system

Abstract

The system according to the embodiment aims to enable participants to control the content of the discussion by proposing and voting on topics. [Solution] A system according to an embodiment includes a collection unit, a selection unit, a proposal unit, a voting unit, an analysis unit, and a provision unit. The collection unit collects information from news sites or social networking sites. The selection unit analyzes the information collected by the collection unit and selects topics. The proposal unit allows participants to propose themes. The voting unit votes on the proposed themes. The analysis unit analyzes participants' comments. The provision unit provides related information based on the results of the analysis by the analysis unit.

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] With conventional technology, discussion topics were set and information was provided one-sidedly, making it difficult to hold flexible discussions that reflected the opinions of participants.

[0005] The system according to the embodiment aims to enable participants to control the content of the discussion by proposing and voting on topics. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, a selection unit, a proposal unit, a voting unit, an analysis unit, and a provision unit. The collection unit collects information from news sites or social networking sites. The selection unit analyzes the information collected by the collection unit and selects a topic. The proposal unit allows participants to propose themes. The voting unit votes on the proposed themes. The analysis unit analyzes the comments made by the participants. The provision unit provides related information based on the results of the analysis by the analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can allow participants to control the content of the discussion by proposing and voting on topics. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

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

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

[0028] (Example 1) A discussion platform according to an embodiment of the present invention is a system that uses a generation AI to conduct Q&A sessions about current top topics, allowing participants to control the content by proposing and voting on discussion topics. The discussion platform collects information from news sites and social media, and the generation AI analyzes the information to select topics. Participants propose topics, and other participants vote to determine the discussion topic. Furthermore, the generation AI analyzes participants' comments during the discussion and provides related information. For example, the discussion platform collects the latest information from news sites and social media and uses natural language processing technology to select the most interesting topic. Next, participants propose topics that interest them, and other participants vote for them by clicking the "Like" button. The topic with the most votes is selected as the discussion topic. Furthermore, the generation AI analyzes participants' comments during the discussion and provides related information. This makes the discussion deeper and more fulfilling. As a result, the discussion platform allows participants to select topics based on their interests, enabling effective discussions. For example, generative AI can collect data from reliable sources and provide the latest research findings, technology trends, news, and statistical data, allowing participants to select topics based on their interests and engage in effective discussions.

[0029] A discussion platform according to an embodiment includes a collection unit, a selection unit, a proposal unit, a voting unit, an analysis unit, and a provision unit. The collection unit collects information from news sites and social networking sites. For example, the collection unit monitors the RSS feeds of news sites and collects information each time a new article is published. The collection unit can also use the social networking site's API to collect posts related to specific hashtags or keywords. The collection unit can also use a news aggregator service to collect and integrate the latest topics from multiple news sites. The selection unit analyzes the collected information and selects topics. For example, the selection unit can use text mining technology to analyze the frequency of keywords from the collected information and select topics of high interest. The selection unit can also use data mining technology to analyze users' interest levels and select topics. The selection unit can also use natural language processing technology to analyze the content of the collected information and select topics. The proposal unit allows participants to propose topics. For example, the proposal unit provides an interface that allows users to freely input topics. The suggestion unit can also suggest related themes by referring to themes previously proposed by the user. Furthermore, the suggestion unit can customize the content of the suggestions based on the user's current areas of interest. The voting unit votes for the proposed themes. The voting unit provides an interface where users can cast their votes by, for example, pressing a "Like" button. The voting unit also has a function of displaying voting results in real time. Furthermore, the voting unit can also display the voting results as graphs or charts. The analysis unit analyzes participants' comments. The analysis unit can analyze the content of participants' comments using, for example, natural language processing technology. The analysis unit can also analyze the emotional aspects of participants' comments using sentiment analysis technology. Furthermore, the analysis unit can evaluate the reliability of comments and prioritize analysis of highly reliable comments. The provision unit provides related information based on the analysis results. The provision unit can provide, for example, related news articles or research papers based on the analysis results. The provision unit can also provide related statistical data based on the analysis results.Furthermore, the providing unit may provide related references based on the analysis results, thereby enabling the discussion platform according to the embodiment to enable participants to select topics based on their own interests and realize effective discussions.

[0030] The discussion platform includes a voting interface. The voting interface is designed to allow participants to easily cast votes. For example, the voting interface may have a user-friendly design and be intuitively operable. The voting interface also has a function for updating voting results in real time. Furthermore, the voting interface can visually display voting results as graphs or charts. This allows participants to easily cast votes and check voting results in real time.

[0031] The discussion platform includes a voting result display unit that displays voting results. The voting result display unit is designed to allow participants to check the voting results. The voting result display unit has a function to display the voting results in real time, for example. The voting result display unit can also visually display the voting results as graphs or charts. Furthermore, the voting result display unit can also display the voting results in text format. This allows participants to visually check the voting results, which can be useful in advancing the discussion.

[0032] The discussion platform includes a reliability assurance unit that collects data from reliable sources. The reliability assurance unit is designed to provide highly reliable information. The reliability assurance unit collects data from reliable sources, such as official news sites and academic papers. The reliability assurance unit also evaluates the reliability of the collected information and provides only highly reliable information. Furthermore, the reliability assurance unit regularly evaluates the reliability of the information sources and selects information sources based on the latest reliability information. This enables the discussion platform to provide highly reliable information.

[0033] The collection unit can collect information from news sites and social media. For example, the collection unit can monitor the RSS feed of a news site and collect information every time a new article is published. The collection unit can also use the API of a social media site to collect posts related to specific hashtags or keywords. Furthermore, the collection unit can use a news aggregator service to collect and integrate the latest topics from multiple news sites. This allows the collection unit to collect the latest information.

[0034] The selection unit can analyze the collected information and select topics. For example, the selection unit can use text mining technology to analyze the frequency of keywords from the collected information and select topics of high interest. The selection unit can also use data mining technology to analyze the level of interest of users and select topics. Furthermore, the selection unit can also use natural language processing technology to analyze the content of the collected information and select topics. This allows the selection unit to select topics of high interest.

[0035] The suggestion unit allows participants to suggest themes. For example, the suggestion unit provides an interface that allows users to freely input themes. The suggestion unit can also suggest related themes by referring to themes previously proposed by users. Furthermore, the suggestion unit can customize the content of the suggestions based on the user's current areas of interest. This allows participants to freely suggest themes.

[0036] The voting unit allows participants to vote on the proposed themes. The voting unit provides an interface where users can vote by, for example, pressing a "Like" button. The voting unit also has a function to display voting results in real time. Furthermore, the voting unit can also display voting results as graphs or charts. This allows participants to vote on the proposed themes.

[0037] The analysis unit can analyze the participants' statements. The analysis unit can analyze the content of the participants' statements using, for example, natural language processing technology. The analysis unit can also analyze the emotional aspects of the participants' statements using sentiment analysis technology. Furthermore, the analysis unit can evaluate the reliability of the statements and prioritize analysis of highly reliable statements. This allows the analysis unit to analyze the participants' statements.

[0038] The providing unit can provide related information based on the analysis results. For example, the providing unit can provide related news articles or research papers based on the analysis results. The providing unit can also provide related statistical data based on the analysis results. Furthermore, the providing unit can provide related references based on the analysis results. This allows the providing unit to provide related information.

[0039] The collection unit can collect information from news sites and social media in real time and constantly update the latest topics. For example, the collection unit can monitor the RSS feeds of news sites in real time and collect information every time a new article is published. The collection unit can also use the APIs of social media to collect posts related to specific hashtags or keywords in real time. Furthermore, the collection unit can use a news aggregator service to collect and integrate the latest topics from multiple news sites. This allows the collection unit to constantly update the latest topics.

[0040] The collection unit can customize the type of information to be collected based on the user's past interests. For example, the collection unit preferentially collects information related to topics that the user has frequently viewed in the past. The collection unit can also analyze the user's past search history and collect information on areas of high interest. Furthermore, the collection unit can collect related information based on articles that the user has "liked" or shared in the past. This allows the collection unit to customize information based on the user's past interests.

[0041] The collection unit can filter information based on specific keywords or hashtags when collecting information. For example, the collection unit filters to collect only articles that include specific keywords. The collection unit can also be set to collect only social media posts that have specific hashtags attached. Furthermore, the collection unit can filter and collect related information based on a keyword list specified by the user. This allows the collection unit to filter information based on specific keywords or hashtags.

[0042] The collection unit can collect topics for each region by taking geographical information into consideration. For example, the collection unit can collect local news and event information based on the user's current location. The collection unit can also preferentially collect information about regions in which the user is interested. Furthermore, the collection unit can collect topics for each region and provide them in accordance with the user's interests. In this way, the collection unit can collect topics for each region.

[0043] The collection unit can preferentially collect posts from social media influencers. For example, the collection unit preferentially collects posts from influencers with a large number of followers. The collection unit can also preferentially collect posts from influencers followed by the user. Furthermore, the collection unit can also preferentially collect posts from influencers who are influential in a specific field. This allows the collection unit to preferentially collect posts from influencers.

[0044] The collection unit can customize the collection method by reflecting the user's past feedback. For example, the collection unit preferentially collects information from information sources that the user has previously rated highly. The collection unit can also filter information from information sources that the user has previously rated poorly. Furthermore, the collection unit can adjust the type and frequency of information to be collected based on the user's feedback. This allows the collection unit to customize the collection method based on the user's feedback.

[0045] When making a selection, the selection unit can evaluate the reliability of the collected information and prioritize highly reliable information. For example, the selection unit can prioritize the selection of information from highly reliable news sites. The selection unit can also prioritize the selection of statements from public institutions and experts. Furthermore, the selection unit can also prioritize the selection of information from information sources with a high past track record and reputation. This allows the selection unit to prioritize the selection of highly reliable information.

[0046] The selection unit can determine the priority of topics based on the importance of information when selecting topics. For example, the selection unit prioritizes the selection of socially important news and incidents. The selection unit can also prioritize the selection of topics that are of high interest to users. Furthermore, the selection unit can also prioritize the selection of information with a high level of urgency. This allows the selection unit to prioritize topics based on the importance of information.

[0047] When selecting topics, the selection unit can optimize the selection criteria by referring to the popularity of past topics. For example, the selection unit preferentially selects topics that many users have shown interest in in the past. The selection unit can also select popular topics by referring to past voting results. Furthermore, the selection unit can select popular topics based on the number of participants in past discussions. This allows the selection unit to optimize the selection criteria by referring to the popularity of past topics.

[0048] The selection unit may refer to related news articles and research papers when selecting a topic. For example, the selection unit may select a topic by referring to the latest news articles related to the topic. The selection unit may also select a topic by referring to research papers related to the topic. Furthermore, the selection unit may also select a topic by referring to statistical data related to the topic. This allows the selection unit to select a topic by referring to related news articles and research papers.

[0049] The selection unit may adjust the selection criteria according to the user's level of expertise when selecting a topic. For example, if the user has specialized knowledge, the selection unit may preferentially select specialized topics. Alternatively, if the user is a beginner, the selection unit may preferentially select basic topics. Furthermore, the selection unit may select topics of appropriate difficulty according to the user's level of expertise. This allows the selection unit to adjust the topic selection criteria according to the user's level of expertise.

[0050] The selection unit may take into consideration the market value of the topic when selecting a topic. For example, the selection unit may preferentially select topics with high market value. The selection unit may also take into consideration the economic impact of the topic when selecting a topic. Furthermore, the selection unit may also evaluate the commercial value of the topic when selecting a topic. This allows the selection unit to take into consideration the market value of the topic when selecting a topic.

[0051] When making a suggestion, the suggestion unit can select the optimal suggestion method by referring to the user's past suggestion history. For example, the suggestion unit can suggest related themes by referring to themes that the user has previously suggested. The suggestion unit can also analyze preference trends from the user's past suggestion history and make suggestions. Furthermore, the suggestion unit can also suggest related themes based on themes that the user has previously given high ratings. This allows the suggestion unit to select the optimal suggestion method by referring to the user's past suggestion history.

[0052] When making a suggestion, the suggestion unit can customize the suggestion content based on the user's current areas of interest. For example, the suggestion unit can suggest themes related to topics that the user is currently interested in. The suggestion unit can also suggest themes related to the user's areas of interest based on the user's current search history. Furthermore, the suggestion unit can also suggest related themes based on news and social media accounts that the user currently follows. This allows the suggestion unit to customize the suggestion content based on the user's current areas of interest.

[0053] The suggestion unit can improve the suggestion method by reflecting user feedback when making a suggestion. The suggestion unit can improve the suggestion method based on, for example, feedback previously provided by the user. The suggestion unit can also customize the content of the suggestion based on user feedback. Furthermore, the suggestion unit can adjust the frequency and timing of suggestions by reflecting user feedback. In this way, the suggestion unit can improve the suggestion method by reflecting user feedback.

[0054] When making a suggestion, the suggestion unit can suggest highly relevant themes taking into account the user's geographical location information. For example, the suggestion unit can suggest local news and event information based on the user's current location. The suggestion unit can also preferentially suggest information about regions in which the user is interested. Furthermore, the suggestion unit can suggest topics by region and provide them in accordance with the user's interests. This allows the suggestion unit to suggest highly relevant themes taking into account the user's geographical location information.

[0055] When making a suggestion, the suggestion unit can analyze the user's social media activity to suggest related themes. For example, the suggestion unit can suggest themes related to accounts the user follows on social media. The suggestion unit can also analyze the content of the user's posts on social media to suggest related themes. Furthermore, the suggestion unit can also suggest related themes by referring to the activities of the user's friends on social media. In this way, the suggestion unit can suggest related themes by analyzing the user's social media activity.

[0056] The suggestion unit can customize the suggestion method by reflecting the user's past feedback when making a suggestion. For example, the suggestion unit suggests related themes based on themes that the user has previously given high ratings to. The suggestion unit can also customize the suggestion content based on the user's past feedback. Furthermore, the suggestion unit can adjust the frequency and timing of suggestions by reflecting the user's past feedback. This allows the suggestion unit to customize the suggestion method by reflecting the user's past feedback.

[0057] When voting, the voting unit can select the optimal voting method by referring to the user's past voting history. For example, the voting unit can suggest related themes by referring to themes on which the user has voted in the past. The voting unit can also suggest voting methods by analyzing preference trends from the user's past voting history. Furthermore, the voting unit can also suggest related themes based on themes that the user has given high ratings to in the past. This allows the voting unit to select the optimal voting method by referring to the user's past voting history.

[0058] The voting unit can customize the voting content based on the user's current areas of interest when voting. For example, the voting unit can suggest themes related to topics that the user is currently interested in. The voting unit can also suggest themes related to the user's areas of interest based on the user's current search history. Furthermore, the voting unit can also suggest related themes based on the news and social media accounts that the user currently follows. This allows the voting unit to customize the voting content based on the user's current areas of interest.

[0059] The voting unit can improve the voting method by reflecting user feedback at the time of voting. For example, the voting unit improves the voting method based on feedback provided by the user in the past. The voting unit can also customize the voting content based on the user feedback. Furthermore, the voting unit can adjust the frequency and timing of voting by reflecting the user feedback. In this way, the voting unit can improve the voting method by reflecting the user feedback.

[0060] When voting, the voting unit can prioritize voting for highly relevant topics by taking into account the user's geographical location information. The voting unit can, for example, suggest local news and event information based on the user's current location. The voting unit can also prioritize suggesting information about areas in which the user is interested. Furthermore, the voting unit can suggest topics by region and provide them according to the user's interests. This allows the voting unit to prioritize voting for highly relevant topics by taking into account the user's geographical location information.

[0061] When voting, the voting unit can analyze the user's social media activity and vote for a related theme. For example, the voting unit can suggest a theme related to an account the user follows on social media. The voting unit can also analyze the content of the user's posts on social media and suggest a related theme. Furthermore, the voting unit can suggest a related theme by referring to the activities of the user's friends on social media. In this way, the voting unit can analyze the user's social media activity and vote for a related theme.

[0062] The voting unit can customize the voting method by reflecting the user's past feedback when voting. For example, the voting unit suggests related themes based on themes that the user has previously given high ratings to. The voting unit can also customize the voting content based on the user's past feedback. Furthermore, the voting unit can adjust the frequency and timing of voting by reflecting the user's past feedback. This allows the voting unit to customize the voting method by reflecting the user's past feedback.

[0063] During analysis, the analysis unit can evaluate the reliability of statements and prioritize highly reliable statements. The analysis unit can evaluate reliability based on, for example, the speaker's past performance and evaluations. The analysis unit can also evaluate reliability based on the consistency and logic of the statement content. Furthermore, the analysis unit can evaluate the reliability of statements based on the reliability of the information sources cited in the statement. This allows the analysis unit to evaluate the reliability of statements and prioritize highly reliable statements.

[0064] During analysis, the analysis unit can determine the priority of analysis based on the importance of the comments. For example, the analysis unit prioritizes analysis of socially important comments. The analysis unit can also prioritize analysis of comments that are of great interest to users. Furthermore, the analysis unit can also prioritize analysis of comments with high urgency. This allows the analysis unit to determine the priority of analysis based on the importance of the comments.

[0065] During analysis, the analysis unit can optimize the analysis criteria by referring to past comment analysis results. For example, the analysis unit prioritizes analysis of comments that many users have shown interest in in the past. The analysis unit can also analyze popular comments by referring to past voting results. Furthermore, the analysis unit can analyze popular comments based on the number of participants in past discussions. This allows the analysis unit to optimize the analysis criteria by referring to past comment analysis results.

[0066] The analysis unit can refer to related news articles and research papers when analyzing a utterance. For example, the analysis unit performs analysis by referring to the latest news articles related to the utterance. The analysis unit can also perform analysis by referring to research papers related to the utterance. Furthermore, the analysis unit can perform analysis by referring to statistical data related to the utterance. This allows the analysis unit to analyze the utterance by referring to related news articles and research papers.

[0067] When analyzing utterances, the analysis unit can adjust the analysis criteria according to the user's level of expertise. For example, if the user has specialized knowledge, the analysis unit will prioritize analyzing specialized utterances. Also, if the user is a beginner, the analysis unit can prioritize analyzing basic utterances. Furthermore, the analysis unit can analyze utterances of an appropriate level of difficulty according to the user's level of expertise. This allows the analysis unit to adjust the utterance analysis criteria according to the user's level of expertise.

[0068] When analyzing comments, the analysis unit can perform the analysis taking into account the market value of the comment. For example, the analysis unit prioritizes analysis of comments with high market value. The analysis unit can also perform the analysis taking into account the economic impact of the comment. Furthermore, the analysis unit can also evaluate and analyze the commercial value of the comment. This allows the analysis unit to perform the analysis taking into account the market value of the comment.

[0069] The providing unit can evaluate the reliability of information at the time of providing it and prioritize highly reliable information. For example, the providing unit can prioritize providing information from highly reliable news sites. The providing unit can also prioritize providing statements from public institutions and experts. Furthermore, the providing unit can prioritize providing information from information sources with a high past track record and reputation. This allows the providing unit to prioritize providing highly reliable information.

[0070] The providing unit can determine the priority of provision based on the importance of the information when providing the information. For example, the providing unit can provide socially important news or incidents with priority. The providing unit can also provide information that is of great interest to users with priority. Furthermore, the providing unit can provide information with high urgency with priority. This allows the providing unit to determine the priority of provision based on the importance of the information.

[0071] The providing unit can optimize the provision criteria by referring to past information provision results when providing information. For example, the providing unit preferentially provides information that many users have shown interest in in the past. The providing unit can also provide popular information by referring to past voting results. Furthermore, the providing unit can provide popular information based on the number of participants in past discussions. This allows the providing unit to optimize the provision criteria by referring to past information provision results.

[0072] The providing unit can refer to related news articles and research papers when providing information. For example, the providing unit provides the information by referring to the latest news articles related to the information to be provided. The providing unit can also provide the information by referring to research papers related to the information to be provided. Furthermore, the providing unit can also provide the information by referring to statistical data related to the information to be provided. This allows the providing unit to provide information by referring to related news articles and research papers.

[0073] The providing unit can adjust the provision criteria according to the user's level of expertise when providing information. For example, if the user has specialized knowledge, the providing unit can provide specialized information preferentially. Also, if the user is a beginner, the providing unit can provide basic information preferentially. Furthermore, the providing unit can provide information of an appropriate level of difficulty according to the user's level of expertise. This allows the providing unit to adjust the information provision criteria according to the user's level of expertise.

[0074] The providing unit can provide information taking into consideration the market value of the information when providing the information. For example, the providing unit provides information with a high market value preferentially. The providing unit can also provide information taking into consideration the economic impact of the information. Furthermore, the providing unit can provide information by evaluating the commercial value of the information. This allows the providing unit to provide information taking into consideration the market value of the information.

[0075] When displaying an interface, the voting interface can select the optimal display method by referring to the user's past operation history. For example, the voting interface can preferentially display interface designs that the user has used favorably in the past. The voting interface can also suggest an easy-to-use interface based on the user's past operation history. Furthermore, the voting interface can select the optimal display method based on interface designs that the user has given high ratings to in the past. This allows the voting interface to select the optimal display method by referring to the user's past operation history.

[0076] The voting interface can customize the display content according to the user's current task when the interface is displayed. For example, when the user is in a discussion, the voting interface can display relevant voting options. Also, when the user is proposing a topic, the voting interface can display voting options related to the proposal. Furthermore, the voting interface can customize and display the optimal voting option according to the user's current task. This allows the voting interface to customize the display content according to the user's current task.

[0077] The voting interface can select the optimal display method by taking into consideration the user's device information when displaying the interface. For example, if the user is using a smartphone, the voting interface can provide a display method that matches the screen size. Furthermore, if the user is using a tablet, the voting interface can provide a display method that is optimized for a large screen. Furthermore, if the user is using a smartwatch, the voting interface can provide a simple and highly visible display method. This allows the voting interface to select the optimal display method by taking into consideration the user's device information.

[0078] The voting interface can provide multilingual display content in accordance with the user's language setting when displaying the interface. For example, the voting interface can automatically set the interface language based on the language setting of the user's device. The voting interface can also provide a language switching function when the user uses multiple languages. Furthermore, if the user selects a specific language, the voting interface can provide the interface in that language. This allows the voting interface to provide multilingual display content in accordance with the user's language setting.

[0079] When displaying the voting results, the voting result display unit can select the optimal display method by referring to the user's past voting history. For example, the voting result display unit preferentially displays display methods that the user has used favorably in the past. The voting result display unit can also suggest easy-to-use display methods based on the user's past voting history. Furthermore, the voting result display unit can select the optimal display method based on display methods that the user has given high ratings to in the past. This allows the voting result display unit to select the optimal display method by referring to the user's past voting history.

[0080] The voting result display unit can customize the display content based on the user's current areas of interest when displaying the voting results. The voting result display unit displays, for example, voting results related to topics in which the user is currently interested. The voting result display unit can also display voting results related to the user's areas of interest based on the user's current search history. Furthermore, the voting result display unit can also display related voting results based on the news and social media accounts the user is currently following. This allows the voting result display unit to customize the display content based on the user's current areas of interest.

[0081] When displaying voting results, the voting result display unit can select the optimal display method by taking into consideration the user's device information. For example, if the user is using a smartphone, the voting result display unit can provide a display method that matches the screen size. Furthermore, if the user is using a tablet, the voting result display unit can also provide a display method that is optimized for a large screen. Furthermore, if the user is using a smartwatch, the voting result display unit can also provide a simple and highly visible display method. This allows the voting result display unit to select the optimal display method by taking into consideration the user's device information.

[0082] When displaying the voting results, the voting result display unit can make the display content multilingual according to the user's language setting. The voting result display unit automatically sets the language of the voting results based on, for example, the language setting of the user's device. The voting result display unit can also provide a language switching function when the user uses multiple languages. Furthermore, if the user selects a specific language, the voting result display unit can also provide the voting results in that language. This allows the voting result display unit to make the display content multilingual according to the user's language setting.

[0083] When ensuring reliability, the reliability assurance unit can select the most appropriate information source by referring to the past reliability evaluations of the information source. For example, the reliability assurance unit preferentially selects information sources that have received high evaluations in the past. The reliability assurance unit can also select information sources that have received high reliability evaluations in the past. Furthermore, the reliability assurance unit can select information sources that have a high track record or evaluations in the past. In this way, the reliability assurance unit can select the most appropriate information source by referring to the past reliability evaluations of the information source.

[0084] The reliability assurance unit can customize the information source based on the current reliability evaluation of the information source when ensuring reliability. For example, the reliability assurance unit preferentially selects information sources with a high current reliability evaluation. The reliability assurance unit can also filter information sources with a low current reliability evaluation. Furthermore, the reliability assurance unit can adjust the selection criteria for the information source based on the current reliability evaluation. This allows the reliability assurance unit to customize the information source based on the current reliability evaluation of the information source.

[0085] When ensuring reliability, the reliability assurance unit can select the most appropriate information source by referring to the past reliability evaluations of the information source. For example, the reliability assurance unit preferentially selects information sources that have received high evaluations in the past. The reliability assurance unit can also select information sources that have received high reliability evaluations in the past. Furthermore, the reliability assurance unit can select information sources that have a high track record or evaluations in the past. In this way, the reliability assurance unit can select the most appropriate information source by referring to the past reliability evaluations of the information source.

[0086] When ensuring reliability, the reliability assurance unit can select the optimal information source taking into consideration the geographical distribution of information sources. For example, the reliability assurance unit selects a highly reliable information source in a region based on the user's current location. The reliability assurance unit can also preferentially select a highly reliable information source in a region that the user is interested in. Furthermore, the reliability assurance unit can select a highly reliable information source for each region and provide it in accordance with the user's interests. This allows the reliability assurance unit to select the optimal information source taking into consideration the geographical distribution of information sources.

[0087] When ensuring trustworthiness, the trustworthiness assurance unit can analyze the social media activity of the information source to evaluate its trustworthiness. The trustworthiness assurance unit can evaluate the trustworthiness of the information source based on, for example, the number of followers and engagement on social media. The trustworthiness assurance unit can also evaluate the trustworthiness of the information source based on the content and frequency of posts on social media. Furthermore, the trustworthiness assurance unit can evaluate the trustworthiness of the information source based on user ratings and comments on social media. In this way, the trustworthiness assurance unit can analyze the social media activity of the information source to evaluate its trustworthiness.

[0088] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0089] The discussion platform can further analyze the user's past discussion history and suggest themes based on topics that the user has shown interest in in the past. For example, it can analyze topics in which the user has made many comments in the past and discussions in which the user has participated for a long time and suggest related themes. It can also suggest related themes based on discussion themes that the user has given high ratings in the past. It can also analyze the content of discussions in which the user has participated in the past and suggest new themes that the user may be interested in. This makes it possible to suggest more personalized themes based on the user's past discussion history.

[0090] The voting interface can further analyze the user's voting behavior and customize voting options based on the user's voting trends. For example, it can prioritize options related to topics on which the user has frequently voted in the past. It can also suggest related voting options based on topics that the user has previously given high ratings. It can also analyze the user's voting history and suggest new voting options that may be of interest to the user. This provides more personalized voting options based on the user's voting behavior.

[0091] The voting result display unit can also analyze the user's reaction to the voting results and adjust the display method. For example, if the user has previously preferred visual display methods, it can prioritize displays using graphs and charts. Alternatively, if the user has preferred text-based displays, it can provide a text-based display. Furthermore, it can adjust the display method in real time based on the user's reaction. This makes it possible to display voting results according to the user's preferences.

[0092] The reliability assurance unit can also collect user feedback and reflect it in the reliability evaluation of the information source. For example, if a user gives a high rating to an information source, the reliability of that information source can be rated high. Conversely, if a user gives a low rating, the reliability of that information source can be rated low. Furthermore, user feedback can be collected periodically and the reliability evaluation can be updated. This makes it possible to select more reliable information sources based on user feedback.

[0093] The collection unit can further adjust the method of information collection by taking into account the user's device information. For example, if the user is using a smartphone, mobile-friendly information can be collected preferentially. Also, if the user is using a tablet, information optimized for large screens can be collected. Furthermore, if the user is using a smartwatch, concise and highly visible information can be collected. This makes it possible to collect optimal information based on the user's device information.

[0094] The processing flow of the first embodiment will be briefly explained below.

[0095] Step 1: The collection unit collects information from news sites and social media. For example, it monitors the RSS feeds of news sites and collects information whenever a new article is published. It can also use social media APIs to collect posts related to specific hashtags or keywords. It can also use news aggregator services to collect and integrate the latest topics from multiple news sites. Step 2: The selection unit analyzes the collected information and selects topics. For example, text mining technology can be used to analyze the frequency of keywords in the collected information and select topics of high interest. Data mining technology can also be used to analyze the level of user interest and select topics. Furthermore, natural language processing technology can be used to analyze the content of the collected information and select topics. Step 3: The suggestion unit allows participants to suggest topics. For example, it provides an interface that allows users to freely input topics. It can also suggest related topics based on themes previously proposed by users. It can also customize the suggestions based on the user's current areas of interest. Step 4: The voting section allows users to vote on the proposed topic. For example, it provides an interface where users can vote by pressing a "Like" button. It also has a function to display the voting results in real time. It can also display the voting results as graphs or charts. Step 5: The analysis unit analyzes the participants' comments. For example, natural language processing technology can be used to analyze the content of the participants' comments. Sentiment analysis technology can also be used to analyze the emotional aspects of the participants' comments. Furthermore, the reliability of the comments can be evaluated, and highly reliable comments can be prioritized for analysis. Step 6: The providing unit provides related information based on the analysis results. For example, based on the analysis results, related news articles or research papers are provided. Based on the analysis results, related statistical data can also be provided. Furthermore, based on the analysis results, related references can also be provided.

[0096] (Example 2) A discussion platform according to an embodiment of the present invention is a system that uses a generation AI to conduct Q&A sessions about current top topics, allowing participants to control the content by proposing and voting on discussion topics. The discussion platform collects information from news sites and social media, and the generation AI analyzes the information to select topics. Participants propose topics, and other participants vote to determine the discussion topic. Furthermore, the generation AI analyzes participants' comments during the discussion and provides related information. For example, the discussion platform collects the latest information from news sites and social media and uses natural language processing technology to select the most interesting topic. Next, participants propose topics that interest them, and other participants vote for them by clicking the "Like" button. The topic with the most votes is selected as the discussion topic. Furthermore, the generation AI analyzes participants' comments during the discussion and provides related information. This makes the discussion deeper and more fulfilling. As a result, the discussion platform allows participants to select topics based on their interests, enabling effective discussions. For example, generative AI can collect data from reliable sources and provide the latest research findings, technology trends, news, and statistical data, allowing participants to select topics based on their interests and engage in effective discussions.

[0097] A discussion platform according to an embodiment includes a collection unit, a selection unit, a proposal unit, a voting unit, an analysis unit, and a provision unit. The collection unit collects information from news sites and social networking sites. For example, the collection unit monitors the RSS feeds of news sites and collects information each time a new article is published. The collection unit can also use the social networking site's API to collect posts related to specific hashtags or keywords. The collection unit can also use a news aggregator service to collect and integrate the latest topics from multiple news sites. The selection unit analyzes the collected information and selects topics. For example, the selection unit can use text mining technology to analyze the frequency of keywords from the collected information and select topics of high interest. The selection unit can also use data mining technology to analyze users' interest levels and select topics. The selection unit can also use natural language processing technology to analyze the content of the collected information and select topics. The proposal unit allows participants to propose topics. For example, the proposal unit provides an interface that allows users to freely input topics. The suggestion unit can also suggest related themes by referring to themes previously proposed by the user. Furthermore, the suggestion unit can customize the content of the suggestions based on the user's current areas of interest. The voting unit votes for the proposed themes. The voting unit provides an interface where users can cast their votes by, for example, pressing a "Like" button. The voting unit also has a function of displaying voting results in real time. Furthermore, the voting unit can also display the voting results as graphs or charts. The analysis unit analyzes participants' comments. The analysis unit can analyze the content of participants' comments using, for example, natural language processing technology. The analysis unit can also analyze the emotional aspects of participants' comments using sentiment analysis technology. Furthermore, the analysis unit can evaluate the reliability of comments and prioritize analysis of highly reliable comments. The provision unit provides related information based on the analysis results. The provision unit can provide, for example, related news articles or research papers based on the analysis results. The provision unit can also provide related statistical data based on the analysis results.Furthermore, the providing unit may provide related references based on the analysis results, thereby enabling the discussion platform according to the embodiment to enable participants to select topics based on their own interests and realize effective discussions.

[0098] The discussion platform includes a voting interface. The voting interface is designed to allow participants to easily cast votes. For example, the voting interface may have a user-friendly design and be intuitively operable. The voting interface also has a function for updating voting results in real time. Furthermore, the voting interface can visually display voting results as graphs or charts. This allows participants to easily cast votes and check voting results in real time.

[0099] The discussion platform includes a voting result display unit that displays voting results. The voting result display unit is designed to allow participants to check the voting results. The voting result display unit has a function to display the voting results in real time, for example. The voting result display unit can also visually display the voting results as graphs or charts. Furthermore, the voting result display unit can also display the voting results in text format. This allows participants to visually check the voting results, which can be useful in advancing the discussion.

[0100] The discussion platform includes a reliability assurance unit that collects data from reliable sources. The reliability assurance unit is designed to provide highly reliable information. The reliability assurance unit collects data from reliable sources, such as official news sites and academic papers. The reliability assurance unit also evaluates the reliability of the collected information and provides only highly reliable information. Furthermore, the reliability assurance unit regularly evaluates the reliability of the information sources and selects information sources based on the latest reliability information. This enables the discussion platform to provide highly reliable information.

[0101] The collection unit can collect information from news sites and social media. For example, the collection unit can monitor the RSS feed of a news site and collect information every time a new article is published. The collection unit can also use the API of a social media site to collect posts related to specific hashtags or keywords. Furthermore, the collection unit can use a news aggregator service to collect and integrate the latest topics from multiple news sites. This allows the collection unit to collect the latest information.

[0102] The selection unit can analyze the collected information and select topics. For example, the selection unit can use text mining technology to analyze the frequency of keywords from the collected information and select topics of high interest. The selection unit can also use data mining technology to analyze the level of interest of users and select topics. Furthermore, the selection unit can also use natural language processing technology to analyze the content of the collected information and select topics. This allows the selection unit to select topics of high interest.

[0103] The suggestion unit allows participants to suggest themes. For example, the suggestion unit provides an interface that allows users to freely input themes. The suggestion unit can also suggest related themes by referring to themes previously proposed by users. Furthermore, the suggestion unit can customize the content of the suggestions based on the user's current areas of interest. This allows participants to freely suggest themes.

[0104] The voting unit allows participants to vote on the proposed themes. The voting unit provides an interface where users can vote by, for example, pressing a "Like" button. The voting unit also has a function to display voting results in real time. Furthermore, the voting unit can also display voting results as graphs or charts. This allows participants to vote on the proposed themes.

[0105] The analysis unit can analyze the participants' statements. The analysis unit can analyze the content of the participants' statements using, for example, natural language processing technology. The analysis unit can also analyze the emotional aspects of the participants' statements using sentiment analysis technology. Furthermore, the analysis unit can evaluate the reliability of the statements and prioritize analysis of highly reliable statements. This allows the analysis unit to analyze the participants' statements.

[0106] The providing unit can provide related information based on the analysis results. For example, the providing unit can provide related news articles or research papers based on the analysis results. The providing unit can also provide related statistical data based on the analysis results. Furthermore, the providing unit can provide related references based on the analysis results. This allows the providing unit to provide related information.

[0107] The collection unit can estimate the user's emotions and adjust the timing of information collection based on the estimated user emotions. For example, when the user is excited, the collection unit collects information in real time and provides it immediately. In addition, when the user is relaxed, the collection unit can periodically collect information and provide it in bulk. Furthermore, when the user is stressed, the collection unit can reduce the frequency of information collection and provide only important information. This allows the collection unit to adjust the timing of information collection according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0108] The collection unit can collect information from news sites and social media in real time and constantly update the latest topics. For example, the collection unit can monitor the RSS feeds of news sites in real time and collect information every time a new article is published. The collection unit can also use the APIs of social media to collect posts related to specific hashtags or keywords in real time. Furthermore, the collection unit can use a news aggregator service to collect and integrate the latest topics from multiple news sites. This allows the collection unit to constantly update the latest topics.

[0109] The collection unit can customize the type of information to be collected based on the user's past interests. For example, the collection unit preferentially collects information related to topics that the user has frequently viewed in the past. The collection unit can also analyze the user's past search history and collect information on areas of high interest. Furthermore, the collection unit can collect related information based on articles that the user has "liked" or shared in the past. This allows the collection unit to customize information based on the user's past interests.

[0110] The collection unit can filter information based on specific keywords or hashtags when collecting information. For example, the collection unit filters to collect only articles that include specific keywords. The collection unit can also be set to collect only social media posts that have specific hashtags attached. Furthermore, the collection unit can filter and collect related information based on a keyword list specified by the user. This allows the collection unit to filter information based on specific keywords or hashtags.

[0111] The collection unit can estimate the user's emotions and determine the priority of information to be collected based on the estimated user emotions. For example, if the user is excited, the collection unit can prioritize collecting entertainment-related information. Also, if the user is relaxed, the collection unit can prioritize collecting relaxing content. Furthermore, if the user is stressed, the collection unit can prioritize collecting information that is useful for stress reduction. This allows the collection unit to determine the priority of information based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0112] The collection unit can collect topics for each region by taking geographical information into consideration. For example, the collection unit can collect local news and event information based on the user's current location. The collection unit can also preferentially collect information about regions in which the user is interested. Furthermore, the collection unit can collect topics for each region and provide them in accordance with the user's interests. In this way, the collection unit can collect topics for each region.

[0113] The collection unit can preferentially collect posts from social media influencers. For example, the collection unit preferentially collects posts from influencers with a large number of followers. The collection unit can also preferentially collect posts from influencers followed by the user. Furthermore, the collection unit can also preferentially collect posts from influencers who are influential in a specific field. This allows the collection unit to preferentially collect posts from influencers.

[0114] The collection unit can customize the collection method by reflecting the user's past feedback. For example, the collection unit preferentially collects information from information sources that the user has previously rated highly. The collection unit can also filter information from information sources that the user has previously rated poorly. Furthermore, the collection unit can adjust the type and frequency of information to be collected based on the user's feedback. This allows the collection unit to customize the collection method based on the user's feedback.

[0115] The selection unit can estimate the user's emotions and adjust the topic selection criteria based on the estimated user emotions. For example, if the user is excited, the selection unit can prioritize selecting entertainment or sports-related topics. Furthermore, if the user is relaxed, the selection unit can prioritize selecting relaxing content. Furthermore, if the user is stressed, the selection unit can prioritize selecting topics that are useful for stress reduction. This allows the selection unit to adjust the topic selection criteria based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0116] When making a selection, the selection unit can evaluate the reliability of the collected information and prioritize highly reliable information. For example, the selection unit can prioritize the selection of information from highly reliable news sites. The selection unit can also prioritize the selection of statements from public institutions and experts. Furthermore, the selection unit can also prioritize the selection of information from information sources with a high past track record and reputation. This allows the selection unit to prioritize the selection of highly reliable information.

[0117] The selection unit can determine the priority of topics based on the importance of information when selecting topics. For example, the selection unit prioritizes the selection of socially important news and incidents. The selection unit can also prioritize the selection of topics that are of high interest to users. Furthermore, the selection unit can also prioritize the selection of information with a high level of urgency. This allows the selection unit to prioritize topics based on the importance of information.

[0118] When selecting topics, the selection unit can optimize the selection criteria by referring to the popularity of past topics. For example, the selection unit preferentially selects topics that many users have shown interest in in the past. The selection unit can also select popular topics by referring to past voting results. Furthermore, the selection unit can select popular topics based on the number of participants in past discussions. This allows the selection unit to optimize the selection criteria by referring to the popularity of past topics.

[0119] The selection unit can estimate the user's emotions and adjust the display method of the selected topic based on the estimated user's emotions. For example, if the user is excited, the selection unit can provide a visually stimulating display method. Furthermore, if the user is relaxed, the selection unit can provide a calm display method. Furthermore, if the user is stressed, the selection unit can provide a simple, highly visible display method. This allows the selection unit to adjust the display method of the topic based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0120] The selection unit may refer to related news articles and research papers when selecting a topic. For example, the selection unit may select a topic by referring to the latest news articles related to the topic. The selection unit may also select a topic by referring to research papers related to the topic. Furthermore, the selection unit may also select a topic by referring to statistical data related to the topic. This allows the selection unit to select a topic by referring to related news articles and research papers.

[0121] The selection unit may adjust the selection criteria according to the user's level of expertise when selecting a topic. For example, if the user has specialized knowledge, the selection unit may preferentially select specialized topics. Alternatively, if the user is a beginner, the selection unit may preferentially select basic topics. Furthermore, the selection unit may select topics of appropriate difficulty according to the user's level of expertise. This allows the selection unit to adjust the topic selection criteria according to the user's level of expertise.

[0122] The selection unit may take into consideration the market value of the topic when selecting a topic. For example, the selection unit may preferentially select topics with high market value. The selection unit may also take into consideration the economic impact of the topic when selecting a topic. Furthermore, the selection unit may also evaluate the commercial value of the topic when selecting a topic. This allows the selection unit to take into consideration the market value of the topic when selecting a topic.

[0123] The suggestion unit can estimate the user's emotions and adjust the theme suggestion method based on the estimated user's emotions. For example, if the user is excited, the suggestion unit can provide a visually stimulating suggestion method. Furthermore, if the user is relaxed, the suggestion unit can provide a calming suggestion method. Furthermore, if the user is stressed, the suggestion unit can provide a simple and highly visible suggestion method. This allows the suggestion unit to adjust the theme suggestion method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0124] When making a suggestion, the suggestion unit can select the optimal suggestion method by referring to the user's past suggestion history. For example, the suggestion unit can suggest related themes by referring to themes that the user has previously suggested. The suggestion unit can also analyze preference trends from the user's past suggestion history and make suggestions. Furthermore, the suggestion unit can also suggest related themes based on themes that the user has previously given high ratings. This allows the suggestion unit to select the optimal suggestion method by referring to the user's past suggestion history.

[0125] When making a suggestion, the suggestion unit can customize the suggestion content based on the user's current areas of interest. For example, the suggestion unit can suggest themes related to topics that the user is currently interested in. The suggestion unit can also suggest themes related to the user's areas of interest based on the user's current search history. Furthermore, the suggestion unit can also suggest related themes based on news and social media accounts that the user currently follows. This allows the suggestion unit to customize the suggestion content based on the user's current areas of interest.

[0126] The suggestion unit can improve the suggestion method by reflecting user feedback when making a suggestion. The suggestion unit can improve the suggestion method based on, for example, feedback previously provided by the user. The suggestion unit can also customize the content of the suggestion based on user feedback. Furthermore, the suggestion unit can adjust the frequency and timing of suggestions by reflecting user feedback. In this way, the suggestion unit can improve the suggestion method by reflecting user feedback.

[0127] The suggestion unit can estimate the user's emotions and determine the priority of themes to be suggested based on the estimated user emotions. For example, if the user is excited, the suggestion unit can prioritize entertainment or sports-related themes. Furthermore, if the user is relaxed, the suggestion unit can prioritize relaxing themes. Furthermore, if the user is stressed, the suggestion unit can prioritize stress-relieving themes. This allows the suggestion unit to prioritize themes based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0128] When making a suggestion, the suggestion unit can suggest highly relevant themes taking into account the user's geographical location information. For example, the suggestion unit can suggest local news and event information based on the user's current location. The suggestion unit can also preferentially suggest information about regions in which the user is interested. Furthermore, the suggestion unit can suggest topics by region and provide them in accordance with the user's interests. This allows the suggestion unit to suggest highly relevant themes taking into account the user's geographical location information.

[0129] When making a suggestion, the suggestion unit can analyze the user's social media activity to suggest related themes. For example, the suggestion unit can suggest themes related to accounts the user follows on social media. The suggestion unit can also analyze the content of the user's posts on social media to suggest related themes. Furthermore, the suggestion unit can also suggest related themes by referring to the activities of the user's friends on social media. In this way, the suggestion unit can suggest related themes by analyzing the user's social media activity.

[0130] The suggestion unit can customize the suggestion method by reflecting the user's past feedback when making a suggestion. For example, the suggestion unit suggests related themes based on themes that the user has previously given high ratings to. The suggestion unit can also customize the suggestion content based on the user's past feedback. Furthermore, the suggestion unit can adjust the frequency and timing of suggestions by reflecting the user's past feedback. This allows the suggestion unit to customize the suggestion method by reflecting the user's past feedback.

[0131] The voting unit can estimate the user's emotions and adjust the voting method based on the estimated user's emotions. For example, if the user is excited, the voting unit can provide a visually stimulating voting method. Furthermore, if the user is relaxed, the voting unit can provide a calm voting method. Furthermore, if the user is stressed, the voting unit can provide a simple, highly visible voting method. This allows the voting unit to adjust the voting method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0132] When voting, the voting unit can select the optimal voting method by referring to the user's past voting history. For example, the voting unit can suggest related themes by referring to themes on which the user has voted in the past. The voting unit can also suggest voting methods by analyzing preference trends from the user's past voting history. Furthermore, the voting unit can also suggest related themes based on themes that the user has given high ratings to in the past. This allows the voting unit to select the optimal voting method by referring to the user's past voting history.

[0133] The voting unit can customize the voting content based on the user's current areas of interest when voting. For example, the voting unit can suggest themes related to topics that the user is currently interested in. The voting unit can also suggest themes related to the user's areas of interest based on the user's current search history. Furthermore, the voting unit can also suggest related themes based on the news and social media accounts that the user currently follows. This allows the voting unit to customize the voting content based on the user's current areas of interest.

[0134] The voting unit can improve the voting method by reflecting user feedback at the time of voting. For example, the voting unit improves the voting method based on feedback provided by the user in the past. The voting unit can also customize the voting content based on the user feedback. Furthermore, the voting unit can adjust the frequency and timing of voting by reflecting the user feedback. In this way, the voting unit can improve the voting method by reflecting the user feedback.

[0135] The voting unit can estimate the user's emotions and determine the priority of themes to be voted on based on the estimated user emotions. For example, if the user is excited, the voting unit can preferentially suggest entertainment or sports-related themes. Furthermore, if the user is relaxed, the voting unit can preferentially suggest relaxing themes. Furthermore, if the user is stressed, the voting unit can preferentially suggest themes that are useful for stress reduction. In this way, the voting unit can determine the priority of themes to be voted on based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0136] When voting, the voting unit can prioritize voting for highly relevant topics by taking into account the user's geographical location information. The voting unit can, for example, suggest local news and event information based on the user's current location. The voting unit can also prioritize suggesting information about areas in which the user is interested. Furthermore, the voting unit can suggest topics by region and provide them according to the user's interests. This allows the voting unit to prioritize voting for highly relevant topics by taking into account the user's geographical location information.

[0137] When voting, the voting unit can analyze the user's social media activity and vote for a related theme. For example, the voting unit can suggest a theme related to an account the user follows on social media. The voting unit can also analyze the content of the user's posts on social media and suggest a related theme. Furthermore, the voting unit can suggest a related theme by referring to the activities of the user's friends on social media. In this way, the voting unit can analyze the user's social media activity and vote for a related theme.

[0138] The voting unit can customize the voting method by reflecting the user's past feedback when voting. For example, the voting unit suggests related themes based on themes that the user has previously given high ratings to. The voting unit can also customize the voting content based on the user's past feedback. Furthermore, the voting unit can adjust the frequency and timing of voting by reflecting the user's past feedback. This allows the voting unit to customize the voting method by reflecting the user's past feedback.

[0139] The analysis unit can estimate the user's emotions and adjust the method of utterance analysis based on the estimated user emotions. For example, if the user is excited, the analysis unit focuses on the emotional aspects of the utterance in the analysis. Furthermore, if the user is relaxed, the analysis unit can analyze the content of the utterance in detail. Furthermore, if the user is feeling stressed, the analysis unit can identify and analyze the stress factors in the utterance. This allows the analysis unit to adjust the method of utterance analysis based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0140] During analysis, the analysis unit can evaluate the reliability of statements and prioritize highly reliable statements. The analysis unit can evaluate reliability based on, for example, the speaker's past performance and evaluations. The analysis unit can also evaluate reliability based on the consistency and logic of the statement content. Furthermore, the analysis unit can evaluate the reliability of statements based on the reliability of the information sources cited in the statement. This allows the analysis unit to evaluate the reliability of statements and prioritize highly reliable statements.

[0141] During analysis, the analysis unit can determine the priority of analysis based on the importance of the comments. For example, the analysis unit prioritizes analysis of socially important comments. The analysis unit can also prioritize analysis of comments that are of great interest to users. Furthermore, the analysis unit can also prioritize analysis of comments with high urgency. This allows the analysis unit to determine the priority of analysis based on the importance of the comments.

[0142] During analysis, the analysis unit can optimize the analysis criteria by referring to past comment analysis results. For example, the analysis unit prioritizes analysis of comments that many users have shown interest in in the past. The analysis unit can also analyze popular comments by referring to past voting results. Furthermore, the analysis unit can analyze popular comments based on the number of participants in past discussions. This allows the analysis unit to optimize the analysis criteria by referring to past comment analysis results.

[0143] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is excited, the analysis unit provides a visually stimulating display method. Furthermore, if the user is relaxed, the analysis unit can provide a calming display method. Furthermore, if the user is stressed, the analysis unit can provide a simple, highly visible display method. This allows the analysis unit to adjust the display method of the analysis results based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0144] The analysis unit can refer to related news articles and research papers when analyzing a utterance. For example, the analysis unit performs analysis by referring to the latest news articles related to the utterance. The analysis unit can also perform analysis by referring to research papers related to the utterance. Furthermore, the analysis unit can perform analysis by referring to statistical data related to the utterance. This allows the analysis unit to analyze the utterance by referring to related news articles and research papers.

[0145] When analyzing utterances, the analysis unit can adjust the analysis criteria according to the user's level of expertise. For example, if the user has specialized knowledge, the analysis unit will prioritize analyzing specialized utterances. Also, if the user is a beginner, the analysis unit can prioritize analyzing basic utterances. Furthermore, the analysis unit can analyze utterances of an appropriate level of difficulty according to the user's level of expertise. This allows the analysis unit to adjust the utterance analysis criteria according to the user's level of expertise.

[0146] When analyzing comments, the analysis unit can perform the analysis taking into account the market value of the comment. For example, the analysis unit prioritizes analysis of comments with high market value. The analysis unit can also perform the analysis taking into account the economic impact of the comment. Furthermore, the analysis unit can also evaluate and analyze the commercial value of the comment. This allows the analysis unit to perform the analysis taking into account the market value of the comment.

[0147] The providing unit can estimate the user's emotions and adjust the information provision method based on the estimated user's emotions. For example, if the user is excited, the providing unit can provide a visually stimulating information provision method. Furthermore, if the user is relaxed, the providing unit can also provide a calming information provision method. Furthermore, if the user is stressed, the providing unit can also provide a simple and highly visible information provision method. This allows the providing unit to adjust the information provision method based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0148] The providing unit can evaluate the reliability of information at the time of providing it and prioritize highly reliable information. For example, the providing unit can prioritize providing information from highly reliable news sites. The providing unit can also prioritize providing statements from public institutions and experts. Furthermore, the providing unit can prioritize providing information from information sources with a high past track record and reputation. This allows the providing unit to prioritize providing highly reliable information.

[0149] The providing unit can determine the priority of provision based on the importance of the information when providing the information. For example, the providing unit can provide socially important news or incidents with priority. The providing unit can also provide information that is of great interest to users with priority. Furthermore, the providing unit can provide information with high urgency with priority. This allows the providing unit to determine the priority of provision based on the importance of the information.

[0150] The providing unit can optimize the provision criteria by referring to past information provision results when providing information. For example, the providing unit preferentially provides information that many users have shown interest in in the past. The providing unit can also provide popular information by referring to past voting results. Furthermore, the providing unit can provide popular information based on the number of participants in past discussions. This allows the providing unit to optimize the provision criteria by referring to past information provision results.

[0151] The providing unit can estimate the user's emotions and adjust the display method of the information to be provided based on the estimated user's emotions. For example, if the user is excited, the providing unit can provide a visually stimulating display method. Furthermore, if the user is relaxed, the providing unit can also provide a calming display method. Furthermore, if the user is stressed, the providing unit can also provide a simple, highly visible display method. This allows the providing unit to adjust the display method of the information based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0152] The providing unit can refer to related news articles and research papers when providing information. For example, the providing unit provides the information by referring to the latest news articles related to the information to be provided. The providing unit can also provide the information by referring to research papers related to the information to be provided. Furthermore, the providing unit can also provide the information by referring to statistical data related to the information to be provided. This allows the providing unit to provide information by referring to related news articles and research papers.

[0153] The providing unit can adjust the provision criteria according to the user's level of expertise when providing information. For example, if the user has specialized knowledge, the providing unit can provide specialized information preferentially. Also, if the user is a beginner, the providing unit can provide basic information preferentially. Furthermore, the providing unit can provide information of an appropriate level of difficulty according to the user's level of expertise. This allows the providing unit to adjust the information provision criteria according to the user's level of expertise.

[0154] The providing unit can provide information taking into consideration the market value of the information when providing the information. For example, the providing unit provides information with a high market value preferentially. The providing unit can also provide information taking into consideration the economic impact of the information. Furthermore, the providing unit can provide information by evaluating the commercial value of the information. This allows the providing unit to provide information taking into consideration the market value of the information.

[0155] The voting interface can estimate the user's emotions and adjust the interface display method based on the estimated user emotions. For example, when the user is excited, the voting interface can provide a visually stimulating interface. When the user is relaxed, the voting interface can also provide a calming interface. When the user is stressed, the voting interface can also provide a simple, highly visible interface. This allows the voting interface to adjust the interface display method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0156] When displaying an interface, the voting interface can select the optimal display method by referring to the user's past operation history. For example, the voting interface can preferentially display interface designs that the user has used favorably in the past. The voting interface can also suggest an easy-to-use interface based on the user's past operation history. Furthermore, the voting interface can select the optimal display method based on interface designs that the user has given high ratings to in the past. This allows the voting interface to select the optimal display method by referring to the user's past operation history.

[0157] The voting interface can customize the display content according to the user's current task when the interface is displayed. For example, when the user is in a discussion, the voting interface can display relevant voting options. Also, when the user is proposing a topic, the voting interface can display voting options related to the proposal. Furthermore, the voting interface can customize and display the optimal voting option according to the user's current task. This allows the voting interface to customize the display content according to the user's current task.

[0158] The voting interface can estimate the user's emotions and adjust the interface's operation procedures based on the estimated user's emotions. For example, the voting interface can provide intuitive and simple operation procedures when the user is excited. The voting interface can also provide detailed operation procedures when the user is relaxed. Furthermore, the voting interface can also provide simple and highly visible operation procedures when the user is stressed. This allows the voting interface to adjust the interface's operation procedures based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0159] The voting interface can select the optimal display method by taking into consideration the user's device information when displaying the interface. For example, if the user is using a smartphone, the voting interface can provide a display method that matches the screen size. Furthermore, if the user is using a tablet, the voting interface can provide a display method that is optimized for a large screen. Furthermore, if the user is using a smartwatch, the voting interface can provide a simple and highly visible display method. This allows the voting interface to select the optimal display method by taking into consideration the user's device information.

[0160] The voting interface can provide multilingual display content in accordance with the user's language setting when displaying the interface. For example, the voting interface can automatically set the interface language based on the language setting of the user's device. The voting interface can also provide a language switching function when the user uses multiple languages. Furthermore, if the user selects a specific language, the voting interface can provide the interface in that language. This allows the voting interface to provide multilingual display content in accordance with the user's language setting.

[0161] The voting result display unit can estimate the user's emotions and adjust the display method of the voting results based on the estimated user emotions. For example, if the user is excited, the voting result display unit can provide a visually stimulating display method. Furthermore, if the user is relaxed, the voting result display unit can also provide a calming display method. Furthermore, if the user is stressed, the voting result display unit can also provide a simple, highly visible display method. This allows the voting result display unit to adjust the display method of the voting results based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0162] When displaying the voting results, the voting result display unit can select the optimal display method by referring to the user's past voting history. For example, the voting result display unit preferentially displays display methods that the user has used favorably in the past. The voting result display unit can also suggest easy-to-use display methods based on the user's past voting history. Furthermore, the voting result display unit can select the optimal display method based on display methods that the user has given high ratings to in the past. This allows the voting result display unit to select the optimal display method by referring to the user's past voting history.

[0163] The voting result display unit can customize the display content based on the user's current areas of interest when displaying the voting results. The voting result display unit displays, for example, voting results related to topics in which the user is currently interested. The voting result display unit can also display voting results related to the user's areas of interest based on the user's current search history. Furthermore, the voting result display unit can also display related voting results based on the news and social media accounts the user is currently following. This allows the voting result display unit to customize the display content based on the user's current areas of interest.

[0164] The voting result display unit can estimate the user's emotions and adjust the display order of the voting results based on the estimated user's emotions. For example, if the user is excited, the voting result display unit can provide a visually stimulating display order. Furthermore, if the user is relaxed, the voting result display unit can also provide a calm display order. Furthermore, if the user is stressed, the voting result display unit can also provide a simple, highly visible display order. This allows the voting result display unit to adjust the display order of the voting results based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0165] When displaying voting results, the voting result display unit can select the optimal display method by taking into consideration the user's device information. For example, if the user is using a smartphone, the voting result display unit can provide a display method that matches the screen size. Furthermore, if the user is using a tablet, the voting result display unit can also provide a display method that is optimized for a large screen. Furthermore, if the user is using a smartwatch, the voting result display unit can also provide a simple and highly visible display method. This allows the voting result display unit to select the optimal display method by taking into consideration the user's device information.

[0166] When displaying the voting results, the voting result display unit can make the display content multilingual according to the user's language setting. The voting result display unit automatically sets the language of the voting results based on, for example, the language setting of the user's device. The voting result display unit can also provide a language switching function when the user uses multiple languages. Furthermore, if the user selects a specific language, the voting result display unit can also provide the voting results in that language. This allows the voting result display unit to make the display content multilingual according to the user's language setting.

[0167] The reliability assurance unit can estimate the user's emotions and select a reliable information source based on the estimated user's emotions. For example, if the user is excited, the reliability assurance unit selects a reliable entertainment-related information source. Furthermore, if the user is relaxed, the reliability assurance unit can select a reliable information source that provides relaxing content. Furthermore, if the user is stressed, the reliability assurance unit can select a reliable information source that helps reduce stress. This allows the reliability assurance unit to select a reliable information source based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0168] When ensuring reliability, the reliability assurance unit can select the most appropriate information source by referring to the past reliability evaluations of the information source. For example, the reliability assurance unit preferentially selects information sources that have received high evaluations in the past. The reliability assurance unit can also select information sources that have received high reliability evaluations in the past. Furthermore, the reliability assurance unit can select information sources that have a high track record or evaluations in the past. In this way, the reliability assurance unit can select the most appropriate information source by referring to the past reliability evaluations of the information source.

[0169] The reliability assurance unit can customize the information source based on the current reliability evaluation of the information source when ensuring reliability. For example, the reliability assurance unit preferentially selects information sources with a high current reliability evaluation. The reliability assurance unit can also filter information sources with a low current reliability evaluation. Furthermore, the reliability assurance unit can adjust the selection criteria for the information source based on the current reliability evaluation. This allows the reliability assurance unit to customize the information source based on the current reliability evaluation of the information source.

[0170] When ensuring reliability, the reliability assurance unit can select the most appropriate information source by referring to the past reliability evaluations of the information source. For example, the reliability assurance unit preferentially selects information sources that have received high evaluations in the past. The reliability assurance unit can also select information sources that have received high reliability evaluations in the past. Furthermore, the reliability assurance unit can select information sources that have a high track record or evaluations in the past. In this way, the reliability assurance unit can select the most appropriate information source by referring to the past reliability evaluations of the information source.

[0171] The reliability assurance unit can estimate the user's emotions and prioritize reliable information sources based on the estimated user emotions. For example, if the user is excited, the reliability assurance unit can prioritize entertainment-related reliable information sources. Furthermore, if the user is relaxed, the reliability assurance unit can prioritize reliable information sources that provide relaxing content. Furthermore, if the user is stressed, the reliability assurance unit can prioritize reliable information sources that help reduce stress. This allows the reliability assurance unit to prioritize reliable information sources based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0172] When ensuring reliability, the reliability assurance unit can select the optimal information source taking into consideration the geographical distribution of information sources. For example, the reliability assurance unit selects a highly reliable information source in a region based on the user's current location. The reliability assurance unit can also preferentially select a highly reliable information source in a region that the user is interested in. Furthermore, the reliability assurance unit can select a highly reliable information source for each region and provide it in accordance with the user's interests. This allows the reliability assurance unit to select the optimal information source taking into consideration the geographical distribution of information sources.

[0173] When ensuring trustworthiness, the trustworthiness assurance unit can analyze the social media activity of the information source to evaluate its trustworthiness. The trustworthiness assurance unit can evaluate the trustworthiness of the information source based on, for example, the number of followers and engagement on social media. The trustworthiness assurance unit can also evaluate the trustworthiness of the information source based on the content and frequency of posts on social media. Furthermore, the trustworthiness assurance unit can evaluate the trustworthiness of the information source based on user ratings and comments on social media. In this way, the trustworthiness assurance unit can analyze the social media activity of the information source to evaluate its trustworthiness. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, selection unit, proposal unit, voting unit, analysis unit, provision unit, voting interface, voting result display unit, and reliability assurance unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects information from news sites and social networking sites via the communication I / F 44 of the smart device 14. The selection unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the collected information to select a topic. The proposal unit is realized by the control unit 46A of the smart device 14 and provides an interface through which participants can propose topics. The voting unit is realized by the control unit 46A of the smart device 14 and allows participants to vote on the proposed topics. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes participants' comments. The provision unit is realized by the specific processing unit 290 of the data processing device 12 and provides related information based on the analysis results. The voting interface is realized by the control unit 46A of the smart device 14 and allows participants to easily vote. The voting result display unit is realized by the control unit 46A of the smart device 14 and displays the voting results in real time. The reliability assurance unit is realized by the specific processing unit 290 of the data processing device 12 and collects data from reliable information sources. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, selection unit, proposal unit, voting unit, analysis unit, provision unit, voting interface, voting result display unit, and reliability assurance unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects information from news sites and social networking sites via the communication I / F 44 of the smart glasses 214. The selection unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the collected information to select a topic. The proposal unit is realized by the control unit 46A of the smart glasses 214 and provides an interface through which participants propose topics. The voting unit is realized by the control unit 46A of the smart glasses 214 and allows participants to vote on the proposed topics. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes participants' comments. The provision unit is realized by the specific processing unit 290 of the data processing device 12 and provides related information based on the analysis results. The voting interface is realized by the control unit 46A of the smart glasses 214 and allows participants to easily cast their votes. The voting result display unit is realized by the control unit 46A of the smart glasses 214, and displays the voting results in real time. The reliability assurance unit is realized by the specific processing unit 290 of the data processing device 12, and collects data from reliable information sources. === Hard Collateral 1-3 === Each of the multiple elements, including the collection unit, selection unit, proposal unit, voting unit, analysis unit, provision unit, voting interface, voting result display unit, and reliability assurance unit, is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the collection unit collects information from news sites and social networking sites via the communication I / F 44 of the headset type terminal 314. The selection unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the collected information to select a topic. The proposal unit is realized by the control unit 46A of the headset type terminal 314 and provides an interface through which participants propose topics. The voting unit is realized by the control unit 46A of the headset type terminal 314 and allows participants to vote on the proposed topics. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes participants' comments. The provision unit is realized by the specific processing unit 290 of the data processing device 12 and provides related information based on the analysis results. The voting interface is realized by the control unit 46A of the headset terminal 314, and allows participants to easily cast their votes. The voting result display unit is realized by the control unit 46A of the headset terminal 314, and displays the voting results in real time. The reliability assurance unit is realized by the specific processing unit 290 of the data processing device 12, and collects data from reliable information sources. === Hard Collateral 1-4 === Each of the multiple elements, including the collection unit, selection unit, proposal unit, voting unit, analysis unit, provision unit, voting interface, voting result display unit, and reliability assurance unit, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects information from news sites and social networking sites via the communication I / F 44 of the robot 414. The selection unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the collected information to select a topic. The proposal unit is realized by the control unit 46A of the robot 414 and provides an interface through which participants can propose topics. The voting unit is realized by the control unit 46A of the robot 414 and allows participants to vote on the proposed topics. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes participants' comments. The provision unit is realized by the specific processing unit 290 of the data processing device 12 and provides related information based on the analysis results. The voting interface is realized by the control unit 46A of the robot 414 and allows participants to easily cast their votes. The voting result display unit is realized by the control unit 46A of the robot 414, and displays the voting results in real time. The reliability assurance unit is realized by the specific processing unit 290 of the data processing device 12, and collects data from reliable information sources.

[0174] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0175] The discussion platform can further analyze the user's past discussion history and suggest themes based on topics that the user has shown interest in in the past. For example, it can analyze topics in which the user has made many comments in the past and discussions in which the user has participated for a long time and suggest related themes. It can also suggest related themes based on discussion themes that the user has given high ratings in the past. It can also analyze the content of discussions in which the user has participated in the past and suggest new themes that the user may be interested in. This makes it possible to suggest more personalized themes based on the user's past discussion history.

[0176] The voting interface can further analyze the user's voting behavior and customize voting options based on the user's voting trends. For example, it can prioritize options related to topics on which the user has frequently voted in the past. It can also suggest related voting options based on topics that the user has previously given high ratings. It can also analyze the user's voting history and suggest new voting options that may be of interest to the user. This provides more personalized voting options based on the user's voting behavior.

[0177] The voting result display unit can also analyze the user's reaction to the voting results and adjust the display method. For example, if the user has previously preferred visual display methods, it can prioritize displays using graphs and charts. Alternatively, if the user has preferred text-based displays, it can provide a text-based display. Furthermore, it can adjust the display method in real time based on the user's reaction. This makes it possible to display voting results according to the user's preferences.

[0178] The reliability assurance unit can also collect user feedback and reflect it in the reliability evaluation of the information source. For example, if a user gives a high rating to an information source, the reliability of that information source can be rated high. Conversely, if a user gives a low rating, the reliability of that information source can be rated low. Furthermore, user feedback can be collected periodically and the reliability evaluation can be updated. This makes it possible to select more reliable information sources based on user feedback.

[0179] The collection unit can further adjust the method of information collection by taking into account the user's device information. For example, if the user is using a smartphone, mobile-friendly information can be collected preferentially. Also, if the user is using a tablet, information optimized for large screens can be collected. Furthermore, if the user is using a smartwatch, concise and highly visible information can be collected. This makes it possible to collect optimal information based on the user's device information.

[0180] The selection unit can estimate the user's emotions and adjust the topic selection criteria based on the estimated user's emotions. For example, if the user is excited, entertainment or sports-related topics can be preferentially selected. Also, if the user is relaxed, relaxing content can be preferentially selected. Furthermore, if the user is stressed, topics that help relieve stress can be preferentially selected. In this way, the selection unit can adjust the topic selection criteria based on the user's emotions.

[0181] The suggestion unit can estimate the user's emotions and adjust the theme suggestion method based on the estimated user's emotions. For example, if the user is excited, a visually stimulating suggestion method can be provided. If the user is relaxed, a calm suggestion method can be provided. Furthermore, if the user is stressed, a simple and highly visible suggestion method can be provided. This allows the suggestion unit to adjust the theme suggestion method based on the user's emotions.

[0182] The voting unit can estimate the user's emotions and adjust the voting method based on the estimated user's emotions. For example, if the user is excited, a visually stimulating voting method is provided. The voting unit can also provide a calm voting method if the user is relaxed. Furthermore, if the user is stressed, a simple and highly visible voting method is also provided. This allows the voting unit to adjust the voting method based on the user's emotions.

[0183] The analysis unit can estimate the user's emotions and adjust the method of utterance analysis based on the estimated user emotions. For example, if the user is excited, the analysis can emphasize the emotional aspects of the utterance. The analysis unit can also analyze the content of the utterance in detail if the user is relaxed. Furthermore, if the user is feeling stressed, the analysis unit can identify and analyze the stress factors in the utterance. This allows the analysis unit to adjust the method of utterance analysis based on the user's emotions.

[0184] The providing unit can estimate the user's emotions and adjust the information provision method based on the estimated user's emotions. For example, if the user is excited, a visually stimulating information provision method is provided. Furthermore, if the user is relaxed, the providing unit can also provide a calming information provision method. Furthermore, if the user is feeling stressed, the providing unit can also provide a simple, highly visible information provision method. This allows the providing unit to adjust the information provision method based on the user's emotions.

[0185] The processing flow of the second embodiment will be briefly explained below.

[0186] Step 1: The collection unit collects information from news sites and social media. For example, it monitors the RSS feeds of news sites and collects information whenever a new article is published. It can also use social media APIs to collect posts related to specific hashtags or keywords. It can also use news aggregator services to collect and integrate the latest topics from multiple news sites. Step 2: The selection unit analyzes the collected information and selects topics. For example, text mining technology can be used to analyze the frequency of keywords in the collected information and select topics of high interest. Data mining technology can also be used to analyze the level of user interest and select topics. Furthermore, natural language processing technology can be used to analyze the content of the collected information and select topics. Step 3: The suggestion unit allows participants to suggest topics. For example, it provides an interface that allows users to freely input topics. It can also suggest related topics based on themes previously proposed by users. It can also customize the suggestions based on the user's current areas of interest. Step 4: The voting section allows users to vote on the proposed topic. For example, it provides an interface where users can vote by pressing a "Like" button. It also has a function to display the voting results in real time. It can also display the voting results as graphs or charts. Step 5: The analysis unit analyzes the participants' comments. For example, natural language processing technology can be used to analyze the content of the participants' comments. Sentiment analysis technology can also be used to analyze the emotional aspects of the participants' comments. Furthermore, the reliability of the comments can be evaluated, and highly reliable comments can be prioritized for analysis. Step 6: The providing unit provides related information based on the analysis results. For example, based on the analysis results, related news articles or research papers are provided. Based on the analysis results, related statistical data can also be provided. Furthermore, based on the analysis results, related references can also be provided.

[0187] 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.

[0188] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0189] 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.

[0190] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0191] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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).

[0197] 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.

[0198] 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.

[0199] 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.

[0200] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0201] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0207] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0208] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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).

[0213] 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.

[0214] 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.

[0215] 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.

[0216] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0217] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0223] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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.

[0228] 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).

[0229] 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.

[0230] 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.

[0231] 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.

[0232] 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.

[0233] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0234] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0235] 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.

[0236] 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.

[0237] 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.

[0238] 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.

[0239] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0240] 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.

[0241] 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.

[0242] 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.

[0243] 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).

[0244] 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.

[0245] 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."

[0246] 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.

[0247] 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.

[0248] 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.

[0249] 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.

[0250] 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.

[0251] 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.

[0252] 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.

[0253] 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.

[0254] 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.

[0255] 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.

[0256] 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.

[0257] 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.

[0258] [Explanation of symbols]

[0259] 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 collection department that collects information from news sites or social media, a selection unit that analyzes the information collected by the collection unit and selects a topic; A proposal section where participants propose themes, a voting section for voting on the proposed themes; an analysis unit that analyzes the participants' comments; a providing unit that provides related information based on the results of the analysis by the analyzing unit; Equipped with A system characterized by:

2. Provides a voting interface 2. The system of claim 1.

3. Equipped with a voting result display unit that displays the voting results 2. The system of claim 1.

4. Equipped with a reliability assurance department that collects data from reliable sources 2. The system of claim 1.

5. The collecting unit Gather information from news sites and social media 2. The system of claim 1.

6. The selection unit Analyze the collected information and select topics 2. The system of claim 1.

7. The proposal unit Participants propose themes 2. The system of claim 1.

8. The voting unit: Vote on the proposed topic 2. The system of claim 1.

9. The analysis unit Analyzing participants' comments 2. The system of claim 1.

10. The providing unit Providing relevant information based on analysis results 2. The system of claim 1.

Images