System

Abstract

An object of the system according to the embodiment is to enable a voter to easily understand a way of thinking of a candidate by summarizing comments of the candidate and comparing policies.SOLUTION: A system includes a candidate speech summarization part, a policy comparison part, and a question answering part. The candidate statement summarizing section summarizes the statements of the candidates. The policy comparison unit compares the policies of the candidates based on the statements summarized by the candidate statement summarization unit. The question answering unit answers the user's question based on the policies compared by the policy comparison unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology makes it difficult to understand candidates' policies and ideals, which could lead to lower voter turnout.

[0005] The system according to the embodiment aims to enable voters to easily understand the thinking of candidates by summarizing their statements and comparing their policies. [Means for solving the problem]

[0006] The system according to the embodiment includes a candidate statement summarizing unit, a policy comparison unit, and a question and answering unit. The candidate statement summarizing unit summarizes the statements of the candidates. The policy comparison unit compares the policies of each candidate based on the statements summarized by the candidate statement summarizing unit. The question and answering unit answers a user's question based on the policies compared by the policy comparison unit. [Effects of the Invention]

[0007] The system according to the embodiment can summarize the statements of candidates and compare their policies, allowing voters to easily understand the thinking of candidates. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

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

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

[0028] (Example 1) The candidate statement summary and candidate comparison tool according to an embodiment of the present invention is a system that summarizes candidate statements, compares policies, and answers user questions, thereby providing an environment in which voters can make decisions based on objective and accurate information.

[0029] A candidate statement summary and candidate comparison tool according to an embodiment includes a candidate statement summary unit, a policy comparison unit, and a question and answer unit. The candidate statement summary unit summarizes candidate statements. For example, the candidate statement summary unit uses a generation AI to analyze a candidate's official statements, social media posts, speeches, and statements made at debates, and then concisely summarizes the candidate's main policies and ideas. The generation AI summarizes the statements using a text generation AI (e.g., LLM). The generation AI can also summarize the content of statements using a multimodal generation AI. The generation AI can also extract and summarize important parts of a sentence. For example, the text generation AI has trained on large amounts of text data and has advanced natural language processing capabilities. The multimodal generation AI can handle multiple modalities, including not only text but also images and audio. The generation AI uses keyword extraction technology to identify particularly important information in statements and summarizes them based on that information. The policy comparison unit compares the policies of each candidate based on the statements summarized by the candidate statement summary unit. For example, the policy comparison unit provides a function that allows users to view each candidate's position on a specific topic or policy. The generation AI analyzes the content of each candidate's statements and organizes and compares them by theme. For example, if candidate A mentions "tax reform" and candidate B mentions "expanding public investment" regarding economic policy, the generation AI displays this in a list format. The question-answering unit answers users' questions based on the policies compared by the policy comparison unit. For example, the question-answering unit has a Q&A function that allows users to post questions based on their interests. The generation AI analyzes users' questions and generates answers by searching and extracting relevant candidate statements. For example, if a user asks, "What are your views on environmental policy?", the generation AI generates answers based on each candidate's statements regarding environmental policy. As a result, the candidate statement summary and candidate comparison tool according to the embodiment can provide an environment in which voters can make decisions based on objective and accurate information.For example, in traditional candidate surveys and vote matches conducted by media outlets and organizations, each candidate answers the questions themselves, making it difficult to verify bias or veracity of the information. However, this tool's AI-based information collection process collects information neutrally, including changes in policies, beliefs, etc., making it possible to present more accurate information to voters.

[0030] The candidate statement summary section can track statements chronologically and visually display changes in policies and ideas. For example, the candidate statement summary section can track a candidate's statements chronologically and visually display changes in policies and ideas. For example, if a candidate previously advocated "tax reform" but has recently begun advocating "expansion of public investment," this change can be displayed in a graph or timeline. This visual display of changes in a candidate's policies and ideas makes it easier for voters to understand the candidate's consistency and changes.

[0031] The candidate statement summary section can compare statements with those of other candidates and statements from past elections to show consistency and changes. For example, if candidate A advocates "tax reform" while candidate B advocates "expanded public investment," the difference is visually displayed. This shows consistency and changes in the candidates' statements, making it easier for voters to understand the candidates' reliability and changes in their policies.

[0032] The candidate statement summarizing unit can automatically translate the statement summaries into different languages ​​and provide summaries in multiple languages. The candidate statement summarizing unit, for example, automatically translates the candidate statement summaries into different languages ​​and provides summaries in multiple languages. For example, it translates into multiple languages ​​such as English, French, and Chinese, and provides summaries in each language. In this way, by making the candidate statement summaries multilingual, information can be provided to voters who speak different languages.

[0033] The candidate statement summarizing unit can provide the statement summary in audio or video format to facilitate visual and auditory understanding. For example, the candidate statement summarizing unit provides the candidate statement summary in audio format to facilitate visual and auditory understanding. For example, the summarized statements are provided as an audio file using speech synthesis technology. In this way, providing the candidate statement summary in audio or video format facilitates visual and auditory understanding.

[0034] The policy comparison section allows the generation AI to perform a detailed analysis of the candidate's policies and evaluate the feasibility and impact of the policies. For example, the policy comparison section allows the generation AI to perform a detailed analysis of each candidate's policies and evaluate the feasibility of the policies. For example, the system evaluates the feasibility of candidate A's "tax reform" policy and displays the results. This makes it easier for voters to understand the realism of policies by evaluating the feasibility and impact of each candidate's policies.

[0035] The policy comparison section can compare a candidate's policies with past performance and examples from other countries to show their specific effects. For example, the policy comparison section can compare a candidate's policies with past performance and show their specific effects. For example, it can compare Candidate A's "tax reform" policy with similar policies from the past and show their effects. By comparing a candidate's policies with past performance and examples from other countries, voters can concretely understand the effects of the policies.

[0036] The policy comparison unit can collect voter reactions to each candidate's policies and display the policy support rate in real time. For example, the policy comparison unit collects voter reactions to each candidate's policies and displays the policy support rate in real time. For example, it displays the support rate for candidate A's "tax reform" policy in real time. In this way, by displaying voter reactions to each candidate's policies in real time, voters can easily understand the policy support rate.

[0037] The policy comparison section can make a multifaceted comparison of each candidate's policies from different perspectives. For example, the policy comparison section compares each candidate's policies from an economic perspective. For example, it compares candidate A's "tax reform" policy with candidate B's "expanded public investment" policy from an economic perspective. This makes it easier for voters to understand the multifaceted impact of policies by comparing each candidate's policies from different perspectives.

[0038] The policy comparison section can visualize candidates' policies in interactive graphs and charts, making it easier to compare them. For example, the policy comparison section can compare candidate policies in interactive graphs. For example, a graph can be used to compare candidate A's "tax reform" policy with candidate B's "expansion of public investment" policy. This makes it easier for voters to compare policies by visualizing candidates' policies in interactive graphs and charts.

[0039] The question answering unit can analyze the question and answer history, identify the user's areas of interest, and provide related information. For example, if the user has many questions about "environmental policy," the generation AI will provide the latest information on environmental policy. This makes it possible to identify the user's areas of interest and provide related information, thereby providing information tailored to the user's interests.

[0040] The question answering unit can associate answers to questions with questions and answers from other users to provide comprehensive information. For example, if a user asks, "Tell me about tax reform," the generation AI will refer to related questions and answers from other users to provide comprehensive information. This makes it possible to provide more comprehensive information by associating answers to questions with questions and answers from other users.

[0041] The question-answering unit can provide an intuitive interface by making the question-answering chat compatible with voice input and voice output. For example, the question-answering unit can make the question-answering chat compatible with voice input, allowing users to post questions by voice. For example, if a user asks by voice, "Tell me about economic policy," the generation AI will provide an answer by voice. In this way, by making the question-answering chat compatible with voice input and voice output, a more intuitive interface can be provided.

[0042] The question and answer unit can link the question and answer chat with social media to incorporate the opinions and feedback of other users. For example, if a user asks, "What is your opinion on tax reform?", the generation AI will refer to opinions on social media to provide an answer. In this way, by linking the question and answer chat with social media, it is possible to incorporate the opinions and feedback of other users.

[0043] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0044] The candidate statement summary section analyzes the content of statements from a geographical perspective and can show the differences and impacts of policies by region. For example, if candidate A advocates "expanding public transportation" in urban areas and emphasizes "support for agriculture" in rural areas, the differences in policies by region are displayed on a map. This makes it easier for voters to understand how the candidate's policies affect the area where they live. In addition, by displaying the evolution of policies by region over time, it is possible to visually grasp the consistency and changes in the candidate's policies.

[0045] The candidate statement summary section can track statements over time and visually display the evolution of policies and ideas. For example, if a candidate previously advocated "tax reform" but has recently begun advocating "expansion of public investment," this evolution can be displayed in graphs and timelines. This makes it easier for voters to understand the consistency and changes of candidates by visually displaying the evolution of their policies and ideas. It can also analyze the evolution of statements and show the circumstances under which candidates changed their policies.

[0046] The candidate statement summary section can compare statements with those of other candidates and statements from past elections to show consistency and changes. For example, if candidate A advocates "tax reform" while candidate B advocates "expanded public investment," the differences are visually displayed. This makes it easier for voters to understand the candidate's credibility and policy evolution by showing consistency and changes in the candidate's statements. It can also compare statements from past elections with current statements to show the evolution of a candidate's policies.

[0047] The candidate statement summarization unit can automatically translate the statement summaries into different languages ​​and provide summaries in multiple languages. For example, the candidate statement summaries can be automatically translated into different languages ​​and provided as multilingual summaries. For example, the candidate statement summaries can be translated into multiple languages, such as English, French, and Chinese, and summaries can be provided in each language. By making the candidate statement summaries multilingual, information can be provided to voters who speak different languages. Furthermore, to improve the accuracy of the translation, it is also possible to perform translations that take into account technical terms and regional expressions.

[0048] The candidate speech summarization unit can provide speech summaries in audio or video format to facilitate visual and auditory understanding. For example, the candidate speech summaries can be provided in audio format to facilitate visual and auditory understanding. For example, the summarized speech can be provided as an audio file using speech synthesis technology. This allows the candidate speech summaries to be provided in audio or video format to facilitate visual and auditory understanding. Furthermore, when provided in video format, subtitles and infographics can be added to supplement the information.

[0049] The policy comparison section uses the generation AI to perform a detailed analysis of the candidate's policies and evaluate the feasibility and impact of the policies. For example, the generation AI analyzes each candidate's policies in detail and evaluates the feasibility of the policies. For example, it evaluates the feasibility of candidate A's "tax reform" policy and displays the results. This makes it easier for voters to understand the realism of policies by evaluating the feasibility and impact of each candidate's policies. It is also possible to simulate the impact of policies and show their specific effects.

[0050] The policy comparison section can compare a candidate's policies with past performance and examples from other countries to show their specific effects. For example, it can compare a candidate's policies with past performance and show their specific effects. For example, it can compare Candidate A's "tax reform" policy with similar policies from the past and show their effects. By comparing a candidate's policies with past performance and examples from other countries, voters can concretely understand the effects of the policies. It can also refer to examples from other countries to show examples of successful and unsuccessful policies.

[0051] The policy comparison section can collect voter reactions to each candidate's policies and display the policy support rate in real time. For example, it can collect voter reactions to each candidate's policies and display the policy support rate in real time. For example, it can display the support rate for candidate A's "tax reform" policy in real time. This makes it easier for voters to understand the support rate for policies by displaying voter reactions to each candidate's policies in real time. It can also display fluctuations in support rate over time, showing changes in policy evaluation over time.

[0052] The question answering unit can analyze the question and answer history, identify the user's areas of interest, and provide related information. For example, if the user has asked many questions about "environmental policy," the generation AI can provide the latest information on environmental policy. This allows the system to identify the user's areas of interest and provide relevant information, thereby providing information tailored to the user's interests. It can also prioritize the display of statements and policies of related candidates based on the user's areas of interest.

[0053] The question answering unit can associate answers to questions with questions and answers from other users to provide comprehensive information. For example, by associating answers to questions with questions and answers from other users, more comprehensive information can be provided. For example, if a user asks, "Tell me about tax reform," the generation AI will refer to related questions and answers from other users and provide comprehensive information. This makes it possible to provide more comprehensive information by associating answers to questions with questions and answers from other users. Related questions and answers can also be displayed in the form of links, allowing users to easily access them.

[0054] The processing flow of the first embodiment will be briefly explained below.

[0055] Step 1: The candidate statement summary unit summarizes the candidate's statements. For example, the generation AI analyzes the candidate's official statements, social media posts, speeches, and comments made at debates to concisely summarize the candidate's main policies and ideas. The generation AI summarizes the statements using text generation AI (e.g., LLM). The generation AI can also summarize the content of statements using multimodal generation AI. The generation AI can also extract and summarize important parts of text. For example, text generation AI has trained on large amounts of text data and has advanced natural language processing capabilities. Multimodal generation AI can handle multiple modalities, including not only text but also images and audio. The generation AI uses keyword extraction technology to pick out particularly important information from statements and use that to create a summary. Step 2: The policy comparison unit compares the policies of each candidate based on the statements summarized by the candidate statement summary unit. For example, the policy comparison unit provides a function that allows users to view each candidate's position on a specific theme or policy. The generation AI analyzes the content of each candidate's statements and organizes and compares them by theme. For example, if candidate A mentions "tax reform" and candidate B mentions "expanding public investment" in relation to economic policy, the generation AI will display this in a list format. Step 3: The question answering unit answers the user's question based on the policies compared by the policy comparison unit. For example, the question answering unit has a Q&A function that allows users to post questions based on their own interests. The generation AI analyzes the user's question and generates an answer by searching and extracting relevant statements from the candidates. For example, if a user asks, "What are your views on environmental policy?", the generation AI generates an answer based on the statements about environmental policy made by each candidate.

[0056] (Example 2) The candidate statement summary and candidate comparison tool according to an embodiment of the present invention is a system that summarizes candidate statements, compares policies, and answers user questions, thereby providing an environment in which voters can make decisions based on objective and accurate information.

[0057] A candidate statement summary and candidate comparison tool according to an embodiment includes a candidate statement summary unit, a policy comparison unit, and a question and answer unit. The candidate statement summary unit summarizes candidate statements. For example, the candidate statement summary unit uses a generation AI to analyze a candidate's official statements, social media posts, speeches, and statements made at debates, and then concisely summarizes the candidate's main policies and ideas. The generation AI summarizes the statements using a text generation AI (e.g., LLM). The generation AI can also summarize the content of statements using a multimodal generation AI. The generation AI can also extract and summarize important parts of a sentence. For example, the text generation AI has trained on large amounts of text data and has advanced natural language processing capabilities. The multimodal generation AI can handle multiple modalities, including not only text but also images and audio. The generation AI uses keyword extraction technology to identify particularly important information in statements and summarizes them based on that information. The policy comparison unit compares the policies of each candidate based on the statements summarized by the candidate statement summary unit. For example, the policy comparison unit provides a function that allows users to view each candidate's position on a specific topic or policy. The generation AI analyzes the content of each candidate's statements and organizes and compares them by theme. For example, if candidate A mentions "tax reform" and candidate B mentions "expanding public investment" regarding economic policy, the generation AI displays this in a list format. The question-answering unit answers users' questions based on the policies compared by the policy comparison unit. For example, the question-answering unit has a Q&A function that allows users to post questions based on their interests. The generation AI analyzes users' questions and generates answers by searching and extracting relevant candidate statements. For example, if a user asks, "What are your views on environmental policy?", the generation AI generates answers based on each candidate's statements regarding environmental policy. As a result, the candidate statement summary and candidate comparison tool according to the embodiment can provide an environment in which voters can make decisions based on objective and accurate information.For example, in traditional candidate surveys and vote matches conducted by media outlets and organizations, each candidate answers the questions themselves, making it difficult to verify bias or veracity of the information. However, this tool's AI-based information collection process collects information neutrally, including changes in policies, beliefs, etc., making it possible to present more accurate information to voters.

[0058] The candidate statement summary unit can perform sentiment analysis on the content of the speech and reflect the emotional tone of the speech in the summary. For example, the candidate statement summary unit analyzes the content of a candidate's speech and performs sentiment analysis. For example, if a candidate says, "This policy is very important, and I will work hard to implement it," the generation AI will reflect the emotional tone of that speech as "strong determination" in the summary. In this way, by reflecting the emotional tone of the candidate's speech in the summary, the nuances of the speech can be conveyed more accurately.

[0059] The candidate statement summary section can track statements chronologically and visually display changes in policies and ideas. For example, the candidate statement summary section can track a candidate's statements chronologically and visually display changes in policies and ideas. For example, if a candidate previously advocated "tax reform" but has recently begun advocating "expansion of public investment," this change can be displayed in a graph or timeline. This visual display of changes in a candidate's policies and ideas makes it easier for voters to understand the candidate's consistency and changes.

[0060] The candidate statement summary section can compare statements with those of other candidates and statements from past elections to show consistency and changes. For example, if candidate A advocates "tax reform" while candidate B advocates "expanded public investment," the difference is visually displayed. This shows consistency and changes in the candidates' statements, making it easier for voters to understand the candidates' reliability and changes in their policies.

[0061] The candidate statement summarizing unit can automatically translate the statement summaries into different languages ​​and provide summaries in multiple languages. The candidate statement summarizing unit, for example, automatically translates the candidate statement summaries into different languages ​​and provides summaries in multiple languages. For example, it translates into multiple languages ​​such as English, French, and Chinese, and provides summaries in each language. In this way, by making the candidate statement summaries multilingual, information can be provided to voters who speak different languages.

[0062] The candidate statement summarizing unit can provide the statement summary in audio or video format to facilitate visual and auditory understanding. For example, the candidate statement summarizing unit provides the candidate statement summary in audio format to facilitate visual and auditory understanding. For example, the summarized statements are provided as an audio file using speech synthesis technology. In this way, providing the candidate statement summary in audio or video format facilitates visual and auditory understanding.

[0063] The candidate statement summarizing unit can use the emotion estimation function to prioritize display of statements that the user is most interested in. The candidate statement summarizing unit, for example, uses the emotion estimation function to prioritize display of statements that the user is most interested in. For example, based on the user's emotion score, statements that are of high interest are displayed preferentially. This makes it possible to provide information that matches the user's interests by prioritized display of statements that the user is most interested in.

[0064] The policy comparison section allows the generation AI to perform a detailed analysis of the candidate's policies and evaluate the feasibility and impact of the policies. For example, the policy comparison section allows the generation AI to perform a detailed analysis of each candidate's policies and evaluate the feasibility of the policies. For example, the system evaluates the feasibility of candidate A's "tax reform" policy and displays the results. This makes it easier for voters to understand the realism of policies by evaluating the feasibility and impact of each candidate's policies.

[0065] The policy comparison section can compare a candidate's policies with past performance and examples from other countries to show their specific effects. For example, the policy comparison section can compare a candidate's policies with past performance and show their specific effects. For example, it can compare Candidate A's "tax reform" policy with similar policies from the past and show their effects. By comparing a candidate's policies with past performance and examples from other countries, voters can concretely understand the effects of the policies.

[0066] The policy comparison unit can collect voter reactions to each candidate's policies and display the policy support rate in real time. For example, the policy comparison unit collects voter reactions to each candidate's policies and displays the policy support rate in real time. For example, it displays the support rate for candidate A's "tax reform" policy in real time. In this way, by displaying voter reactions to each candidate's policies in real time, voters can easily understand the policy support rate.

[0067] The policy comparison section can make a multifaceted comparison of each candidate's policies from different perspectives. For example, the policy comparison section compares each candidate's policies from an economic perspective. For example, it compares candidate A's "tax reform" policy with candidate B's "expanded public investment" policy from an economic perspective. This makes it easier for voters to understand the multifaceted impact of policies by comparing each candidate's policies from different perspectives.

[0068] The policy comparison section can visualize candidates' policies in interactive graphs and charts, making it easier to compare them. For example, the policy comparison section can compare candidate policies in interactive graphs. For example, a graph can be used to compare candidate A's "tax reform" policy with candidate B's "expansion of public investment" policy. This makes it easier for voters to compare policies by visualizing candidates' policies in interactive graphs and charts.

[0069] The policy comparison unit can use the emotion estimation function to preferentially display the policy that the user most sympathizes with. The policy comparison unit, for example, uses the emotion estimation function to preferentially display the policy that the user most sympathizes with. For example, based on the user's emotion score, the policy with which the user has a high degree of sympathy is preferentially displayed. This makes it possible to provide information according to the user's interests by preferentially displaying the policy that the user most sympathizes with.

[0070] The question answering unit performs sentiment analysis on the user's question, understanding the intent and emotions of the question and generating an answer. For example, if a user asks, "Is this policy really effective?", the generation AI will understand the doubts and anxieties and generate an appropriate answer. This allows the system to provide a more appropriate answer by understanding the intent and emotions of the user's question and generating an answer.

[0071] The question answering unit can analyze the question and answer history, identify the user's areas of interest, and provide related information. For example, if the user has many questions about "environmental policy," the generation AI will provide the latest information on environmental policy. This makes it possible to identify the user's areas of interest and provide related information, thereby providing information tailored to the user's interests.

[0072] The question answering unit can associate answers to questions with questions and answers from other users to provide comprehensive information. For example, if a user asks, "Tell me about tax reform," the generation AI will refer to related questions and answers from other users to provide comprehensive information. This makes it possible to provide more comprehensive information by associating answers to questions with questions and answers from other users.

[0073] The question-answering unit can provide an intuitive interface by making the question-answering chat compatible with voice input and voice output. For example, the question-answering unit can make the question-answering chat compatible with voice input, allowing users to post questions by voice. For example, if a user asks by voice, "Tell me about economic policy," the generation AI will provide an answer by voice. In this way, by making the question-answering chat compatible with voice input and voice output, a more intuitive interface can be provided.

[0074] The question and answer unit can link the question and answer chat with social media to incorporate the opinions and feedback of other users. For example, if a user asks, "What is your opinion on tax reform?", the generation AI will refer to opinions on social media to provide an answer. In this way, by linking the question and answer chat with social media, it is possible to incorporate the opinions and feedback of other users.

[0075] The question answering unit can use the emotion estimation function to generate answers that correspond to the user's emotions and provide empathetic responses. For example, the question answering unit can use the emotion estimation function to generate answers that correspond to the user's emotions and provide more empathetic responses. For example, if a user is feeling anxious and wondering, "Is this policy really effective?", the generation AI can empathize with that emotion and provide an answer that gives a sense of security. In this way, by generating answers that correspond to the user's emotions, a more empathetic response can be provided.

[0076] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0077] The candidate statement summary section analyzes the content of statements from a geographical perspective and can show the differences and impacts of policies by region. For example, if candidate A advocates "expanding public transportation" in urban areas and emphasizes "support for agriculture" in rural areas, the differences in policies by region are displayed on a map. This makes it easier for voters to understand how the candidate's policies affect the area where they live. In addition, by displaying the evolution of policies by region over time, it is possible to visually grasp the consistency and changes in the candidate's policies.

[0078] The candidate statement summary unit can perform sentiment analysis on the content of the statements and reflect the emotional tone of the statements in the summary. For example, if a candidate says, "This policy is very important, and I will work hard on it," the generation AI will reflect the emotional tone of that statement as "strong determination" in the summary. By reflecting the emotional tone of the candidate's statements in the summary, the nuances of the statements can be conveyed more accurately. Sentiment analysis can also be used to determine whether the candidate's statements are positive or negative, and provide that information to the user.

[0079] The candidate statement summary section can track statements over time and visually display the evolution of policies and ideas. For example, if a candidate previously advocated "tax reform" but has recently begun advocating "expansion of public investment," this evolution can be displayed in graphs and timelines. This makes it easier for voters to understand the consistency and changes of candidates by visually displaying the evolution of their policies and ideas. It can also analyze the evolution of statements and show the circumstances under which candidates changed their policies.

[0080] The candidate statement summary section can compare statements with those of other candidates and statements from past elections to show consistency and changes. For example, if candidate A advocates "tax reform" while candidate B advocates "expanded public investment," the differences are visually displayed. This makes it easier for voters to understand the candidate's credibility and policy evolution by showing consistency and changes in the candidate's statements. It can also compare statements from past elections with current statements to show the evolution of a candidate's policies.

[0081] The candidate statement summarization unit can automatically translate the statement summaries into different languages ​​and provide summaries in multiple languages. For example, the candidate statement summaries can be automatically translated into different languages ​​and provided as multilingual summaries. For example, the candidate statement summaries can be translated into multiple languages, such as English, French, and Chinese, and summaries can be provided in each language. By making the candidate statement summaries multilingual, information can be provided to voters who speak different languages. Furthermore, to improve the accuracy of the translation, it is also possible to perform translations that take into account technical terms and regional expressions.

[0082] The candidate speech summarization unit can provide speech summaries in audio or video format to facilitate visual and auditory understanding. For example, the candidate speech summaries can be provided in audio format to facilitate visual and auditory understanding. For example, the summarized speech can be provided as an audio file using speech synthesis technology. This allows the candidate speech summaries to be provided in audio or video format to facilitate visual and auditory understanding. Furthermore, when provided in video format, subtitles and infographics can be added to supplement the information.

[0083] The candidate statement summarization unit can use the emotion estimation function to prioritize displaying statements that the user is most interested in. For example, the emotion estimation function can be used to prioritize displaying statements that the user is most interested in. For example, statements that are of high interest are prioritized based on the user's emotion score. This makes it possible to provide information that matches the user's interests by prioritized displaying statements that the user is most interested in. It is also possible to analyze the user's past browsing history and question history to prioritize displaying topics that are of high interest to the user.

[0084] The policy comparison section uses the generation AI to perform a detailed analysis of the candidate's policies and evaluate the feasibility and impact of the policies. For example, the generation AI analyzes each candidate's policies in detail and evaluates the feasibility of the policies. For example, it evaluates the feasibility of candidate A's "tax reform" policy and displays the results. This makes it easier for voters to understand the realism of policies by evaluating the feasibility and impact of each candidate's policies. It is also possible to simulate the impact of policies and show their specific effects.

[0085] The policy comparison section can compare a candidate's policies with past performance and examples from other countries to show their specific effects. For example, it can compare a candidate's policies with past performance and show their specific effects. For example, it can compare Candidate A's "tax reform" policy with similar policies from the past and show their effects. By comparing a candidate's policies with past performance and examples from other countries, voters can concretely understand the effects of the policies. It can also refer to examples from other countries to show examples of successful and unsuccessful policies.

[0086] The policy comparison section can collect voter reactions to each candidate's policies and display the policy support rate in real time. For example, it can collect voter reactions to each candidate's policies and display the policy support rate in real time. For example, it can display the support rate for candidate A's "tax reform" policy in real time. This makes it easier for voters to understand the support rate for policies by displaying voter reactions to each candidate's policies in real time. It can also display fluctuations in support rate over time, showing changes in policy evaluation over time.

[0087] The policy comparison unit can use the emotion estimation function to prioritize displaying policies that the user most sympathizes with. For example, the emotion estimation function can be used to prioritize displaying policies that the user most sympathizes with. For example, based on the user's emotion score, policies with a high degree of sympathy can be prioritized. This makes it possible to provide information according to the user's interests by prioritized displaying policies with which the user most sympathizes with. In addition, the policy comparison unit can analyze the user's past question history and browsing history to prioritize displaying policies with a high degree of sympathy.

[0088] The question answering unit performs sentiment analysis on the user's question, understanding the intent and emotions of the question and generating an answer. For example, if a user asks, "Is this policy really effective?", the generation AI will understand the doubts and anxieties and generate an appropriate answer. This allows the AI ​​to understand the intent and emotions of the user's question and generate an answer that is appropriate. Sentiment analysis can also be used to provide an answer that reflects the user's emotions.

[0089] The question answering unit can analyze the question and answer history, identify the user's areas of interest, and provide related information. For example, if the user has asked many questions about "environmental policy," the generation AI can provide the latest information on environmental policy. This allows the system to identify the user's areas of interest and provide relevant information, thereby providing information tailored to the user's interests. It can also prioritize the display of statements and policies of related candidates based on the user's areas of interest.

[0090] The question answering unit can associate answers to questions with questions and answers from other users to provide comprehensive information. For example, by associating answers to questions with questions and answers from other users, more comprehensive information can be provided. For example, if a user asks, "Tell me about tax reform," the generation AI will refer to related questions and answers from other users and provide comprehensive information. This makes it possible to provide more comprehensive information by associating answers to questions with questions and answers from other users. Related questions and answers can also be displayed in the form of links, allowing users to easily access them.

[0091] The question answering unit can use the emotion estimation function to generate answers that correspond to the user's emotions and provide empathetic responses. For example, the emotion estimation function can be used to generate answers that correspond to the user's emotions and provide a more empathetic response. For example, if a user is feeling anxious and wondering, "Is this policy really effective?", the generation AI can empathize with that emotion and provide an answer that gives a sense of security. In this way, by generating answers that correspond to the user's emotions, a more empathetic response can be provided. The emotion estimation function can also be used to provide information that corresponds to the user's emotions.

[0092] The processing flow of the second embodiment will be briefly explained below.

[0093] Step 1: The candidate statement summary unit summarizes the candidate's statements. For example, the generation AI analyzes the candidate's official statements, social media posts, speeches, and comments made at debates to concisely summarize the candidate's main policies and ideas. The generation AI summarizes the statements using text generation AI (e.g., LLM). The generation AI can also summarize the content of statements using multimodal generation AI. The generation AI can also extract and summarize important parts of text. For example, text generation AI has trained on large amounts of text data and has advanced natural language processing capabilities. Multimodal generation AI can handle multiple modalities, including not only text but also images and audio. The generation AI uses keyword extraction technology to pick out particularly important information from statements and use that to create a summary. Step 2: The policy comparison unit compares the policies of each candidate based on the statements summarized by the candidate statement summary unit. For example, the policy comparison unit provides a function that allows users to view each candidate's position on a specific theme or policy. The generation AI analyzes the content of each candidate's statements and organizes and compares them by theme. For example, if candidate A mentions "tax reform" and candidate B mentions "expanding public investment" in relation to economic policy, the generation AI will display this in a list format. Step 3: The question answering unit answers the user's question based on the policies compared by the policy comparison unit. For example, the question answering unit has a Q&A function that allows users to post questions based on their own interests. The generation AI analyzes the user's question and generates an answer by searching and extracting relevant statements from the candidates. For example, if a user asks, "What are your views on environmental policy?", the generation AI generates an answer based on the statements about environmental policy made by each candidate.

[0094] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0095] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0096] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0097] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0098] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0099] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0100] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0101] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0102] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0103] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0104] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0105] 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.

[0106] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0107] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0108] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0109] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0110] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0111] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0112] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0113] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0114] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0115] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0116] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0117] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0118] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0119] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0120] 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.

[0121] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0122] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0123] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0124] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0125] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0126] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0127] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0128] 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.

[0129] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0130] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0131] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0132] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0133] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0134] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0135] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0136] 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.

[0137] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0138] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0139] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0140] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0141] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0142] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0143] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0144] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0145] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0146] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0147] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0148] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0149] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0150] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0151] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0152] 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.

[0153] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0154] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0155] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0156] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0157] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0158] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0159] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0160] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0161] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a candidate statement summarizing section that summarizes statements made by candidates; a policy comparison unit that compares the policies of each candidate based on the statements summarized by the candidate statement summarization unit; a question answering unit that answers a question from a user based on the policies compared by the policy comparison unit. A system characterized by:

2. The candidate statement summary section Track the statements over time and visually display the evolution of the policies and ideas. The system of claim 1 .

3. The candidate statement summary section Automatically translate speech summaries into different languages ​​and provide multilingual summaries The system of claim 1 .

4. The policy comparison unit The AI ​​generates a detailed analysis of the candidate's policies and evaluates their feasibility and impact. The system of claim 1 .

5. The question answering unit A sentiment analysis is performed on the question from the user, and an answer is generated based on the understanding of the intent and sentiment of the question. The system of claim 1 .

6. The candidate statement summary section Perform sentiment analysis on the speech and reflect the emotional tone of the speech in the summary The system of claim 1 .

7. The policy comparison unit Using an emotion estimation function, the policy that the user most sympathizes with is preferentially displayed. The system of claim 1 .

8. The question answering unit Using an emotion estimation function, an answer is generated according to the user's emotion, and an empathetic response is provided. The system of claim 1 .

Images