user preference information with content information to calculate the relationship. This makes it possible to suggest personalized content that matches the viewer's emotions and preferences.

[0554] "User preference information" refers to information about the personal preferences and interests that viewers express in relation to the content they watch.

[0555] "Means of acquisition during viewing" refers to technologies for capturing and analyzing viewers' behavior and viewing records in real time as they play video content.

[0556] A "data bank of viewing content" is a collection of data containing a wide variety of videos and related information, which can be accessed according to the viewer's needs.

[0557] "Means for acquiring and analyzing relevant information" refers to methods for collecting information such as metadata and user reviews related to the content being viewed, and for analyzing patterns and trends based on that information.

[0558] A "means for calculating relevance" is an algorithm that compares a user's preference information with the characteristics of the content they watch and quantifies the degree of agreement.

[0559] "Personalized content suggestions" refers to selecting and presenting content that is best suited to each individual viewer based on an analysis of their past viewing history and emotions.

[0560] To realize this invention, a system is used that acquires and processes viewer preference information in real time when viewers watch video content. The system consists of a terminal such as a smartphone or tablet and a server that performs data analysis.

[0561] While the viewer is playing content, the device uses sensors such as cameras and microphones to collect the viewer's facial expressions and voice, and performs emotion analysis. This analysis uses emotion AI software such as "Affectiva." The preference information obtained as a result of the analysis is securely transmitted to and stored on a server using cloud technology such as "Firebase."

[0562] The server uses a generative AI model to analyze the received preference information by comparing it with the characteristic information of the content being viewed in the database. This calculates the relevance of personalized content based on the viewer's emotions and past viewing history, and extracts the most suitable video content. The information thus calculated is sent back to the device and presented to the viewer as a recommendation.

[0563] For example, if a viewer is watching an emotionally moving film and shedding tears, this emotion is analyzed and recognized in real time. Based on this, other emotionally moving films are recommended from the server to the user's device. This makes it possible to effectively suggest content that matches the viewer's preferences and mood.

[0564] An example of a prompt is, "How can we suggest emotional content based on the emotions a user expresses during an emotional or romantic scene?" By inputting this prompt into a generative AI model, appropriate content recommendations tailored to the viewer's emotions can be achieved.

[0565] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0566] Step 1:

[0567] The device detects when the viewer starts playing content and activates its sensors. The device uses its camera and microphone to collect the viewer's facial expressions and voice in real time and analyzes their emotions. This analysis generates data that indicates the viewer's current emotional state.

[0568] Step 2:

[0569] The device transmits the analyzed sentiment data and viewing history to the server via the network. The input consists of the sentiment analysis results and viewing history data, which the server uses to prepare to match with content metadata recorded in its database.

[0570] Step 3:

[0571] Based on the sentiment data received by the server, a generative AI model is applied to update the viewer's profile. The inputs are sentiment data, viewing history, and existing viewer profiles. Data calculations are performed on this data, and personalized preference data is output. This result enables more accurate content recommendations.

[0572] Step 4:

[0573] The server utilizes a generative model to compare viewing content with viewer profiles in the database. This process involves inputting updated viewer profiles and content metadata. The server calculates content relevance based on the viewer's preferences and emotions, and extracts and lists matching content.

[0574] Step 5:

[0575] The server generates a list of highly relevant content and sends the results to the terminal. The output is a list of recommended content based on the viewer's preferences, which is then passed to the terminal. The terminal receives this list and presents the results to the viewer through an intuitive interface.

[0576] Step 6:

[0577] The user selects the next content they wish to view from the presented content. This generates new data based on the user's selection, which is used to improve their profile for future viewing. This output data is then used in subsequent analysis processes.

[0578] Through these steps, it becomes possible to recommend the most suitable content based on the viewer's emotions and preferences.

[0579] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0580] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0581] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0582] [Fourth Embodiment]

[0583] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0584] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0585] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0586] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0587] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0588] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0589] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0590] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0591] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0592] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0593] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0594] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0595] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0596] This invention is a system that assists users in selecting the most suitable candidate or political party, and its embodiments are described below. This system exchanges information among three parties: a terminal, a server, and a user.

[0597] First, the device presents the user with a questionnaire. The questionnaire includes questions about political values, policies of interest, and social issues that the user considers important. By answering this questionnaire, the user's values ​​information is generated. This values ​​information is sent from the device to a server and becomes the basic data for analysis.

[0598] The server collects information from its accumulated database, including each candidate's and party's pledges, past achievements, and social media ratings. This data is managed to keep it constantly up-to-date. The server then uses a generative model to analyze the candidate information and extract keywords related to each candidate's characteristics and policies.

[0599] The server's next step is to compare the user's values ​​information with the candidate's data. A matching algorithm is used to calculate the degree of agreement between the two. This calculation is weighted particularly towards policy areas that the user prioritizes, resulting in a more accurate match.

[0600] Finally, the terminal displays the matching score results sent from the server to the user. For example, a user who focuses on environmental issues might be presented with candidates who actively propose environmental policies with a high matching score. The displayed information includes the candidate's name, matching score, and reasons for recommendation, which the user can use to consider who to vote for.

[0601] This system allows users to efficiently acquire information and select candidates and political parties that best align with their values, thereby promoting rational voting behavior.

[0602] The following describes the processing flow.

[0603] Step 1:

[0604] The device presents the user with a questionnaire. The questionnaire includes questions about the user's political values ​​and policy interests. By answering this questionnaire, the user's own value system is formed.

[0605] Step 2:

[0606] The device sends the user's response data to the server. The server stores the received data in preparation for analysis.

[0607] Step 3:

[0608] The server collects candidate information from a database. This information includes candidates' pledges, past achievements, and social media ratings. The server retrieves the latest data and keeps it constantly updated.

[0609] Step 4:

[0610] The server uses a generative model to analyze candidate information. This analysis extracts the characteristics and policy keywords of each candidate.

[0611] Step 5:

[0612] The server compares the user's values ​​information with candidate information. The server uses a matching algorithm to calculate the degree of match between the user and each candidate. In this process, the user's areas of focus are given particular weight.

[0613] Step 6:

[0614] The server sends the calculation results to the terminal. These results include the name of the candidate who best matches the user, the degree of match, and the reason for the recommendation.

[0615] Step 7:

[0616] The device displays the results it received to the user. The user then considers which candidate to vote for based on the information presented.

[0617] (Example 1)

[0618] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0619] Traditional election support systems have faced challenges in providing users with sufficient information to select candidates and political parties that best align with their values, making rational voting decisions difficult. Furthermore, collecting fair and reliable data from the vast amount of information available online and conducting analyses tailored to users' interests and values ​​is not easy.

[0620] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0621] In this invention, the server includes means for acquiring user value information through an information input device, means for acquiring and analyzing pledges and past achievements from candidate information sources, and means for comparing the user's value information with candidate information and calculating the degree of agreement. This makes it possible for users to easily obtain information on candidates and political parties that match their own values, thereby supporting rational voting behavior.

[0622] An "information input device" is a device that collects information about users' values ​​and transmits it to a server as structured data.

[0623] "User value information" refers to data that indicates the political values ​​and interests of users, and is collected through survey responses.

[0624] "Sources of candidate information" refer to databases and other information sources that hold information related to candidates, such as their pledges, past achievements, and evaluations.

[0625] A "campaign promise" is information that outlines the policy commitments and goals that a candidate presents during their election campaign.

[0626] "Past achievements" refers to information that shows the results and accomplishments a candidate has achieved through their political activities in the past.

[0627] A "generative model" is an artificial intelligence model used for data analysis, specifically for extracting keywords related to candidate characteristics and policies.

[0628] "Score of agreement" is an indicator that shows the compatibility between the user's value information and the candidate's information, and is calculated using an appropriate matching algorithm.

[0629] The system in this invention consists of a combination of an information input device, a server, and a user terminal. The information input device presents a questionnaire to the user and collects value information. The user answers the questionnaire, and that value information is transmitted from the information input device to the server.

[0630] The server is a high-performance computer with the ability to access a stored database. This database contains important information such as candidates' pledges and past achievements. The server retrieves the necessary information from this database and analyzes the data using a generative AI model. The generative AI model is used to extract candidate characteristics and relevant policy keywords.

[0631] The server then compares the user's values ​​information with the analyzed candidate information. A matching algorithm is applied, weighting key areas based on the user's interests and calculating the degree of match. Based on this degree of match, the server sends candidate information with a high degree of match to the user's terminal.

[0632] The user terminal displays the matching score results received from the server on the screen. By referring to the presented information, the user can obtain the information needed to select the candidate or political party that best matches their values.

[0633] Specific example

[0634] For example, if a user inputs value information such as "I am interested in renewable energy" into an information input device, the server will gather information on candidates with policies related to renewable energy from its database and analyze it with a generative AI model to generate a list of suitable candidates. The user can then use this list to make a rational decision about who to vote for.

[0635] Example of a prompt

[0636] "Who is the candidate whose values ​​best align with mine? I place great importance on environmental issues and renewable energy."

[0637] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0638] Step 1:

[0639] The device presents the user with a survey. The input includes the survey questions. The user answers these questions and generates their own values ​​information. Specifically, the user selects options for each question and enters comments as needed. As a result, the user's values ​​information is output on the device as structured data.

[0640] Step 2:

[0641] The terminal sends value information it generates to the server. The input includes value information generated by the user. The terminal performs secure communication and transmits the value information to the server. The output is the value information data received by the server.

[0642] Step 3:

[0643] The server calls the database to collect candidate information. Input includes candidate pledges, past performance, and relevant evaluation information retrieved from the database. The server automatically accesses the database and collects this data. The output is a dataset of candidate information stored within the server.

[0644] Step 4:

[0645] The server uses a generative AI model to analyze candidate information. The input includes a dataset of collected candidate information. The server applies the generative AI model to extract policy keywords and candidate characteristics. The output is the analyzed dataset.

[0646] Step 5:

[0647] The server compares the analyzed data with the user's values ​​information. The input includes the user's values ​​information and the analyzed candidate data. The server uses a matching algorithm to compare the data and calculate the degree of agreement. The output includes a numerical score of agreement and related information.

[0648] Step 6:

[0649] The server sends the match score results to the terminal. The input includes the calculated match score and associated candidate information. The server then sends these results back to the terminal. The output is a dataset for display on the user terminal.

[0650] Step 7:

[0651] The terminal displays the matching score results to the user. The input includes a dataset of matching scores and candidate information received from the server. The terminal visualizes this on the screen and displays it for the user to see. The output includes specific candidate information and their matching scores presented to the user.

[0652] (Application Example 1)

[0653] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0654] In current voting practices, it is difficult for voters to find candidates or political parties that align with their values ​​and interests, and the means to support those candidates are limited. This hinders rational voting and reduces the willingness to participate in political activities. In this situation, there is a need for a system that efficiently and accurately supports candidate selection and further promotes support for those candidates.

[0655] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0656] In this invention, the server includes means for acquiring user value information through questionnaires, means for acquiring and analyzing candidate information data, means for comparing the user's value information with the candidate information to calculate the degree of agreement, and means for the user to make electronic donations based on the presented candidate information. This makes it possible for users to not only choose the candidate or political party that best matches their values, but also to easily support that candidate, thereby promoting rational voting behavior.

[0657] A "survey" is a question-based method used to understand users' political values, interests, and the social issues they are concerned with.

[0658] "Values ​​information" refers to data that indicates users' political and social values, obtained through surveys.

[0659] "Candidate information" refers to information obtained from a database that includes the pledges, past achievements, and evaluations of political candidates and political parties.

[0660] "Analysis" is the process of thoroughly investigating candidate information and extracting keywords related to their characteristics and policies.

[0661] "Score of agreement" is an evaluation metric that compares user value information with candidate information to show how well the two match.

[0662] "Presentation" refers to the act of visually displaying candidate information to the user based on a calculated degree of similarity.

[0663] "Electronic donation" is a method of providing financial support online based on candidate information presented to the user.

[0664] The system for implementing this invention begins with the user answering a questionnaire via a terminal. The questionnaire includes questions designed to understand the user's political values ​​and social issues of interest. Once the user answers the questionnaire, the results are transmitted from the terminal to the server as value information.

[0665] Based on the received values ​​information, the server refers to a database of candidate information and collects each candidate's pledges, past achievements, and evaluations. This candidate information is analyzed using a generative AI model to extract keywords related to the candidates' characteristics and policies.

[0666] The server then compares the user's values ​​information with candidate information using a matching degree calculation algorithm. It assigns weights to policy areas that the user considers particularly important, and precisely calculates the degree of matching. Candidate information is then displayed on the terminal in order of highest matching degree.

[0667] Users can make electronic donations through their devices based on the highly matched candidates presented. Donations are processed through an electronic payment system, offering a variety of payment options.

[0668] For example, if a user indicates a particular interest in "environmental issues," the survey will include a prompt such as, "How interested are you in environmental policy?" After the user responds, the server will present candidates with a high degree of matching who have policies specifically focused on environmental issues. Smartphones and smart glasses are used throughout this entire process to enhance user convenience.

[0669] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0670] Step 1:

[0671] The user answers a survey via their device. The survey includes questions about political values ​​and social issues, generating the user's values ​​information. The input for this step is the user's answers, and the output is sent to the server as values ​​information.

[0672] Step 2:

[0673] The server collects candidate information from the database based on the received values ​​information. Candidate information includes pledges, past achievements, and evaluations. In this step, values ​​information is provided as input, and candidate information for analysis is output.

[0674] Step 3:

[0675] The server analyzes candidate information using a generation AI model. Here, keywords related to candidate characteristics and policies are extracted. The input in this step is candidate information, and the output is the policy keywords resulting from the analysis.

[0676] Step 4:

[0677] The server compares the user's values ​​information with the analysis results of the generated AI model and calculates the degree of agreement. In this process, specific policy areas are weighted. The input is the values ​​information and analysis results, and the output is the degree of agreement.

[0678] Step 5:

[0679] The server sends candidate information to the terminal in order of matching degree and presents it to the user. The input for this step is the matching degree, and the output is the presented candidate information.

[0680] Step 6:

[0681] Users make electronic donations via their terminal based on the presented candidate information. The input is candidate selection based on the degree of match, and the output is the completion of the donation through the electronic payment system.

[0682] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0683] This invention is a system that assists users in selecting the most suitable candidates and political parties, and is particularly characterized by its ability to recognize the user's emotions and utilize that data to provide even more accurate and personalized information. This system processes information among three parties: the terminal, the server, and the user.

[0684] First, the device displays a questionnaire to the user. The user then answers the presented questionnaire. At this time, the device has an emotion engine built in, which can analyze the user's emotions in real time. The results of this emotion analysis are added to the user's value information, improving the accuracy of the data.

[0685] The survey responses and sentiment analysis results are sent from the terminal to the server. The server receives this data and accesses a database to collect information such as the candidate's pledges, past achievements, and social media ratings. This data is frequently updated to ensure it remains up-to-date.

[0686] The server uses a generative model to analyze candidate information and extracts candidate characteristics and policy keywords based on the analysis results. It then matches the candidate information with a user profile that takes into account the user's values ​​and sentiment analysis results. This allows the server to calculate the degree of match between the user and each candidate. In calculating the degree of match, the sentiment expressed by the user in specific policy areas is also weighted.

[0687] The calculated match score is sent from the server to the terminal and presented to the user. The presentation includes the name of the candidate or party, the match score, and the reason for the recommendation, allowing the user to consider the options.

[0688] For example, if a user shows strong interest in a particular policy, and the emotion engine recognizes the user's emotions as positive at the time of their response, then candidates who focus on that policy will be suggested to the user with a high degree of agreement. This system allows users to conduct election campaigns based on their own values ​​and emotions, leading to a deeper understanding of the issues.

[0689] The following describes the processing flow.

[0690] Step 1:

[0691] The device displays a survey to the user. The survey consists of questions about political values ​​and policy interests, and the user answers these questions.

[0692] Step 2:

[0693] The emotion engine built into the device analyzes the user's emotions in real time while they are answering the survey. The emotion engine determines the emotional category, such as positive, negative, or neutral, by analyzing the user's voice tone, facial expressions, response speed, and other factors.

[0694] Step 3:

[0695] After a user completes a survey, their device sends the response data and analyzed sentiment data to a server. This data is then organized as information about the user's values.

[0696] Step 4:

[0697] The server accesses the database here to collect information such as candidates' pledges, past achievements, and social media ratings. The database is regularly updated to maintain the most up-to-date information.

[0698] Step 5:

[0699] The server uses a generative model to analyze the collected candidate information. This analysis extracts and lists the candidate's policy keywords and characteristics.

[0700] Step 6:

[0701] The server matches the user's values ​​information (including emotional data) with candidate information. The server uses a matching algorithm to calculate the degree of agreement between the user and each candidate. In this calculation, particular weight is given to policy areas in which the user has a strong emotional response.

[0702] Step 7:

[0703] The calculated match score is sent from the server to the terminal. The result includes each candidate's name, match score, and reason for recommendation.

[0704] Step 8:

[0705] The device displays the matching score results to the user. Based on the information presented, the user can consider which candidate they are more interested in. Personalized candidate suggestions are possible because the matching score takes into account the user's sentiment data.

[0706] (Example 2)

[0707] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0708] In elections and political choices, there is a challenge in accurately and effectively reflecting the emotions and values ​​of users. Traditional methods do not adequately consider users' emotions when providing information, resulting in a situation where it is difficult for users to choose the most suitable candidates or policies.

[0709] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0710] In this invention, the server includes means for analyzing the user's emotions and integrating the results with the user's values ​​information, means for obtaining and analyzing pledges and achievements from a data storage of candidate information, and means for analyzing candidate information using a generative model. This makes it possible to present personalized candidate information that reflects the user's emotions and values.

[0711] A "survey" is a series of questions presented to users to confirm their values ​​and opinions.

[0712] A "device" is a component of a machine or system designed to perform a specific function.

[0713] "Emotional analysis" is a technology that determines a user's psychological state based on their facial expressions, tone of voice, and other factors.

[0714] "Values ​​information" refers to data about users' beliefs and what they consider important.

[0715] "Candidate information" refers to various data about candidates who are the subject of elections or political choices.

[0716] A "generative model" is an algorithm used to make predictions and analyses for specific purposes or problems based on large amounts of data.

[0717] "Score of agreement" is a numerical value or indicator that shows the degree of compatibility between the user's value information and the analyzed candidate information.

[0718] This system is designed to help users select the most suitable candidates and political parties. In particular, it aims to provide more accurate information by analyzing users' emotions in real time and integrating that data with value-based information.

[0719] First, the device displays a survey to the user and accepts their responses. The survey includes questions such as which policies the user is interested in. At this time, the device is equipped with an emotion analysis engine that analyzes the user's facial expressions and tone of voice through the camera and microphone. The results of the emotion analysis are directly integrated into the user's values ​​information.

[0720] Next, the device sends the survey results and sentiment analysis data to the server. The server receives this data and collects candidate information (such as pledges, achievements, and social media ratings) stored in its database. This candidate information is frequently updated to ensure it is always up-to-date.

[0721] The server analyzes candidate information using a generative AI model, extracting its characteristics and policy keywords. The data obtained from this analysis is processed by the generative AI model, and the degree of match with the optimal candidate is calculated. The user's sentiment towards a specific policy area is also reflected as a weight in this match calculation.

[0722] For example, if a user expresses interest in environmental policy and the sentiment analysis engine detects positive emotions during their survey response, the system will recommend candidates who focus on environmental policy with a high degree of agreement. In this way, users can make more appropriate choices based on their own values ​​and emotions.

[0723] An example of a prompt might be, "Please explain how the emotional data analyzed in real time by a device equipped with an emotion engine influences user choices." This prompt provides detailed information about the system's operation and its intended purpose.

[0724] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0725] Step 1:

[0726] The device displays a survey to the user. The survey input consists of question information, which are comprehensive questions. The user answers based on these questions. The device uses its built-in camera and microphone to analyze the user's emotions in real time from their facial expressions and voice. This analysis generates emotion data, such as positive or negative, which is output along with the user's answers.

[0727] Step 2:

[0728] The terminal transmits the analyzed sentiment data and user survey response data to the server via communication means such as the internet. The server receives this input data and stores it in data storage. At this stage, the data format is also converted and shaped to a format suitable for analysis.

[0729] Step 3:

[0730] The server accesses data storage and collects data from candidate information, including pledges, past performance, and social media ratings. The collected data becomes input for analysis using a generative AI model. The server runs the generative AI model and extracts candidate characteristics and policy keywords. This result is output as analysis data.

[0731] Step 4:

[0732] The server compares user profiles, including sentiment data and survey response data, with analyzed candidate data to calculate the degree of match. Here, the user's sentiment towards a particular policy is considered as a weight for the degree of match. A set of match scores is output as a result of this calculation.

[0733] Step 5:

[0734] The server prepares candidate information to recommend to the user based on the match score. This information includes the candidate's name, match score, and reason for recommendation. The recommendation information is prioritized to reflect its importance to the user.

[0735] Step 6:

[0736] The server sends the prepared recommendation information to the terminal. The terminal receives this data and presents it visually to the user. The user can review the candidate information through lists and charts on the screen and make the best selection.

[0737] (Application Example 2)

[0738] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0739] It is difficult for viewers to efficiently select videos that match their interests and emotions from a vast amount of content. In particular, the lack of personalized suggestions based on emotions is a challenge in increasing viewer satisfaction.

[0740] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0741] In this invention, the server includes means for acquiring user preference information at the time of viewing, means for acquiring and analyzing relevant information from a data bank of viewing content, and means for comparing the user preference information with content information to calculate the relationship. This makes it possible to suggest personalized content that matches the viewer's emotions and preferences.

[0742] "User preference information" refers to information about the personal preferences and interests that viewers express in relation to the content they watch.

[0743] "Means of acquisition during viewing" refers to technologies for capturing and analyzing viewers' behavior and viewing records in real time as they play video content.

[0744] A "data bank of viewing content" is a collection of data containing a wide variety of videos and related information, which can be accessed according to the viewer's needs.

[0745] "Means for acquiring and analyzing relevant information" refers to methods for collecting information such as metadata and user reviews related to the content being viewed, and for analyzing patterns and trends based on that information.

[0746] A "means for calculating relevance" is an algorithm that compares a user's preference information with the characteristics of the content they watch and quantifies the degree of agreement.

[0747] "Personalized content suggestions" refers to selecting and presenting content that is best suited to each individual viewer based on an analysis of their past viewing history and emotions.

[0748] To realize this invention, a system is used that acquires and processes viewer preference information in real time when viewers watch video content. The system consists of a terminal such as a smartphone or tablet and a server that performs data analysis.

[0749] While the viewer is playing content, the device uses sensors such as cameras and microphones to collect the viewer's facial expressions and voice, and performs emotion analysis. This analysis uses emotion AI software such as "Affectiva." The preference information obtained as a result of the analysis is securely transmitted to and stored on a server using cloud technology such as "Firebase."

[0750] The server uses a generative AI model to analyze the received preference information by comparing it with the characteristic information of the content being viewed in the database. This calculates the relevance of personalized content based on the viewer's emotions and past viewing history, and extracts the most suitable video content. The information thus calculated is sent back to the device and presented to the viewer as a recommendation.

[0751] For example, if a viewer is watching an emotionally moving film and shedding tears, this emotion is analyzed and recognized in real time. Based on this, other emotionally moving films are recommended from the server to the user's device. This makes it possible to effectively suggest content that matches the viewer's preferences and mood.

[0752] An example of a prompt is, "How can we suggest emotional content based on the emotions a user expresses during an emotional or romantic scene?" By inputting this prompt into a generative AI model, appropriate content recommendations tailored to the viewer's emotions can be achieved.

[0753] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0754] Step 1:

[0755] The device detects when the viewer starts playing content and activates its sensors. The device uses its camera and microphone to collect the viewer's facial expressions and voice in real time and analyzes their emotions. This analysis generates data that indicates the viewer's current emotional state.

[0756] Step 2:

[0757] The device transmits the analyzed sentiment data and viewing history to the server via the network. The input consists of the sentiment analysis results and viewing history data, which the server uses to prepare to match with content metadata recorded in its database.

[0758] Step 3:

[0759] Based on the sentiment data received by the server, a generative AI model is applied to update the viewer's profile. The inputs are sentiment data, viewing history, and existing viewer profiles. Data calculations are performed on this data, and personalized preference data is output. This result enables more accurate content recommendations.

[0760] Step 4:

[0761] The server utilizes a generative model to compare viewing content with viewer profiles in the database. This process involves inputting updated viewer profiles and content metadata. The server calculates content relevance based on the viewer's preferences and emotions, and extracts and lists matching content.

[0762] Step 5:

[0763] The server generates a list of highly relevant content and sends the results to the terminal. The output is a list of recommended content based on the viewer's preferences, which is then passed to the terminal. The terminal receives this list and presents the results to the viewer through an intuitive interface.

[0764] Step 6:

[0765] The user selects the next content they wish to view from the presented content. This generates new data based on the user's selection, which is used to improve their profile for future viewing. This output data is then used in subsequent analysis processes.

[0766] Through these steps, it becomes possible to recommend the most suitable content based on the viewer's emotions and preferences.

[0767] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0768] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0769] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0770] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0771] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0772] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0773] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0774] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0775] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0776] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0777] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0778] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0779] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0780] 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.

[0781] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0782] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0783] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0784] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0785] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0786] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0787] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0788] The following is further disclosed regarding the embodiments described above.

[0789] (Claim 1)

[0790] A means of obtaining user value information through surveys,

[0791] A method for obtaining and analyzing campaign promises and achievements from a database of candidate information,

[0792] A means of calculating the degree of agreement by comparing user value information with candidate information,

[0793] A means of presenting candidate information to users based on the degree of match,

[0794] A system that includes this.

[0795] (Claim 2)

[0796] The system according to claim 1, which uses a generative model to analyze candidate information.

[0797] (Claim 3)

[0798] The system according to claim 1, which calculates the degree of agreement by weighting the user's interests for specific fields.

[0799] "Example 1"

[0800] (Claim 1)

[0801] A means of acquiring user value information through an information input device,

[0802] A means of obtaining and analyzing campaign promises and past achievements from candidate information sources,

[0803] A method for calculating the degree of agreement by comparing user value information with candidate information,

[0804] A means of presenting candidate information to users based on the degree of match,

[0805] An information processing system that includes this.

[0806] (Claim 2)

[0807] The information processing system according to claim 1, which uses a generative model for analyzing candidate information.

[0808] (Claim 3)

[0809] The information processing system according to claim 1, which calculates the degree of agreement by weighting the user's interests for specific domains.

[0810] "Application Example 1"

[0811] (Claim 1)

[0812] A means of obtaining user value information through surveys,

[0813] A means of acquiring and analyzing candidate information data,

[0814] A means of calculating the degree of agreement by comparing user value information with candidate information,

[0815] A means of presenting candidate information to users based on the degree of match,

[0816] A means for users to make electronic donations based on the candidate information presented,

[0817] A system that includes this.

[0818] (Claim 2)

[0819] The system according to claim 1, which uses a generative model to analyze candidate information.

[0820] (Claim 3)

[0821] The system according to claim 1, which calculates the degree of agreement by weighting the user's interests for specific fields.

[0822] "Example 2 of combining an emotion engine"

[0823] (Claim 1)

[0824] A device that displays a survey to users and accepts their responses,

[0825] A device that analyzes users' emotions and integrates the results into users' value information,

[0826] A device that retrieves and analyzes candidate information data, including pledges and achievements,

[0827] A device that analyzes candidate information using a generative model,

[0828] A device that compares user value information with analyzed candidate information and calculates the degree of agreement,

[0829] A device that presents candidate information to the user based on the degree of similarity,

[0830] A system that includes this.

[0831] (Claim 2)

[0832] The system according to claim 1, which analyzes user sentiment and calculates the degree of agreement by weighting it for specific policy areas.

[0833] (Claim 3)

[0834] The system according to claim 1, comprising a device for transmitting survey response data and sentiment analysis results to a central processing unit using secure communication means.

[0835] "Application example 2 when combining with an emotional engine"

[0836] (Claim 1)

[0837] A means of obtaining user preference information during viewing,

[0838] A means of obtaining and analyzing relevant information from a database of viewing content,

[0839] A method for calculating the correlation between user preference information and content information,

[0840] A means of presenting viewing content information to users based on relevance,

[0841] A system that includes this.

[0842] (Claim 2)

[0843] The system according to claim 1, which uses a generative model to analyze viewing content information.

[0844] (Claim 3)

[0845] The system according to claim 1, which calculates correlation by weighting user emotions against specific fields. [Explanation of Symbols]

[0846] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of obtaining user value information through surveys, A means of acquiring and analyzing candidate information data, A means of calculating the degree of agreement by comparing user value information with candidate information, A means of presenting candidate information to users based on the degree of match, A means for users to make electronic donations based on the candidate information presented, A system that includes this.

2. The system according to claim 1, which uses a generative model to analyze candidate information.

3. The system according to claim 1, which calculates the degree of agreement by weighting the user's interests for specific fields.

Images