system

Abstract

The system according to this embodiment aims to improve effective communication skills through practice in debate and speech. [Solution] The system according to the embodiment comprises a debate unit, a judging unit, an advice unit, a speech analysis unit, an evaluation unit, and an expression advice unit. The debate unit performs debate practice. The judging unit judges the results of the debate performed by the debate unit. The advice unit provides advice on areas for improvement based on the results obtained by the judging unit. The speech analysis unit performs public speech practice. The evaluation unit performs an evaluation based on the speech content analyzed by the speech analysis unit. The expression advice unit provides advice based on the evaluation results obtained by the evaluation unit.

Description

Technical Field

[0006] , , ,

[0005] , , ,

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, it is difficult to effectively conduct debates or speech practice, and there are problems with presentation skills after becoming a working adult.

[0005] The system according to the embodiment aims to improve effective communication skills through debates or speech practice.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a debate unit, a judging unit, an advice unit, a speech analysis unit, an evaluation unit, and an expression advice unit. The debate unit performs debate practice. The judging unit judges the results of the debate performed by the debate unit. The advice unit provides advice on areas for improvement based on the results obtained by the judging unit. The speech analysis unit performs public speech practice. The evaluation unit performs an evaluation based on the speech content analyzed by the speech analysis unit. The expression advice unit provides advice based on the evaluation results obtained by the evaluation unit. [Effects of the Invention]

[0007] The system according to this embodiment can improve effective communication skills through practice in debate and speech. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9]This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F supervises communication between a plurality of 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), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

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

[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, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

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

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) An educational support application according to an embodiment of the present invention is a system that uses generative AI to practice debate and speech. This system comprises a debate unit that conducts debate practice, a judging unit that judges the results of the debate, an advice unit that provides advice on areas for improvement based on the judging results, a speech analysis unit that conducts public speech practice, an evaluation unit that evaluates the content of the speech, and an expression advice unit that provides advice based on the evaluation results. For example, when a user practices debate, the debate unit acts as an opponent and conducts the debate. The debate unit conducts debates on a variety of topics, from humorous to serious, and the judging unit analyzes the results of the debate and provides advice on areas for improvement and effective phrasing. This allows the user to improve their debate skills. Next, when a user practices public speech, the speech analysis unit analyzes the content of the speech, evaluates facial expressions, speaking style, and content, and the evaluation unit provides advice. This allows the user to improve their speech skills. Furthermore, the expression advice unit reads the emotions during the speech from facial expressions and voice and provides advice on speaking style and facial expressions. This allows users to practice in a more practical way. Finally, a combination of generative AI and speech recognition / speech synthesis systems enables interactive discussions. This allows users to practice debates and speeches in multiple languages, not only Japanese, but also English, Chinese, and others. As a result, the educational support app can efficiently practice debates and speeches and improve skills.

[0029] The educational support application according to this embodiment comprises a debate unit, a judging unit, an advice unit, a speech analysis unit, an evaluation unit, and an expression advice unit. The debate unit conducts debate practice. For example, when a user practices debating, the AI ​​acts as an opponent and conducts the debate. The debate unit can conduct debates on a variety of topics, from humorous to serious. For example, the debate unit can provide topics such as politics, economics, social issues, and entertainment. The judging unit judges the results of the debate conducted by the debate unit. For example, the judging unit analyzes the results of the debate and advises on areas for improvement and effective phrasing. The judging unit can evaluate the results of the debate based on evaluation items and scoring methods. The advice unit advises on areas for improvement based on the results obtained by the judging unit. For example, the advice unit provides advice based on the format of the feedback and the method of presenting areas for improvement. The speech analysis unit conducts public speech practice. The speech analysis unit analyzes the content of a speech when the user practices speaking, and evaluates aspects such as facial expressions, speaking style, and the content of the speech. The speech analysis unit can evaluate the speech based on the frequency and format of the speech practice. The evaluation unit performs an evaluation based on the speech content analyzed by the speech analysis unit. The evaluation unit evaluates the speech based on evaluation items and scoring methods, for example. The facial expression advice unit provides advice based on the evaluation results obtained by the evaluation unit. The facial expression advice unit provides advice based on areas for improvement in facial expressions and the format of the feedback, for example. As a result, the educational support application according to this embodiment can efficiently practice debate and speech and improve skills.

[0030] The Debate Club provides opportunities for debate practice. For example, when a user practices debating, the Debate Club uses AI as a partner. The Debate Club can conduct debates on a variety of topics, from humorous to serious. Specifically, the Debate Club uses AI to generate appropriate counterarguments and opinions for topics selected by the user, and conducts the debate through dialogue with the user. The AI ​​uses natural language processing technology to analyze the user's statements and offers counterarguments and questions at the appropriate time. For example, on political topics, the AI ​​offers opinions based on the latest news and statistical data, encouraging the user to think deeply. On economic topics, the AI ​​cites market trends and economic theories to offer logical counterarguments to the user. On social issues, the AI ​​provides opinions from diverse perspectives, encouraging the user to engage in a balanced discussion. On entertainment topics, the AI ​​offers opinions with humor, allowing the user to enjoy a relaxed debate. This allows the debate club to help users develop the skills to respond flexibly to a variety of topics. Furthermore, the debate club includes a function to record the progress of debates and the content of statements, allowing users to review them later, in order to support the improvement of their debate skills. This enables users to objectively evaluate their own debate performance and identify areas for improvement.

[0031] The judging panel evaluates the results of debates conducted by the debate team. For example, the judging panel analyzes the debate results and advises on areas for improvement and effective phrasing. Specifically, the judging panel uses AI to analyze the content of the debate and evaluate the logic, persuasiveness, and expressiveness of the user's statements. The AI ​​utilizes natural language processing technology to meticulously analyze the user's statements, identifying logical consistency and persuasive points. It also evaluates the tone, rhythm, and word choice of the user's statements and advises on effective phrasing and expression. For example, if a user makes a statement that lacks logical consistency, the judging panel will point this out and provide specific advice on how to construct the argument. It will also specifically indicate what data and examples should be cited and what words should be chosen to make a persuasive statement. Furthermore, the judging panel scores the debate results and quantitatively evaluates the degree of improvement in the user's skills. This allows users to understand the current state of their debate skills and identify specific areas for improvement. The judging panel plays a crucial role in ensuring that users steadily improve their skills through debate practice.

[0032] The Advice Department provides advice on areas for improvement based on the results obtained by the Judging Department. For example, the Advice Department provides advice based on the format of the feedback and the method of presenting areas for improvement. Specifically, the Advice Department provides individualized feedback to support the improvement of the user's debate skills. The AI ​​analyzes the user's statements and the progress of the debate, and suggests specific areas for improvement. For example, if a user makes a statement lacking logical consistency, the Advice Department will point this out and provide specific advice on how to construct the argument. It also specifically indicates what data and examples to cite and what words to choose in order to make a persuasive statement. Furthermore, the Advice Department evaluates the tone, rhythm, and word choice of the user's statements and advises on effective phrasing and expression. For example, if a user continues to speak in a monotonous tone, the Advice Department will point this out and provide specific advice on how to change the tone. This allows users to objectively evaluate their debate skills and identify specific areas for improvement. The Advice Department plays a crucial role in enabling users to steadily improve their skills through debate practice.

[0033] The Speech Analysis Department facilitates public speaking practice. For example, when a user practices a speech, the Speech Analysis Department analyzes the speech content, evaluating aspects such as facial expressions, speaking style, and the content itself. Specifically, the Speech Analysis Department uses AI to record and videotape the user's speech and analyzes the content in detail. The AI ​​uses speech recognition technology to transcribe the user's speech into text and evaluates its logical coherence and persuasiveness. It also uses facial recognition technology to analyze the user's facial expressions, evaluating emotional expression and eye movements during the speech. Furthermore, it uses speech analysis technology to analyze the user's speaking style, evaluating tone, rhythm, and clarity of pronunciation. For instance, if a user is nervous and their facial expression is stiff during a speech, the Speech Analysis Department will point this out and provide specific advice on how to relax. Similarly, if a user is speaking in a monotonous tone, the Speech Analysis Department will point this out and provide specific advice on how to change their tone. This allows users to objectively evaluate their own speech skills and identify specific areas for improvement. The Speech Analysis Department plays a crucial role in enabling users to steadily improve their skills through public speaking practice.

[0034] The evaluation department conducts evaluations based on the speech content analyzed by the speech analysis department. For example, the evaluation department evaluates speeches based on evaluation criteria and scoring methods. Specifically, the evaluation department uses AI to analyze the user's speech content in detail and scores it based on evaluation criteria such as logic, persuasiveness, and expressiveness. The AI ​​utilizes natural language processing technology to analyze the user's utterances, identifying logical consistency and persuasive points. It also evaluates the user's tone, rhythm, and word choice, scoring effective phrasing and expression. For example, if a user makes a statement lacking logical consistency, the evaluation department will point this out and provide specific advice on how to construct a more logical argument. Furthermore, it will specifically indicate what data and examples to cite and what words to choose to make a persuasive speech. In addition, the evaluation department has a function to record the user's speech progress and content, allowing for later review. This enables users to objectively evaluate their speech performance and identify areas for improvement. The evaluation department plays a crucial role in enabling users to steadily improve their skills through speech practice.

[0035] The facial expression advice unit provides advice based on the evaluation results obtained by the evaluation unit. For example, the facial expression advice unit provides advice based on areas for improvement in facial expressions and the format of feedback. Specifically, the facial expression advice unit uses AI to analyze the user's facial expressions in detail and evaluate emotional expression and eye movements during the speech. The AI ​​uses facial recognition technology to analyze the user's facial expressions and evaluate emotional expression and eye movements during the speech. For example, if the user is tense and their facial expression is stiff during the speech, the facial expression advice unit will point this out and provide specific advice on how to relax. Also, if the user's gaze is fixed in one place, the facial expression advice unit will point this out and provide specific advice on how to move their gaze. Furthermore, the facial expression advice unit can monitor changes in the user's facial expressions in real time and provide feedback at the appropriate time during the speech. This allows the user to objectively evaluate their own facial expressions and find specific areas for improvement. The facial expression advice unit plays an important role in enabling users to steadily improve their skills through speech practice.

[0036] The Debate Club allows users to debate on a variety of topics, from humorous to serious. For example, it offers topics in politics, economics, social issues, and entertainment. For instance, a humorous topic could be "What would happen if animals could talk?" A serious topic could be "The importance of climate change countermeasures." Furthermore, an entertainment-related topic could be "Reviews of the latest movies." This diverse range of topics allows users to broadly improve their debating skills.

[0037] The debate club can conduct debates in multiple languages, including not only Japanese but also English and Chinese. For example, the debate club can conduct debates in Japanese. It can also conduct debates in English. Furthermore, it can conduct debates in Chinese. This allows users to improve their language skills by debating in multiple languages. Some or all of the above processes in the debate club may be performed using, for example, a generative AI, or not. For example, the debate club can input a Japanese debate topic into a generative AI, which can then translate it into English or Chinese and conduct the debate.

[0038] The speech analysis unit can practice speeches in multiple languages. For example, it can practice speeches in Japanese. It can also practice speeches in English. Furthermore, it can practice speeches in Chinese. This allows users to improve their language skills by practicing speeches in multiple languages. Some or all of the above-described processes in the speech analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the speech analysis unit can input Japanese speech content into a generative AI, which can then translate it into English or Chinese for speech practice.

[0039] The Debate Club can provide optimal topics during debate practice by referring to the user's past debate history. For example, the Debate Club can re-present topics that the user has struggled with in the past to encourage them to overcome those difficulties. It can also provide topics that the user has excelled at in the past to build their confidence. Furthermore, the Debate Club can broaden the user's skill set by providing new topics that the user has never discussed before. In this way, referring to past debate history can promote the improvement of the user's skills. Some or all of the above processes in the Debate Club may be performed using, for example, a generative AI, or not. For example, the Debate Club can input the user's past debate history data into a generative AI, which can then provide optimal topics.

[0040] The debate club can customize debate topics based on the user's interests and concerns during practice sessions. For example, if a user is interested in sports, the debate club can provide sports-related topics. Similarly, if a user is interested in environmental issues, the debate club can provide topics related to environmental protection. Furthermore, if a user is interested in technology, the debate club can provide topics related to the latest technologies. This allows for increased motivation during practice by providing topics tailored to the user's interests. Some or all of the above processes in the debate club may be performed using, for example, a generative AI, or without one. For instance, the debate club can input user interest data into a generative AI, which can then customize the topics.

[0041] The Debate Club can provide users with highly relevant topics based on their geographical location during debate practice. For example, if a user lives in an urban area, the Debate Club can provide topics related to urban issues. If a user lives in a rural area, the Debate Club can also provide topics related to agriculture or the local economy. Furthermore, if a user lives abroad, the Debate Club can provide topics related to social issues in that country. By providing topics based on geographical location, it is possible to attract users' interest more easily. Some or all of the above processing in the Debate Club may be performed using, for example, a generative AI, or not using a generative AI. For example, the Debate Club can input the user's geographical location data into a generative AI, which can then provide highly relevant topics.

[0042] The Debate Club can analyze users' social media activity during debate practice and provide relevant topics. For example, the Debate Club can provide topics based on topics that users frequently mention on social media. It can also provide topics based on the interests of influencers that users follow. Furthermore, the Debate Club can provide topics based on the topics of online communities that users participate in. This makes it easier to attract users' interest by providing topics based on their social media activity. Some or all of the above processing in the Debate Club may be performed using, for example, generative AI, or not using generative AI. For example, the Debate Club can input user social media activity data into a generative AI, which can then provide relevant topics.

[0043] The judging panel can improve the accuracy of its judgments based on the interrelationships of the debate. For example, the judging panel can evaluate the quality of counterarguments in the debate. It can also evaluate the logical consistency in the debate. Furthermore, it can evaluate the method of presenting evidence in the debate. By considering the interrelationships of the debate, the accuracy of the judgments can be improved. Some or all of the above processes in the judging panel may be performed using, for example, a generative AI, or not using a generative AI. For example, the judging panel can input debate interrelationship data into a generative AI, which can then improve the accuracy of its judgments.

[0044] The judging panel can make judgments based on the attribute information of the debate participants. For example, the judging panel may adjust the judging criteria based on the participant's age. The judging panel may also adjust the judging criteria based on the participant's experience level. Furthermore, the judging panel may adjust the judging criteria based on the participant's expertise. This allows for more appropriate judgments by considering the participant's attribute information. Some or all of the above processing in the judging panel may be performed using, for example, a generative AI, or not using a generative AI. For example, the judging panel can input participant attribute information data into a generative AI, which can then adjust the judging criteria.

[0045] The judging panel can make judgments based on the geographical distribution of the debates. For example, the judging panel may consider the cultural background of each region when making judgments. The judging panel may also consider the social issues of each region when making judgments. Furthermore, the judging panel may also consider the linguistic characteristics of each region when making judgments. This allows for more appropriate judgments by considering the geographical distribution. Some or all of the above processing by the judging panel may be performed using, for example, a generative AI, or not using a generative AI. For example, the judging panel can input regional data into a generative AI, which can then adjust the judging criteria.

[0046] The judging unit can improve the accuracy of its judgments by referring to relevant literature on the debate topic. For example, the judging unit can refer to academic papers related to the debate topic. It can also refer to news articles related to the debate topic. Furthermore, it can refer to specialized books related to the debate topic. In this way, the accuracy of the judgments can be improved by referring to relevant literature. Some or all of the above processing in the judging unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the judging unit can input relevant literature data into a generative AI, which can then improve the accuracy of the judgments.

[0047] The advice unit can adjust the level of detail in its advice based on the importance of the debate. For example, it can provide detailed advice for important debates, basic advice for general debates, and concise advice for simple debates. This allows for more effective feedback by providing advice with a level of detail appropriate to the importance of the debate. Some or all of the above processing in the advice unit may be performed using, for example, a generative AI, or without one. For example, the advice unit can input debate importance data into a generative AI, which can then adjust the level of detail in the advice.

[0048] The advice unit can apply different advice algorithms depending on the debate category when providing advice. For example, in the case of a political debate, the advice unit provides logical advice. In the case of a debate on environmental issues, the advice unit can also provide emotional advice. Furthermore, in the case of a debate on technology, the advice unit can provide technical advice. This allows for more effective feedback by applying an advice algorithm appropriate to the debate category. Some or all of the above processing in the advice unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the advice unit can input debate category data into a generative AI, and the generative AI can apply different advice algorithms.

[0049] The advice unit can apply different advice algorithms depending on the debate category when providing advice. For example, in the case of a political debate, the advice unit provides logical advice. In the case of a debate on environmental issues, the advice unit can also provide emotional advice. Furthermore, in the case of a debate on technology, the advice unit can provide technical advice. This allows for more effective feedback by applying an advice algorithm appropriate to the debate category. Some or all of the above processing in the advice unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the advice unit can input debate category data into a generative AI, and the generative AI can apply different advice algorithms.

[0050] The advice unit can prioritize advice based on the submission date of the debate. For example, in the case of an urgent debate, the advice unit will provide advice with the highest priority. In the case of a regular debate, the advice unit can also provide advice with the usual priority. Furthermore, in the case of a future debate, the advice unit can postpone providing advice. This allows for more effective feedback by prioritizing advice based on the submission date. Some or all of the above processing in the advice unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the advice unit can input debate submission date data into a generative AI, and the generative AI can determine the priority of advice.

[0051] The advice unit can adjust the order of advice based on the relevance of the debate. For example, the advice unit can provide advice in order of importance. It can also provide advice in an order that is easy for the user to understand. Furthermore, the advice unit can provide advice based on the user's interests. This allows for more effective feedback by providing advice in an order based on relevance. Some or all of the above processing in the advice unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the advice unit can input debate relevance data into a generative AI, which can then adjust the order of advice.

[0052] The speech analysis unit can adjust the level of detail of its analysis based on the importance of the speech. For example, it can perform a detailed analysis for important speeches. It can also perform a basic analysis for general speeches. Furthermore, it can perform a concise analysis for simple speeches. This allows for more effective feedback by performing analysis with a level of detail appropriate to the importance of the speech. Some or all of the above processing in the speech analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the speech analysis unit can input speech importance data into a generative AI, which can then adjust the level of detail of the analysis.

[0053] The speech analysis unit can apply different analysis algorithms depending on the category of the speech during speech analysis. For example, the speech analysis unit can perform a logical analysis for speeches on politics. It can also perform an emotional analysis for speeches on environmental issues. Furthermore, it can perform a technical analysis for speeches on technology. By applying an analysis algorithm appropriate to the category of the speech, more effective feedback becomes possible. Some or all of the above processing in the speech analysis unit may be performed using, for example, generative AI, or without generative AI. For example, the speech analysis unit can input speech category data into a generative AI, which can then apply different analysis algorithms.

[0054] The speech analysis unit can prioritize speech analysis based on the submission date of each speech. For example, it can prioritize urgent speeches, while also prioritizing regular speeches. Furthermore, it can postpone the analysis of future speeches. This allows for more effective feedback by prioritizing analysis based on submission date. Some or all of the above processes in the speech analysis unit may be performed using, for example, a generative AI, or not. For example, the speech analysis unit can input speech submission date data into a generative AI, which can then determine the analysis priority.

[0055] The speech analysis unit can adjust the order of analysis based on the relevance of the speech during speech analysis. For example, the speech analysis unit can analyze in order from the most important points. It can also analyze in an order that is easy for the user to understand. Furthermore, the speech analysis unit can analyze based on the user's interests. This allows for more effective feedback by analyzing in an order based on relevance. Some or all of the above processing in the speech analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the speech analysis unit can input speech relevance data into a generative AI, and the generative AI can adjust the order of analysis.

[0056] The evaluation unit can improve the accuracy of its evaluation based on the interrelationships of the speeches during the evaluation process. For example, the evaluation unit can evaluate the quality of counterarguments within the speeches. It can also evaluate the logical consistency within the speeches. Furthermore, it can evaluate how evidence is presented within the speeches. By considering the interrelationships of the speeches, the accuracy of the evaluation can be improved. Some or all of the above processing in the evaluation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the evaluation unit can input speech interrelationship data into a generative AI, which can then improve the accuracy of the evaluation.

[0057] The evaluation unit can perform evaluations based on the attribute information of the speech participants. For example, the evaluation unit can adjust the evaluation criteria based on the participant's age. It can also adjust the evaluation criteria based on the participant's experience level. Furthermore, it can adjust the evaluation criteria based on the participant's expertise. This allows for more appropriate evaluations by considering the participant's attribute information. Some or all of the above processing in the evaluation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the evaluation unit can input participant attribute information data into a generative AI, which can then adjust the evaluation criteria.

[0058] The evaluation unit can perform evaluations based on the geographical distribution of speeches. For example, the evaluation unit can consider the cultural background of each region when performing evaluations. It can also consider the social issues of each region when performing evaluations. Furthermore, the evaluation unit can consider the linguistic characteristics of each region when performing evaluations. This allows for more appropriate evaluations by considering geographical distribution. Some or all of the above processing in the evaluation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the evaluation unit can input regional data into a generative AI, and the generative AI can adjust the evaluation criteria.

[0059] The evaluation unit can improve the accuracy of its evaluation by referring to relevant literature on the speech during the evaluation process. For example, the evaluation unit may refer to academic papers related to the topic of the speech. It may also refer to news articles related to the topic of the speech. Furthermore, it may refer to specialized books related to the topic of the speech. In this way, the accuracy of the evaluation can be improved by referring to relevant literature. Some or all of the above processing in the evaluation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the evaluation unit may input the relevant literature data into a generative AI, which can then improve the accuracy of the evaluation.

[0060] The facial expression advice unit can adjust the level of detail in its advice based on the importance of the speech. For example, it provides detailed facial expression advice for important speeches. It can also provide basic facial expression advice for general speeches. Furthermore, it can provide concise facial expression advice for simple speeches. This allows for more effective feedback by providing facial expression advice with a level of detail appropriate to the importance of the speech. Some or all of the above processing in the facial expression advice unit may be performed using, for example, a generative AI, or without a generative AI. For example, the facial expression advice unit can input speech importance data into a generative AI, which can then adjust the level of detail in its advice.

[0061] The facial expression advice unit can apply different advice algorithms depending on the category of the speech when providing facial expression advice. For example, in the case of a political speech, the facial expression advice unit can provide advice on creating a serious facial expression. In the case of a speech on environmental issues, it can also provide advice on creating an emotional facial expression. Furthermore, in the case of a speech on technology, it can provide advice on creating a technical facial expression. This allows for more effective feedback by applying an advice algorithm appropriate to the category of the speech. Some or all of the above processing in the facial expression advice unit may be performed using, for example, a generative AI, or without a generative AI. For example, the facial expression advice unit can input speech category data into a generative AI, which can then apply different advice algorithms.

[0062] The facial expression advice unit can prioritize advice based on the speech submission date. For example, in the case of an urgent speech, the facial expression advice unit will provide facial expression advice with the highest priority. In the case of a regular speech, the facial expression advice unit can also provide facial expression advice with the usual priority. Furthermore, in the case of a future speech, the facial expression advice unit can postpone providing facial expression advice. This allows for more effective feedback by providing facial expression advice with priority based on the submission date. Some or all of the above processing in the facial expression advice unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the facial expression advice unit can input speech submission date data into a generative AI, and the generative AI can determine the priority of advice.

[0063] The facial expression advice unit can adjust the order of advice based on the relevance of the speech when providing facial expression advice. For example, the facial expression advice unit can provide facial expression advice in order of importance. It can also provide facial expression advice in an order that is easy for the user to understand. Furthermore, the facial expression advice unit can provide facial expression advice based on the user's interests. This allows for more effective feedback by providing facial expression advice in an order based on relevance. Some or all of the above processing in the facial expression advice unit may be performed using, for example, a generative AI, or without a generative AI. For example, the facial expression advice unit can input speech relevance data into a generative AI, which can then adjust the order of advice.

[0064] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0065] The debate club can refer to a user's past debate history and provide topics designed to promote their growth. For example, it can revisit topics the user previously struggled with to encourage them to overcome their weaknesses. It can also provide topics the user excelled at to build their confidence. Furthermore, it can offer new topics the user has never discussed before to broaden their skill set. By providing topics that promote user growth, debate practice becomes more effective.

[0066] The judging panel can improve the accuracy of its judgments based on the interrelationships of the debate. For example, it can evaluate the quality of counterarguments within the debate, the consistency of logic within the debate, and the method of presenting evidence within the debate. By considering the interrelationships of the debate, the accuracy of the judging can be improved.

[0067] The debate club can customize topics based on users' interests. For example, if a user is interested in sports, they can be offered sports-related topics. Similarly, if a user is interested in environmental issues, they can be offered topics related to environmental protection. Furthermore, if a user is interested in technology, they can be offered topics related to the latest technologies. This allows the club to increase users' motivation for practice by providing topics tailored to their interests.

[0068] The speech analysis department can apply different analysis algorithms depending on the category of the speech. For example, a speech on politics can be analyzed logically. A speech on environmental issues can be analyzed emotionally. Furthermore, a speech on technology can be analyzed technically. By applying an analysis algorithm appropriate to the category of the speech, more effective feedback can be provided.

[0069] The debate club can provide users with highly relevant topics based on their geographical location. For example, if a user lives in an urban area, it can offer topics related to urban issues. If a user lives in a rural area, it can offer topics related to agriculture or the local economy. Furthermore, if a user lives abroad, it can offer topics related to social issues in that country. By providing topics based on geographical location, it is possible to attract users' interest more easily.

[0070] The following briefly describes the processing flow for example form 1.

[0071] Step 1: The Debate Club conducts debate practice. When users practice debating, an AI acts as their opponent. The Debate Club can conduct debates on a variety of topics, from humorous to serious. For example, it offers topics such as politics, economics, social issues, and entertainment. Step 2: The judging panel evaluates the results of the debate conducted by the debate team. They analyze the debate results and provide advice on areas for improvement and effective phrasing. They evaluate the debate results based on evaluation criteria and scoring methods. Step 3: The Advice Department provides advice on areas for improvement based on the results obtained by the Judging Department. The advice is given based on the format of the feedback and the method of presenting areas for improvement. Step 4: The speech analysis department conducts public speaking practice. As the user practices their speech, the department analyzes the content of the speech and evaluates aspects such as facial expressions, speaking style, and the content of the speech. The speech is evaluated based on the frequency and format of the speech practice. Step 5: The evaluation department conducts an evaluation based on the speech content analyzed by the speech analysis department. The speech is evaluated based on evaluation items and scoring methods. Step 6: The facial expression advice unit provides advice based on the evaluation results obtained by the evaluation unit. The advice is given based on areas for improvement in facial expressions and the format of the feedback.

[0072] (Example of form 2) An educational support application according to an embodiment of the present invention is a system that uses generative AI to practice debate and speech. This system comprises a debate unit that conducts debate practice, a judging unit that judges the results of the debate, an advice unit that provides advice on areas for improvement based on the judging results, a speech analysis unit that conducts public speech practice, an evaluation unit that evaluates the content of the speech, and an expression advice unit that provides advice based on the evaluation results. For example, when a user practices debate, the debate unit acts as an opponent and conducts the debate. The debate unit conducts debates on a variety of topics, from humorous to serious, and the judging unit analyzes the results of the debate and provides advice on areas for improvement and effective phrasing. This allows the user to improve their debate skills. Next, when a user practices public speech, the speech analysis unit analyzes the content of the speech, evaluates facial expressions, speaking style, and content, and the evaluation unit provides advice. This allows the user to improve their speech skills. Furthermore, the expression advice unit reads the emotions during the speech from facial expressions and voice and provides advice on speaking style and facial expressions. This allows users to practice in a more practical way. Finally, a combination of generative AI and speech recognition / speech synthesis systems enables interactive discussions. This allows users to practice debates and speeches in multiple languages, not only Japanese, but also English, Chinese, and others. As a result, the educational support app can efficiently practice debates and speeches and improve skills.

[0073] The educational support application according to this embodiment comprises a debate unit, a judging unit, an advice unit, a speech analysis unit, an evaluation unit, and an expression advice unit. The debate unit conducts debate practice. For example, when a user practices debating, the AI ​​acts as an opponent and conducts the debate. The debate unit can conduct debates on a variety of topics, from humorous to serious. For example, the debate unit can provide topics such as politics, economics, social issues, and entertainment. The judging unit judges the results of the debate conducted by the debate unit. For example, the judging unit analyzes the results of the debate and advises on areas for improvement and effective phrasing. The judging unit can evaluate the results of the debate based on evaluation items and scoring methods. The advice unit advises on areas for improvement based on the results obtained by the judging unit. For example, the advice unit provides advice based on the format of the feedback and the method of presenting areas for improvement. The speech analysis unit conducts public speech practice. The speech analysis unit analyzes the content of a speech when the user practices speaking, and evaluates aspects such as facial expressions, speaking style, and the content of the speech. The speech analysis unit can evaluate the speech based on the frequency and format of the speech practice. The evaluation unit performs an evaluation based on the speech content analyzed by the speech analysis unit. The evaluation unit evaluates the speech based on evaluation items and scoring methods, for example. The facial expression advice unit provides advice based on the evaluation results obtained by the evaluation unit. The facial expression advice unit provides advice based on areas for improvement in facial expressions and the format of the feedback, for example. As a result, the educational support application according to this embodiment can efficiently practice debate and speech and improve skills.

[0074] The Debate Club provides opportunities for debate practice. For example, when a user practices debating, the Debate Club uses AI as a partner. The Debate Club can conduct debates on a variety of topics, from humorous to serious. Specifically, the Debate Club uses AI to generate appropriate counterarguments and opinions for topics selected by the user, and conducts the debate through dialogue with the user. The AI ​​uses natural language processing technology to analyze the user's statements and offers counterarguments and questions at the appropriate time. For example, on political topics, the AI ​​offers opinions based on the latest news and statistical data, encouraging the user to think deeply. On economic topics, the AI ​​cites market trends and economic theories to offer logical counterarguments to the user. On social issues, the AI ​​provides opinions from diverse perspectives, encouraging the user to engage in a balanced discussion. On entertainment topics, the AI ​​offers opinions with humor, allowing the user to enjoy a relaxed debate. This allows the debate club to help users develop the skills to respond flexibly to a variety of topics. Furthermore, the debate club includes a function to record the progress of debates and the content of statements, allowing users to review them later, in order to support the improvement of their debate skills. This enables users to objectively evaluate their own debate performance and identify areas for improvement.

[0075] The judging panel evaluates the results of debates conducted by the debate team. For example, the judging panel analyzes the debate results and advises on areas for improvement and effective phrasing. Specifically, the judging panel uses AI to analyze the content of the debate and evaluate the logic, persuasiveness, and expressiveness of the user's statements. The AI ​​utilizes natural language processing technology to meticulously analyze the user's statements, identifying logical consistency and persuasive points. It also evaluates the tone, rhythm, and word choice of the user's statements and advises on effective phrasing and expression. For example, if a user makes a statement that lacks logical consistency, the judging panel will point this out and provide specific advice on how to construct the argument. It will also specifically indicate what data and examples should be cited and what words should be chosen to make a persuasive statement. Furthermore, the judging panel scores the debate results and quantitatively evaluates the degree of improvement in the user's skills. This allows users to understand the current state of their debate skills and identify specific areas for improvement. The judging panel plays a crucial role in ensuring that users steadily improve their skills through debate practice.

[0076] The Advice Department provides advice on areas for improvement based on the results obtained by the Judging Department. For example, the Advice Department provides advice based on the format of the feedback and the method of presenting areas for improvement. Specifically, the Advice Department provides individualized feedback to support the improvement of the user's debate skills. The AI ​​analyzes the user's statements and the progress of the debate, and suggests specific areas for improvement. For example, if a user makes a statement lacking logical consistency, the Advice Department will point this out and provide specific advice on how to construct the argument. It also specifically indicates what data and examples to cite and what words to choose in order to make a persuasive statement. Furthermore, the Advice Department evaluates the tone, rhythm, and word choice of the user's statements and advises on effective phrasing and expression. For example, if a user continues to speak in a monotonous tone, the Advice Department will point this out and provide specific advice on how to change the tone. This allows users to objectively evaluate their debate skills and identify specific areas for improvement. The Advice Department plays a crucial role in enabling users to steadily improve their skills through debate practice.

[0077] The Speech Analysis Department facilitates public speaking practice. For example, when a user practices a speech, the Speech Analysis Department analyzes the speech content, evaluating aspects such as facial expressions, speaking style, and the content itself. Specifically, the Speech Analysis Department uses AI to record and videotape the user's speech and analyzes the content in detail. The AI ​​uses speech recognition technology to transcribe the user's speech into text and evaluates its logical coherence and persuasiveness. It also uses facial recognition technology to analyze the user's facial expressions, evaluating emotional expression and eye movements during the speech. Furthermore, it uses speech analysis technology to analyze the user's speaking style, evaluating tone, rhythm, and clarity of pronunciation. For instance, if a user is nervous and their facial expression is stiff during a speech, the Speech Analysis Department will point this out and provide specific advice on how to relax. Similarly, if a user is speaking in a monotonous tone, the Speech Analysis Department will point this out and provide specific advice on how to change their tone. This allows users to objectively evaluate their own speech skills and identify specific areas for improvement. The Speech Analysis Department plays a crucial role in enabling users to steadily improve their skills through public speaking practice.

[0078] The evaluation department conducts evaluations based on the speech content analyzed by the speech analysis department. For example, the evaluation department evaluates speeches based on evaluation criteria and scoring methods. Specifically, the evaluation department uses AI to analyze the user's speech content in detail and scores it based on evaluation criteria such as logic, persuasiveness, and expressiveness. The AI ​​utilizes natural language processing technology to analyze the user's utterances, identifying logical consistency and persuasive points. It also evaluates the user's tone, rhythm, and word choice, scoring effective phrasing and expression. For example, if a user makes a statement lacking logical consistency, the evaluation department will point this out and provide specific advice on how to construct a more logical argument. Furthermore, it will specifically indicate what data and examples to cite and what words to choose to make a persuasive speech. In addition, the evaluation department has a function to record the user's speech progress and content, allowing for later review. This enables users to objectively evaluate their speech performance and identify areas for improvement. The evaluation department plays a crucial role in enabling users to steadily improve their skills through speech practice.

[0079] The facial expression advice unit provides advice based on the evaluation results obtained by the evaluation unit. For example, the facial expression advice unit provides advice based on areas for improvement in facial expressions and the format of feedback. Specifically, the facial expression advice unit uses AI to analyze the user's facial expressions in detail and evaluate emotional expression and eye movements during the speech. The AI ​​uses facial recognition technology to analyze the user's facial expressions and evaluate emotional expression and eye movements during the speech. For example, if the user is tense and their facial expression is stiff during the speech, the facial expression advice unit will point this out and provide specific advice on how to relax. Also, if the user's gaze is fixed in one place, the facial expression advice unit will point this out and provide specific advice on how to move their gaze. Furthermore, the facial expression advice unit can monitor changes in the user's facial expressions in real time and provide feedback at the appropriate time during the speech. This allows the user to objectively evaluate their own facial expressions and find specific areas for improvement. The facial expression advice unit plays an important role in enabling users to steadily improve their skills through speech practice.

[0080] The Debate Club allows users to debate on a variety of topics, from humorous to serious. For example, it offers topics in politics, economics, social issues, and entertainment. For instance, a humorous topic could be "What would happen if animals could talk?" A serious topic could be "The importance of climate change countermeasures." Furthermore, an entertainment-related topic could be "Reviews of the latest movies." This diverse range of topics allows users to broadly improve their debating skills.

[0081] The debate club can conduct debates in multiple languages, including not only Japanese but also English and Chinese. For example, the debate club can conduct debates in Japanese. It can also conduct debates in English. Furthermore, it can conduct debates in Chinese. This allows users to improve their language skills by debating in multiple languages. Some or all of the above processes in the debate club may be performed using, for example, a generative AI, or not. For example, the debate club can input a Japanese debate topic into a generative AI, which can then translate it into English or Chinese and conduct the debate.

[0082] The speech analysis unit can practice speeches in multiple languages. For example, it can practice speeches in Japanese. It can also practice speeches in English. Furthermore, it can practice speeches in Chinese. This allows users to improve their language skills by practicing speeches in multiple languages. Some or all of the above-described processes in the speech analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the speech analysis unit can input Japanese speech content into a generative AI, which can then translate it into English or Chinese for speech practice.

[0083] The debate function can estimate the user's emotions and select a debate topic based on those emotions. For example, if the user is relaxed, the debate function might select a topic that includes light humor. If the user is nervous, the debate function might select a simple and easy-to-understand topic. Furthermore, if the user is excited, the debate function might select a challenging and profound topic. This allows for more effective debate practice by selecting topics that match the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the debate function may be performed using a generative AI, or not. For example, the debate function can input the user's facial expression data into a generative AI, which can then estimate the emotions and select a topic.

[0084] The Debate Club can provide optimal topics during debate practice by referring to the user's past debate history. For example, the Debate Club can re-present topics that the user has struggled with in the past to encourage them to overcome those difficulties. It can also provide topics that the user has excelled at in the past to build their confidence. Furthermore, the Debate Club can broaden the user's skill set by providing new topics that the user has never discussed before. In this way, referring to past debate history can promote the improvement of the user's skills. Some or all of the above processes in the Debate Club may be performed using, for example, a generative AI, or not. For example, the Debate Club can input the user's past debate history data into a generative AI, which can then provide optimal topics.

[0085] The debate club can customize debate topics based on the user's interests and concerns during practice sessions. For example, if a user is interested in sports, the debate club can provide sports-related topics. Similarly, if a user is interested in environmental issues, the debate club can provide topics related to environmental protection. Furthermore, if a user is interested in technology, the debate club can provide topics related to the latest technologies. This allows for increased motivation during practice by providing topics tailored to the user's interests. Some or all of the above processes in the debate club may be performed using, for example, a generative AI, or without one. For instance, the debate club can input user interest data into a generative AI, which can then customize the topics.

[0086] The debate unit can estimate the user's emotions and adjust the pace of the debate based on those emotions. For example, if the user is nervous, the debate unit will conduct the debate at a slow pace. If the user is relaxed, the debate unit can conduct the debate at a normal pace. Furthermore, if the user is excited, the debate unit can conduct the debate at a fast pace. This allows for more effective practice by conducting the debate at a pace that matches the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the debate unit may be performed using a generative AI, or not. For example, the debate unit can input the user's facial expression data into a generative AI, which can then estimate the emotions and adjust the pace.

[0087] The Debate Club can provide users with highly relevant topics based on their geographical location during debate practice. For example, if a user lives in an urban area, the Debate Club can provide topics related to urban issues. If a user lives in a rural area, the Debate Club can also provide topics related to agriculture or the local economy. Furthermore, if a user lives abroad, the Debate Club can provide topics related to social issues in that country. By providing topics based on geographical location, it is possible to attract users' interest more easily. Some or all of the above processing in the Debate Club may be performed using, for example, a generative AI, or not using a generative AI. For example, the Debate Club can input the user's geographical location data into a generative AI, which can then provide highly relevant topics.

[0088] The Debate Club can analyze users' social media activity during debate practice and provide relevant topics. For example, the Debate Club can provide topics based on topics that users frequently mention on social media. It can also provide topics based on the interests of influencers that users follow. Furthermore, the Debate Club can provide topics based on the topics of online communities that users participate in. This makes it easier to attract users' interest by providing topics based on their social media activity. Some or all of the above processing in the Debate Club may be performed using, for example, generative AI, or not using generative AI. For example, the Debate Club can input user social media activity data into a generative AI, which can then provide relevant topics.

[0089] The judging unit can estimate the user's emotions and adjust the judgment criteria based on the estimated emotions. For example, if the user is tense, the judging unit can make a judgment using lenient criteria. If the user is relaxed, the judging unit can make a judgment using normal criteria. Furthermore, if the user is excited, the judging unit can make a judgment using strict criteria. This allows for more appropriate feedback by making judgments based on criteria that match the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the judging unit may be performed using a generative AI, or not using a generative AI. For example, the judging unit can input user facial expression data into a generative AI, which can estimate emotions and adjust the judgment criteria.

[0090] The judging panel can improve the accuracy of its judgments based on the interrelationships of the debate. For example, the judging panel can evaluate the quality of counterarguments in the debate. It can also evaluate the logical consistency in the debate. Furthermore, it can evaluate the method of presenting evidence in the debate. By considering the interrelationships of the debate, the accuracy of the judgments can be improved. Some or all of the above processes in the judging panel may be performed using, for example, a generative AI, or not using a generative AI. For example, the judging panel can input debate interrelationship data into a generative AI, which can then improve the accuracy of its judgments.

[0091] The judging panel can make judgments based on the attribute information of the debate participants. For example, the judging panel may adjust the judging criteria based on the participant's age. The judging panel may also adjust the judging criteria based on the participant's experience level. Furthermore, the judging panel may adjust the judging criteria based on the participant's expertise. This allows for more appropriate judgments by considering the participant's attribute information. Some or all of the above processing in the judging panel may be performed using, for example, a generative AI, or not using a generative AI. For example, the judging panel can input participant attribute information data into a generative AI, which can then adjust the judging criteria.

[0092] The judging unit can estimate the user's emotions and adjust the order in which the judgment results are displayed based on the estimated emotions. For example, if the user is nervous, the judging unit will display the most positive feedback first. If the user is relaxed, the judging unit can also display the feedback in the normal order. Furthermore, if the user is excited, the judging unit can also display the most important feedback first. This allows for more effective feedback by displaying results in an order that corresponds to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the judging unit may be performed using a generative AI, or not using a generative AI. For example, the judging unit can input the user's facial expression data into a generative AI, which can estimate emotions and adjust the order in which the results are displayed.

[0093] The judging panel can make judgments based on the geographical distribution of the debates. For example, the judging panel may consider the cultural background of each region when making judgments. The judging panel may also consider the social issues of each region when making judgments. Furthermore, the judging panel may also consider the linguistic characteristics of each region when making judgments. This allows for more appropriate judgments by considering the geographical distribution. Some or all of the above processing by the judging panel may be performed using, for example, a generative AI, or not using a generative AI. For example, the judging panel can input regional data into a generative AI, which can then adjust the judging criteria.

[0094] The judging unit can improve the accuracy of its judgments by referring to relevant literature on the debate topic. For example, the judging unit can refer to academic papers related to the debate topic. It can also refer to news articles related to the debate topic. Furthermore, it can refer to specialized books related to the debate topic. In this way, the accuracy of the judgments can be improved by referring to relevant literature. Some or all of the above processing in the judging unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the judging unit can input relevant literature data into a generative AI, which can then improve the accuracy of the judgments.

[0095] The advice unit can estimate the user's emotions and adjust the way it expresses advice based on those emotions. For example, if the user is nervous, the advice unit will give advice in gentle words. If the user is relaxed, the advice unit can also give detailed advice. Furthermore, if the user is excited, the advice unit can provide advice that includes words of encouragement. This allows for more effective feedback by providing advice in a way that matches the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the advice unit may be performed using a generative AI, or not using a generative AI. For example, the advice unit can input user facial expression data into a generative AI, which can estimate emotions and adjust the way it expresses advice.

[0096] The advice unit can adjust the level of detail in its advice based on the importance of the debate. For example, it can provide detailed advice for important debates, basic advice for general debates, and concise advice for simple debates. This allows for more effective feedback by providing advice with a level of detail appropriate to the importance of the debate. Some or all of the above processing in the advice unit may be performed using, for example, a generative AI, or without one. For example, the advice unit can input debate importance data into a generative AI, which can then adjust the level of detail in the advice.

[0097] The advice unit can apply different advice algorithms depending on the debate category when providing advice. For example, in the case of a political debate, the advice unit provides logical advice. In the case of a debate on environmental issues, the advice unit can also provide emotional advice. Furthermore, in the case of a debate on technology, the advice unit can provide technical advice. This allows for more effective feedback by applying an advice algorithm appropriate to the debate category. Some or all of the above processing in the advice unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the advice unit can input debate category data into a generative AI, and the generative AI can apply different advice algorithms.

[0098] The advice unit can apply different advice algorithms depending on the debate category when providing advice. For example, in the case of a political debate, the advice unit provides logical advice. In the case of a debate on environmental issues, the advice unit can also provide emotional advice. Furthermore, in the case of a debate on technology, the advice unit can provide technical advice. This allows for more effective feedback by applying an advice algorithm appropriate to the debate category. Some or all of the above processing in the advice unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the advice unit can input debate category data into a generative AI, and the generative AI can apply different advice algorithms.

[0099] The advice unit can estimate the user's emotions and adjust the length of the advice based on the estimated emotions. For example, if the user is nervous, the advice unit can provide short, concise advice. If the user is relaxed, the advice unit can provide more detailed advice. Furthermore, if the user is excited, the advice unit can provide longer advice, including words of encouragement. This allows for more effective feedback by providing advice of a length appropriate to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the advice unit may be performed using or without a generative AI. For example, the advice unit can input user facial expression data into a generative AI, which can then estimate the emotions and adjust the length of the advice.

[0100] The advice unit can prioritize advice based on the submission date of the debate. For example, in the case of an urgent debate, the advice unit will provide advice with the highest priority. In the case of a regular debate, the advice unit can also provide advice with the usual priority. Furthermore, in the case of a future debate, the advice unit can postpone providing advice. This allows for more effective feedback by prioritizing advice based on the submission date. Some or all of the above processing in the advice unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the advice unit can input debate submission date data into a generative AI, and the generative AI can determine the priority of advice.

[0101] The advice unit can adjust the order of advice based on the relevance of the debate. For example, the advice unit can provide advice in order of importance. It can also provide advice in an order that is easy for the user to understand. Furthermore, the advice unit can provide advice based on the user's interests. This allows for more effective feedback by providing advice in an order based on relevance. Some or all of the above processing in the advice unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the advice unit can input debate relevance data into a generative AI, which can then adjust the order of advice.

[0102] The speech analysis unit can estimate the user's emotions and adjust the speech analysis method based on the estimated emotions. For example, if the user is nervous, the speech analysis unit can provide gentle feedback. If the user is relaxed, the speech analysis unit can also provide detailed feedback. Furthermore, if the user is excited, the speech analysis unit can provide feedback that includes words of encouragement. This allows for more effective feedback by analyzing the speech in a way that suits the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the speech analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the speech analysis unit can input user facial expression data into a generative AI, which can then estimate emotions and adjust the speech analysis method.

[0103] The speech analysis unit can adjust the level of detail of its analysis based on the importance of the speech. For example, it can perform a detailed analysis for important speeches. It can also perform a basic analysis for general speeches. Furthermore, it can perform a concise analysis for simple speeches. This allows for more effective feedback by performing analysis with a level of detail appropriate to the importance of the speech. Some or all of the above processing in the speech analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the speech analysis unit can input speech importance data into a generative AI, which can then adjust the level of detail of the analysis.

[0104] The speech analysis unit can apply different analysis algorithms depending on the category of the speech during speech analysis. For example, the speech analysis unit can perform a logical analysis for speeches on politics. It can also perform an emotional analysis for speeches on environmental issues. Furthermore, it can perform a technical analysis for speeches on technology. By applying an analysis algorithm appropriate to the category of the speech, more effective feedback becomes possible. Some or all of the above processing in the speech analysis unit may be performed using, for example, generative AI, or without generative AI. For example, the speech analysis unit can input speech category data into a generative AI, which can then apply different analysis algorithms.

[0105] The speech analysis unit can estimate the user's emotions and adjust the order in which the speech analysis results are displayed based on the estimated emotions. For example, if the user is nervous, the speech analysis unit can display the most positive feedback first. If the user is relaxed, the speech analysis unit can also display the feedback in the normal order. Furthermore, if the user is excited, the speech analysis unit can also display the most important feedback first. This allows for more effective feedback by displaying results in an order that corresponds to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the speech analysis unit may be performed using a generative AI, or not using a generative AI. For example, the speech analysis unit can input the user's facial expression data into a generative AI, which can estimate emotions and adjust the display order of the results.

[0106] The speech analysis unit can prioritize speech analysis based on the submission date of each speech. For example, it can prioritize urgent speeches, while also prioritizing regular speeches. Furthermore, it can postpone the analysis of future speeches. This allows for more effective feedback by prioritizing analysis based on submission date. Some or all of the above processes in the speech analysis unit may be performed using, for example, a generative AI, or not. For example, the speech analysis unit can input speech submission date data into a generative AI, which can then determine the analysis priority.

[0107] The speech analysis unit can adjust the order of analysis based on the relevance of the speech during speech analysis. For example, the speech analysis unit can analyze in order from the most important points. It can also analyze in an order that is easy for the user to understand. Furthermore, the speech analysis unit can analyze based on the user's interests. This allows for more effective feedback by analyzing in an order based on relevance. Some or all of the above processing in the speech analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the speech analysis unit can input speech relevance data into a generative AI, and the generative AI can adjust the order of analysis.

[0108] The evaluation unit can estimate the user's emotions and adjust the evaluation criteria based on the estimated emotions. For example, if the user is tense, the evaluation unit can evaluate using lenient criteria. It can also evaluate using normal criteria if the user is relaxed. Furthermore, if the user is excited, the evaluation unit can evaluate using strict criteria. This allows for more appropriate feedback by evaluating according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the evaluation unit may be performed using or without a generative AI. For example, the evaluation unit can input user facial expression data into a generative AI, which can then estimate emotions and adjust the evaluation criteria.

[0109] The evaluation unit can improve the accuracy of its evaluation based on the interrelationships of the speeches during the evaluation process. For example, the evaluation unit can evaluate the quality of counterarguments within the speeches. It can also evaluate the logical consistency within the speeches. Furthermore, it can evaluate how evidence is presented within the speeches. By considering the interrelationships of the speeches, the accuracy of the evaluation can be improved. Some or all of the above processing in the evaluation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the evaluation unit can input speech interrelationship data into a generative AI, which can then improve the accuracy of the evaluation.

[0110] The evaluation unit can perform evaluations based on the attribute information of the speech participants. For example, the evaluation unit can adjust the evaluation criteria based on the participant's age. It can also adjust the evaluation criteria based on the participant's experience level. Furthermore, it can adjust the evaluation criteria based on the participant's expertise. This allows for more appropriate evaluations by considering the participant's attribute information. Some or all of the above processing in the evaluation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the evaluation unit can input participant attribute information data into a generative AI, which can then adjust the evaluation criteria.

[0111] The evaluation unit can estimate the user's emotions and adjust the order in which the evaluation results are displayed based on the estimated emotions. For example, if the user is nervous, the evaluation unit can display the most positive feedback first. If the user is relaxed, the evaluation unit can also display the feedback in the normal order. Furthermore, if the user is excited, the evaluation unit can also display the most important feedback first. This allows for more effective feedback by displaying results in an order that corresponds to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the evaluation unit may be performed using a generative AI, or not using a generative AI. For example, the evaluation unit can input the user's facial expression data into a generative AI, which can then estimate emotions and adjust the order in which the results are displayed.

[0112] The evaluation unit can perform evaluations based on the geographical distribution of speeches. For example, the evaluation unit can consider the cultural background of each region when performing evaluations. It can also consider the social issues of each region when performing evaluations. Furthermore, the evaluation unit can consider the linguistic characteristics of each region when performing evaluations. This allows for more appropriate evaluations by considering geographical distribution. Some or all of the above processing in the evaluation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the evaluation unit can input regional data into a generative AI, and the generative AI can adjust the evaluation criteria.

[0113] The evaluation unit can improve the accuracy of its evaluation by referring to relevant literature on the speech during the evaluation process. For example, the evaluation unit may refer to academic papers related to the topic of the speech. It may also refer to news articles related to the topic of the speech. Furthermore, it may refer to specialized books related to the topic of the speech. In this way, the accuracy of the evaluation can be improved by referring to relevant literature. Some or all of the above processing in the evaluation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the evaluation unit may input the relevant literature data into a generative AI, which can then improve the accuracy of the evaluation.

[0114] The facial expression advice unit can estimate the user's emotions and adjust the method of facial expression advice based on the estimated emotions. For example, if the user is tense, the facial expression advice unit can provide facial expression advice to help them relax. It can also provide advice to help the user maintain a natural expression if they are relaxed. Furthermore, if the user is excited, the facial expression advice unit can provide advice to help them create a calm expression. This allows for more effective feedback by providing facial expression advice in a way that suits the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the facial expression advice unit may be performed using a generative AI, or not. For example, the facial expression advice unit can input the user's facial expression data into a generative AI, which can then estimate the emotions and adjust the method of facial expression advice.

[0115] The facial expression advice unit can adjust the level of detail in its advice based on the importance of the speech. For example, it provides detailed facial expression advice for important speeches. It can also provide basic facial expression advice for general speeches. Furthermore, it can provide concise facial expression advice for simple speeches. This allows for more effective feedback by providing facial expression advice with a level of detail appropriate to the importance of the speech. Some or all of the above processing in the facial expression advice unit may be performed using, for example, a generative AI, or without a generative AI. For example, the facial expression advice unit can input speech importance data into a generative AI, which can then adjust the level of detail in its advice.

[0116] The facial expression advice unit can apply different advice algorithms depending on the category of the speech when providing facial expression advice. For example, in the case of a political speech, the facial expression advice unit can provide advice on creating a serious facial expression. In the case of a speech on environmental issues, it can also provide advice on creating an emotional facial expression. Furthermore, in the case of a speech on technology, it can provide advice on creating a technical facial expression. This allows for more effective feedback by applying an advice algorithm appropriate to the category of the speech. Some or all of the above processing in the facial expression advice unit may be performed using, for example, a generative AI, or without a generative AI. For example, the facial expression advice unit can input speech category data into a generative AI, which can then apply different advice algorithms.

[0117] The facial expression advice unit can estimate the user's emotions and adjust the length of the facial expression advice based on the estimated emotions. For example, if the user is tense, the facial expression advice unit can provide short, concise facial expression advice. If the user is relaxed, the facial expression advice unit can also provide detailed facial expression advice. Furthermore, if the user is excited, the facial expression advice unit can provide longer facial expression advice that includes words of encouragement. This allows for more effective feedback by providing facial expression advice of a length appropriate to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the facial expression advice unit may be performed using a generative AI, or not. For example, the facial expression advice unit can input the user's facial expression data into a generative AI, which can estimate the emotions and adjust the length of the facial expression advice.

[0118] The facial expression advice unit can prioritize advice based on the speech submission date. For example, in the case of an urgent speech, the facial expression advice unit will provide facial expression advice with the highest priority. In the case of a regular speech, the facial expression advice unit can also provide facial expression advice with the usual priority. Furthermore, in the case of a future speech, the facial expression advice unit can postpone providing facial expression advice. This allows for more effective feedback by providing facial expression advice with priority based on the submission date. Some or all of the above processing in the facial expression advice unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the facial expression advice unit can input speech submission date data into a generative AI, and the generative AI can determine the priority of advice.

[0119] The facial expression advice unit can adjust the order of advice based on the relevance of the speech when providing facial expression advice. For example, the facial expression advice unit can provide facial expression advice in order of importance. It can also provide facial expression advice in an order that is easy for the user to understand. Furthermore, the facial expression advice unit can provide facial expression advice based on the user's interests. This allows for more effective feedback by providing facial expression advice in an order based on relevance. Some or all of the above processing in the facial expression advice unit may be performed using, for example, a generative AI, or without a generative AI. For example, the facial expression advice unit can input speech relevance data into a generative AI, which can then adjust the order of advice.

[0120] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0121] The debate club can refer to a user's past debate history and provide topics designed to promote their growth. For example, it can revisit topics the user previously struggled with to encourage them to overcome their weaknesses. It can also provide topics the user excelled at to build their confidence. Furthermore, it can offer new topics the user has never discussed before to broaden their skill set. By providing topics that promote user growth, debate practice becomes more effective.

[0122] The debate system can estimate the user's emotions and adjust the pace of the debate based on those emotions. For example, if the user is nervous, the debate will proceed at a slower pace. If the user is relaxed, the debate can proceed at a normal pace. Furthermore, if the user is excited, the debate can proceed at a faster pace. This allows for more effective practice by adjusting the debate pace to the user's emotions.

[0123] The speech analysis unit can estimate the user's emotions and adjust the speech analysis method based on those estimated emotions. For example, if the user is nervous, it can provide feedback in gentle words. If the user is relaxed, it can provide detailed feedback. Furthermore, if the user is excited, it can provide feedback that includes words of encouragement. This allows for more effective feedback by analyzing the speech in a way that suits the user's emotions.

[0124] The judging panel can improve the accuracy of its judgments based on the interrelationships of the debate. For example, it can evaluate the quality of counterarguments within the debate, the consistency of logic within the debate, and the method of presenting evidence within the debate. By considering the interrelationships of the debate, the accuracy of the judging can be improved.

[0125] The advice function can estimate the user's emotions and adjust the way it expresses advice based on those emotions. For example, if the user is nervous, it will offer advice in gentle words. If the user is relaxed, it can offer more detailed advice. Furthermore, if the user is excited, it can offer advice that includes words of encouragement. This allows for more effective feedback by providing advice in a way that matches the user's emotions.

[0126] The debate club can customize topics based on users' interests. For example, if a user is interested in sports, they can be offered sports-related topics. Similarly, if a user is interested in environmental issues, they can be offered topics related to environmental protection. Furthermore, if a user is interested in technology, they can be offered topics related to the latest technologies. This allows the club to increase users' motivation for practice by providing topics tailored to their interests.

[0127] The evaluation unit can estimate the user's emotions and adjust the evaluation criteria based on those emotions. For example, if the user is tense, it can evaluate using lenient criteria. If the user is relaxed, it can evaluate using normal criteria. Furthermore, if the user is excited, it can evaluate using strict criteria. This allows for more appropriate feedback by evaluating according to the user's emotions.

[0128] The speech analysis department can apply different analysis algorithms depending on the category of the speech. For example, a speech on politics can be analyzed logically. A speech on environmental issues can be analyzed emotionally. Furthermore, a speech on technology can be analyzed technically. By applying an analysis algorithm appropriate to the category of the speech, more effective feedback can be provided.

[0129] The facial expression advice unit can estimate the user's emotions and adjust the method of facial expression advice based on the estimated emotions. For example, if the user is tense, it can provide facial expression advice to help them relax. If the user is relaxed, it can also provide advice to help them maintain a natural expression. Furthermore, if the user is excited, it can provide advice to help them create a calm expression. This allows for more effective feedback by providing facial expression advice in a way that suits the user's emotions.

[0130] The debate club can provide users with highly relevant topics based on their geographical location. For example, if a user lives in an urban area, it can offer topics related to urban issues. If a user lives in a rural area, it can offer topics related to agriculture or the local economy. Furthermore, if a user lives abroad, it can offer topics related to social issues in that country. By providing topics based on geographical location, it is possible to attract users' interest more easily.

[0131] The following briefly describes the processing flow for example form 2.

[0132] Step 1: The Debate Club conducts debate practice. When users practice debating, an AI acts as their opponent. The Debate Club can conduct debates on a variety of topics, from humorous to serious. For example, it offers topics such as politics, economics, social issues, and entertainment. Step 2: The judging panel evaluates the results of the debate conducted by the debate team. They analyze the debate results and provide advice on areas for improvement and effective phrasing. They evaluate the debate results based on evaluation criteria and scoring methods. Step 3: The Advice Department provides advice on areas for improvement based on the results obtained by the Judging Department. The advice is given based on the format of the feedback and the method of presenting areas for improvement. Step 4: The speech analysis department conducts public speaking practice. As the user practices their speech, the department analyzes the content of the speech and evaluates aspects such as facial expressions, speaking style, and the content of the speech. The speech is evaluated based on the frequency and format of the speech practice. Step 5: The evaluation department conducts an evaluation based on the speech content analyzed by the speech analysis department. The speech is evaluated based on evaluation items and scoring methods. Step 6: The facial expression advice unit provides advice based on the evaluation results obtained by the evaluation unit. The advice is given based on areas for improvement in facial expressions and the format of the feedback.

[0133] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0134] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0135] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0136] Each of the multiple elements described above, including the debate unit, judging unit, advice unit, speech analysis unit, evaluation unit, and facial expression advice unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the debate unit is implemented by the control unit 46A of the smart device 14, and the AI ​​acts as an opponent when the user practices debate. The judging unit is implemented by the specific processing unit 290 of the data processing unit 12, and analyzes the results of the debate and advises on areas for improvement. The advice unit is implemented by the specific processing unit 290 of the data processing unit 12, and provides feedback based on the results of the judging unit. The speech analysis unit is implemented by the control unit 46A of the smart device 14, and analyzes the content of the speech. The evaluation unit is implemented by the specific processing unit 290 of the data processing unit 12, and evaluates the speech. The facial expression advice unit is implemented by the control unit 46A of the smart device 14, and reads emotions from facial expressions and voice and provides advice. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0137] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0138] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0139] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0140] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0141] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0143] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0144] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0145] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0146] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0147] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0148] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0149] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0150] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0151] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0152] Each of the multiple elements described above, including the debate unit, judging unit, advice unit, speech analysis unit, evaluation unit, and facial expression advice unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the debate unit is implemented by the control unit 46A of the smart glasses 214, and the AI ​​acts as an opponent when the user practices debating. The judging unit is implemented by the specific processing unit 290 of the data processing unit 12, and analyzes the results of the debate and advises on areas for improvement. The advice unit is implemented by the specific processing unit 290 of the data processing unit 12, and provides feedback based on the results of the judging unit. The speech analysis unit is implemented by the control unit 46A of the smart glasses 214, and analyzes the content of the speech. The evaluation unit is implemented by the specific processing unit 290 of the data processing unit 12, and evaluates the speech. The facial expression advice unit is implemented by the control unit 46A of the smart glasses 214, and reads emotions from facial expressions and voice and provides advice. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0153] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0154] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0155] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0156] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0157] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0158] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0159] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0160] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0161] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0162] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0163] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0164] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0165] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0166] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0167] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0168] Each of the multiple elements described above, including the debate unit, judging unit, advice unit, speech analysis unit, evaluation unit, and facial expression advice unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the debate unit is implemented by the control unit 46A of the headset terminal 314, and the AI ​​acts as an opponent when the user practices debate. The judging unit is implemented by the specific processing unit 290 of the data processing unit 12, and analyzes the results of the debate and advises on areas for improvement. The advice unit is implemented by the specific processing unit 290 of the data processing unit 12, and provides feedback based on the results of the judging unit. The speech analysis unit is implemented by the control unit 46A of the headset terminal 314, and analyzes the content of the speech. The evaluation unit is implemented by the specific processing unit 290 of the data processing unit 12, and evaluates the speech. The facial expression advice unit is implemented by the control unit 46A of the headset terminal 314, and reads emotions from facial expressions and voice and provides advice. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0169] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0170] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0171] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0172] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0173] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0174] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0175] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0176] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0177] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0178] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0179] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0180] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0181] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0182] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0183] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0184] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0185] Each of the multiple elements described above, including the debate unit, judging unit, advice unit, speech analysis unit, evaluation unit, and facial expression advice unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the debate unit is implemented by the control unit 46A of the robot 414, and the AI ​​acts as an opponent when the user practices debate. The judging unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, and analyzes the results of the debate and advises on areas for improvement. The advice unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, and provides feedback based on the results of the judging unit. The speech analysis unit is implemented by, for example, the control unit 46A of the robot 414, and analyzes the content of the speech. The evaluation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, and evaluates the speech. The facial expression advice unit is implemented by, for example, the control unit 46A of the robot 414, and reads emotions from facial expressions and voice and provides advice. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0186] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0187] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0188] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0189] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0190] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0191] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0192] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0193] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0194] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0195] 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.

[0196] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0197] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0198] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0199] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0200] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0201] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0202] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0203] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0204] (Note 1) The debate club, which practices debate, A judging panel that judges the results of the debate conducted by the aforementioned debate panel, An advice unit provides advice on areas for improvement based on the results obtained by the aforementioned judging unit, The speech analysis department conducts public speech practice, An evaluation unit that performs an evaluation based on the speech content analyzed by the speech analysis unit, The system includes an expression advice unit that provides advice based on the evaluation results obtained by the evaluation unit. A system characterized by the following features. (Note 2) The aforementioned debate club, Debates are held on a variety of topics, from humorous to serious. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned debate club, The debate will be conducted not only in Japanese, but also in multiple languages ​​such as English and Chinese. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned speech analysis unit, Practice your speech in multiple languages. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned debate club, The system estimates the user's emotions and selects debate topics based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned debate club, During debate practice, the system provides optimal topics by referencing the user's past debate history. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned debate club, During debate practice, the agenda can be customized based on the user's interests and preferences. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned debate club, It estimates the user's emotions and adjusts the pace of the debate based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned debate club, During debate practice, relevant topics are provided based on the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned debate club, During debate practice, analyze users' social media activity and provide relevant topics. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned judging unit, It estimates the user's emotions and adjusts the judgment criteria based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned judging unit, During judging, improve the accuracy of judging based on the interrelationships of the debate. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned judging unit, During judging, the judges will make decisions based on the attribute information of the debate participants. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned judging unit, It estimates the user's emotions and adjusts the order in which the judgment results are displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned judging unit, During judging, the judges will make decisions based on the geographical distribution of the debate participants. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned judging unit, When judging, refer to relevant literature on debate to improve the accuracy of your judgment. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned advice section, It estimates the user's emotions and adjusts the way advice is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned advice section, When giving advice, adjust the level of detail based on the importance of the debate. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned advice section, When providing advice, different advice algorithms are applied depending on the debate category. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned advice section, When providing advice, different advice algorithms are applied depending on the debate category. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned advice section, It estimates the user's emotions and adjusts the length of the advice based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned advice section, When giving advice, prioritize the advice based on the submission deadline for the debate. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned advice section, When giving advice, adjust the order of advice based on its relevance in the debate. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned speech analysis unit, It estimates the user's emotions and adjusts the speech analysis method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned speech analysis unit, When analyzing a speech, adjust the level of detail based on the importance of the speech. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned speech analysis unit, When analyzing speeches, different analysis algorithms are applied depending on the category of the speech. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned speech analysis unit, It estimates the user's emotions and adjusts the order in which the speech analysis results are displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned speech analysis unit, When analyzing speeches, prioritize the analysis based on when the speeches were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned speech analysis unit, When analyzing speeches, adjust the order of analysis based on the relevance of the speeches. The system described in Appendix 1, characterized by the features described herein. (Note 30) The evaluation unit, It estimates the user's emotions and adjusts the evaluation criteria based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The evaluation unit, During evaluation, improve the accuracy of the assessment based on the interrelationships between speeches. The system described in Appendix 1, characterized by the features described herein. (Note 32) The evaluation unit, During the evaluation process, the participants' demographic information will be used as a basis for the assessment. The system described in Appendix 1, characterized by the features described herein. (Note 33) The evaluation unit, It estimates the user's emotions and adjusts the order in which evaluation results are displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 34) The evaluation unit, During the evaluation, the evaluation will be based on the geographical distribution of the speeches. The system described in Appendix 1, characterized by the features described herein. (Note 35) The evaluation unit, During evaluation, refer to relevant literature related to the speech to improve the accuracy of the assessment. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned facial expression advice unit, The system estimates the user's emotions and adjusts the method of providing facial expression advice based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned facial expression advice unit, When giving advice on facial expressions, adjust the level of detail based on the importance of the speech. The system described in Appendix 1, characterized by the features described herein. (Note 38) The aforementioned facial expression advice unit, When providing facial expression advice, different advice algorithms are applied depending on the speech category. The system described in Appendix 1, characterized by the features described herein. (Note 39) The aforementioned facial expression advice unit, It estimates the user's emotions and adjusts the length of the facial expression advice based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 40) The aforementioned facial expression advice unit, When giving advice on facial expressions, prioritize the advice based on the deadline for submitting the speech. The system described in Appendix 1, characterized by the features described herein. (Note 41) The aforementioned facial expression advice unit, When giving advice on facial expressions, adjust the order of advice based on the relevance of the speech. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0205] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The debate club, which practices debate, A judging panel that judges the results of the debate conducted by the aforementioned debate panel, An advice unit provides advice on areas for improvement based on the results obtained by the aforementioned judging unit, The speech analysis department conducts public speech practice, An evaluation unit that performs an evaluation based on the speech content analyzed by the speech analysis unit, The system includes an expression advice unit that provides advice based on the evaluation results obtained by the evaluation unit. A system characterized by the following features.

2. The aforementioned debate club, Debates are held on a variety of topics, from humorous to serious. The system according to feature 1.

3. The aforementioned debate club, The debate will be conducted not only in Japanese, but also in multiple languages ​​such as English and Chinese. The system according to feature 1.

4. The aforementioned speech analysis unit, Practice your speech in multiple languages. The system according to feature 1.

5. The aforementioned debate club, The system estimates the user's emotions and selects debate topics based on those estimated emotions. The system according to feature 1.

6. The aforementioned debate club, During debate practice, the system provides optimal topics by referencing the user's past debate history. The system according to feature 1.

7. The aforementioned debate club, During debate practice, the agenda can be customized based on the user's interests and preferences. The system according to feature 1.

8. The aforementioned debate club, It estimates the user's emotions and adjusts the pace of the debate based on those emotions. The system according to feature 1.

Images