system

Abstract

The system according to the embodiment aims to generate opinions from various perspectives on presentation slides and correct and improve the slides. [Solution] A system according to an embodiment includes an input unit, a position assignment unit, a generation unit, and a correction unit. The input unit inputs slides for a presentation. The position assignment unit assigns different positions based on the slides input by the input unit. The generation unit generates opinions about the slides based on the positions assigned by the position assignment unit. The correction unit corrects and improves the slides based on the opinions generated by the generation unit.

Description

[Technical Field]

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

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

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

[0004] Conventional technology has had the problem of making it difficult to capture opinions from a variety of perspectives on presentation slides, making it difficult to make revisions that fully take into account the audience's reactions.

[0005] The system according to the embodiment aims to generate opinions from various perspectives on presentation slides and correct and improve the slides. [Means for solving the problem]

[0006] The system according to the embodiment includes an input unit, a position assignment unit, a generation unit, and a correction unit. The input unit inputs slides for a presentation. The position assignment unit assigns different positions based on the slides input by the input unit. The generation unit generates opinions about the slides based on the positions assigned by the position assignment unit. The correction unit corrects and improves the slides based on the opinions generated by the generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can generate opinions on presentation slides from various perspectives and correct and improve the slides. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A presentation support system according to an embodiment of the present invention is a system for improving the quality of presentations using a generative AI. This presentation support system provides the presenter with a wide variety of opinions on the slides by inputting presentation slides into the generative AI and assigning different perspectives to the generative AI. For example, the generative AI can be assigned perspectives such as expert, novice, critical, experts from different industries, and people with different cultural backgrounds. The generative AI generates opinions on the slides based on each perspective. For example, an expert's perspective may generate opinions on technical details, a beginner's perspective may generate opinions on understandability, and a critical perspective may generate opinions on areas for improvement. The presentation slides can then be modified and improved based on the generated opinions. This is expected to improve the quality of the presentation and enhance audience response. For example, when inputting presentation slides into the generative AI, the slide content and structure are described in detail. Next, different perspectives are assigned to the generative AI. The generative AI generates opinions on the slides based on each perspective. The presentation slides are then modified and improved based on the generated opinions. For example, technical details may be added to reflect the expert's opinion, or understandability may be improved to reflect the beginner's opinion. This is expected to improve the quality of presentations and result in better audience responses. Furthermore, it is important to have a mechanism to ensure the quality of the opinions generated by the generative AI. For example, one possible method would be for the generative AI to learn from past presentation data and generate opinions based on that data. This is expected to improve the quality of the opinions generated, and therefore the quality of the presentation. In this way, the presentation support system can improve the quality of presentations.

[0029] A presentation support system according to an embodiment includes an input unit, a position assignment unit, a generation unit, and a correction unit. The input unit inputs presentation slides. The presentation slides may include, but are not limited to, technical content, business content, and educational content. The input unit may, for example, describe the content and structure of the slides in detail. The position assignment unit assigns different positions based on the slides input by the input unit. The position assignment unit may assign positions such as expert, novice, critical viewpoint, experts in different industries, and people with different cultural backgrounds. The generation unit generates opinions about the slides based on the positions assigned by the position assignment unit. The generation unit generates opinions about the slides based on each position using, for example, a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the generation unit may generate opinions about technical details from an expert's perspective, opinions about understandability from a beginner's perspective, and opinions about areas for improvement from a critical viewpoint. The correction unit corrects and improves slides based on the opinions generated by the generation unit. The correction unit may, for example, change the layout of slides or add or delete content based on the generated opinions. The correction unit may, for example, add technical details based on the opinions of experts or improve understandability based on the opinions of beginners. This allows the presentation support system according to the embodiment to improve the quality of presentations. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI. For example, the generation unit may learn past presentation data and generate opinions based on the data. Some or all of the above-described processing in the correction unit may be performed using, for example, an AI. For example, the correction unit may correct and improve slides using an AI model that corrects and improves slides based on the generated opinions. This allows the presentation support system according to the embodiment to improve the quality of presentations.

[0030] The position assignment unit can assign the positions of experts, beginners, critical viewpoints, experts in different industries, and people with different cultural backgrounds. The position assignment unit can assign, for example, the position of an expert. The expert's position is an expert in a specific field or an industry expert. For example, in the case of a technical topic, the position of a technical expert can be assigned. The position assignment unit can also assign the position of a beginner. The beginner's position is a beginner in a specific field or a general beginner. For example, in the case of an educational topic, the position of an educational beginner can be assigned. Furthermore, the position assignment unit can also assign a critical viewpoint. A critical viewpoint requires clarification of the perspective from which criticism is made and the criteria for criticism. For example, in the case of a business topic, a critical business viewpoint can be assigned. This allows the position assignment unit to generate opinions from a variety of viewpoints. Some or all of the above-described processing in the position assignment unit may be performed using, for example, AI, or may be performed without AI. For example, the position assignment unit can estimate a user's emotions and adjust the method of assigning a position based on the estimated user emotions. This allows the position assigning unit to provide a method for assigning a position according to the user's feelings.

[0031] The generation unit can learn past presentation data and generate opinions based on that data. The generation unit can generate opinions based on, for example, past presentation data. Past presentation data includes data from a specific period or data on a specific theme. For example, the generation unit can analyze past presentation data to generate effective opinions. The generation unit can also generate optimal opinions by referring to past presentation data. This allows the generation unit to improve the quality of the generated opinions. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can generate opinions using a generation AI model that generates opinions based on past presentation data. This allows the generation unit to generate highly accurate opinions based on past data.

[0032] The correction unit may correct and improve the slides based on the generated opinions. For example, the correction unit may change the layout of the slides based on the generated opinions. For example, the correction unit may change the layout of the slides to improve visibility. The correction unit may also add or delete content from the slides based on the generated opinions. For example, the correction unit may add technical details based on the opinions of experts and improve understandability based on the opinions of beginners. In this way, the correction unit can improve the presentation slides based on the opinions. Some or all of the above-described processing in the correction unit may be performed using, for example, AI, or may be performed without using AI. For example, the correction unit may correct and improve the slides using an AI model that corrects and improves the slides based on the generated opinions. In this way, the correction unit can correct and improve the presentation slides based on the generated opinions.

[0033] The input unit can analyze the user's past presentation history and select an appropriate input method. The input unit can suggest an optimal input method based on, for example, the layout and design of slides used by the user in the past. The input unit can also analyze the success rate of the user's past presentations and select an effective input method. Furthermore, the input unit can suggest an optimal input method based on presentation tools and software used by the user in the past. This allows the input unit to provide an optimal input method based on the past history. Some or all of the above-described processing in the input unit may be performed using, for example, AI, or may be performed without using AI. For example, the input unit can select an input method using an AI model that selects an optimal input method based on the user's past presentation history. This allows the input unit to provide an optimal input method based on the past history.

[0034] When inputting slides, the input unit can filter slides based on the user's current project or areas of interest. For example, the input unit can prioritize input of slides related to a project the user is currently working on. The input unit can also filter and input related slides based on the user's areas of interest. Furthermore, the input unit can select and input slides based on topics in which the user has previously shown interest. This allows the input unit to prioritize input of slides based on the user's interests. Some or all of the above-described processing in the input unit may be performed using, for example, AI, or may be performed without using AI. For example, the input unit can input slides using an AI model that filters slides based on the user's current project or areas of interest. This allows the input unit to prioritize input of slides based on the user's interests.

[0035] When inputting slides, the input unit can prioritize inputting highly relevant slides taking into account the user's geographical location information. For example, if the user is in a specific area, the input unit can prioritize inputting slides related to that area. Furthermore, if the user is traveling, the input unit can prioritize inputting slides related to the travel destination. Furthermore, if the user is participating in a specific event, the input unit can prioritize inputting slides related to the event. This allows the input unit to input highly relevant slides based on the geographical location information. Some or all of the above-described processing in the input unit may be performed using, for example, AI, or may be performed without using AI. For example, the input unit can input slides using an AI model that selects highly relevant slides based on the user's geographical location information. This allows the input unit to input highly relevant slides based on the geographical location information.

[0036] The input unit can analyze the user's social media activity and input relevant slides when inputting slides. For example, the input unit can input relevant slides based on content shared by the user on social media. The input unit can also input relevant slides based on content of accounts the user follows on social media. Furthermore, the input unit can select and input slides based on groups or events the user participates in on social media. In this way, the input unit can input relevant slides based on social media activity. Some or all of the above-described processing in the input unit may be performed using, for example, AI, or may be performed without using AI. For example, the input unit can input slides using an AI model that selects relevant slides based on the user's social media activity. In this way, the input unit can input relevant slides based on social media activity.

[0037] When assigning a position, the position assigning unit can select an appropriate position based on the theme of the presentation. For example, in the case of a technical theme, the position assigning unit can assign an expert position. Furthermore, in the case of an educational theme, the position assigning unit can assign a beginner position. Furthermore, in the case of a business theme, the position assigning unit can assign the position of an expert in a different industry. This allows the position assigning unit to select an optimal position based on the theme of the presentation. Some or all of the above-mentioned processing in the position assigning unit may be performed using, for example, AI, or may be performed without using AI. For example, the position assigning unit can select a position using an AI model that selects an optimal position based on the theme of the presentation. This allows the position assigning unit to select an optimal position based on the theme of the presentation.

[0038] When assigning a position, the position assigning unit can select a position by referring to past presentation data. For example, the position assigning unit can select an optimal position based on positions that were successful in past presentations. The position assigning unit can also select an optimal position by avoiding positions that were unsuccessful in past presentations. Furthermore, the position assigning unit can analyze past presentation data and select the most effective position. This allows the position assigning unit to select an optimal position based on past data. Some or all of the above-described processing in the position assigning unit may be performed using, for example, AI, or may be performed without using AI. For example, the position assigning unit can select a position using an AI model that selects an optimal position based on past presentation data. This allows the position assigning unit to select an optimal position based on past data.

[0039] When assigning a position, the position assigning unit can select a position based on the user's occupation or field of expertise. For example, if the user is an engineer, the position assigning unit can assign a technical position. Furthermore, if the user is an educator, the position assigning unit can assign an educational position. Furthermore, if the user is a businessman, the position assigning unit can assign a business position. This allows the position assigning unit to select an optimal position based on the user's occupation or field of expertise. Some or all of the above-mentioned processing in the position assigning unit may be performed using AI, for example, or may be performed without using AI. For example, the position assigning unit can select a position using an AI model that selects an optimal position based on the user's occupation or field of expertise. This allows the position assigning unit to select an optimal position based on the user's occupation or field of expertise.

[0040] When assigning a position, the position assigning unit can select a position based on the user's cultural background. For example, if the user has a different cultural background, the position assigning unit can assign a position related to that culture. Furthermore, if the user works in a multicultural environment, the position assigning unit can assign a multicultural position. Furthermore, if the user has a strong interest in a particular culture, the position assigning unit can assign a position related to that culture. This allows the position assigning unit to select an optimal position based on the cultural background. Some or all of the above-described processing in the position assigning unit may be performed using, for example, AI, or may be performed without using AI. For example, the position assigning unit can select a position using an AI model that selects an optimal position based on the user's cultural background. This allows the position assigning unit to select an optimal position based on the cultural background.

[0041] When generating an opinion, the generation unit can adjust the level of detail of the opinion based on the purpose of the presentation. For example, if the purpose of the presentation is educational, the generation unit can generate an opinion that includes detailed explanations. Furthermore, if the purpose of the presentation is business, the generation unit can generate an opinion that focuses on the main points. Furthermore, if the purpose of the presentation is technical, the generation unit can generate an opinion that includes technical details. This allows the generation unit to generate an opinion that matches the purpose of the presentation. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can adjust the level of detail of the opinion using an AI model that adjusts the level of detail of the opinion based on the purpose of the presentation. This allows the generation unit to generate an opinion that matches the purpose of the presentation.

[0042] When generating opinions, the generation unit can improve the accuracy of the opinions by referring to past presentation data. The generation unit can, for example, generate highly accurate opinions based on past presentation data. The generation unit can also analyze past presentation data and generate effective opinions. Furthermore, the generation unit can generate optimal opinions by referring to past presentation data. This allows the generation unit to generate highly accurate opinions based on past data. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can generate opinions using a generation AI model that generates opinions based on past presentation data. This allows the generation unit to generate highly accurate opinions based on past data.

[0043] When generating opinions, the generation unit can adjust the content of the opinions based on the target audience of the presentation. For example, if the audience is experts, the generation unit can generate opinions that include technical details. Furthermore, if the audience is beginners, the generation unit can generate opinions that include easy-to-understand explanations. Furthermore, if the audience is business people, the generation unit can generate opinions that include a business perspective. This allows the generation unit to provide opinions that are appropriate for the target audience. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can adjust the content of the opinions using an AI model that adjusts the content of the opinions based on the target audience of the presentation. This allows the generation unit to provide opinions that are appropriate for the target audience.

[0044] When generating an opinion, the generation unit can adjust the length of the opinion based on the time constraints of the presentation. For example, if the presentation time is short, the generation unit can generate a short opinion that covers the main points. Furthermore, if the presentation time is long, the generation unit can generate a long opinion that includes detailed explanations. Furthermore, the generation unit can generate an opinion of an appropriate length based on the time constraints of the presentation. This allows the generation unit to provide an opinion of an appropriate length based on the time constraints. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can adjust the length of the opinion using an AI model that adjusts the length of the opinion based on the time constraints of the presentation. This allows the generation unit to provide an opinion of an appropriate length based on the time constraints.

[0045] During revision, the revision unit can determine the priority of revisions based on the importance of the generated opinions. For example, the revision unit can revise the slide by preferentially reflecting important opinions. The revision unit can also revise the slide while leaving opinions with low importance for later. Furthermore, the revision unit can determine the order of revisions based on the importance of the opinions. This allows the revision unit to make revisions in an appropriate order based on the importance of the opinions. Some or all of the above-described processing in the revision unit may be performed using, for example, AI, or may be performed without using AI. For example, the revision unit can determine the priority of revisions using an AI model that determines the priority of revisions based on the importance of the generated opinions. This allows the revision unit to make revisions in an appropriate order based on the importance of the opinions.

[0046] The correction unit can improve the accuracy of correction by referring to past presentation data during correction. The correction unit can perform highly accurate correction based on, for example, past presentation data. The correction unit can also analyze past presentation data and suggest an effective correction method. Furthermore, the correction unit can select an optimal correction method by referring to past presentation data. This allows the correction unit to perform highly accurate correction based on past data. Some or all of the above-described processing in the correction unit may be performed using, for example, AI, or may be performed without using AI. For example, the correction unit can improve the accuracy of correction by using an AI model that improves the accuracy of correction based on past presentation data. This allows the correction unit to perform highly accurate correction based on past data.

[0047] During revision, the correction unit can adjust the content of the revision based on the target audience of the presentation. For example, if the audience is experts, the correction unit can make revisions that include technical details. Furthermore, if the audience is beginners, the correction unit can make revisions that include easy-to-understand explanations. Furthermore, if the audience is business people, the correction unit can make revisions that include a business perspective. This allows the correction unit to make appropriate revisions according to the target audience. Some or all of the above-mentioned processing in the correction unit may be performed using, for example, AI, or may be performed without using AI. For example, the correction unit can adjust the content of the revision using an AI model that adjusts the content of the revision based on the target audience of the presentation. This allows the correction unit to make appropriate revisions according to the target audience.

[0048] During revision, the correction unit can adjust the scope of revision based on the time constraints of the presentation. For example, if the presentation time is short, the correction unit can make revisions that focus on the main points. Furthermore, if the presentation time is long, the correction unit can make revisions that include detailed explanations. Furthermore, the correction unit can make revisions to an appropriate extent based on the time constraints of the presentation. This allows the correction unit to make revisions to an appropriate extent based on the time constraints. Some or all of the above-described processing in the correction unit may be performed using, for example, AI, or may be performed without using AI. For example, the correction unit can adjust the scope of revisions using an AI model that adjusts the scope of revisions based on the time constraints of the presentation. This allows the correction unit to make revisions to an appropriate extent based on the time constraints.

[0049] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0050] The presentation support system can further include a voice analysis unit. The voice analysis unit can analyze the presenter's voice and evaluate the clarity of pronunciation, speaking speed, intonation, etc. For example, if the presenter is speaking too quickly, the voice analysis unit can advise the presenter to slow down. If the presenter's voice is too quiet, the voice analysis unit can also suggest that the presenter increase the volume of their voice. Furthermore, if the presenter's intonation is monotonous, the voice analysis unit can advise the presenter to use more intonation. In this way, the presentation support system can provide feedback on the presenter's voice and improve the quality of the presentation.

[0051] The presentation support system may further include a visual analysis unit. The visual analysis unit may analyze the presenter's facial expressions and gestures to evaluate the effectiveness of the presentation. For example, if the presenter is smiling while speaking, the visual analysis unit may evaluate the presenter's friendliness toward the audience. In addition, if the presenter is using his or her hands to explain something, the visual analysis unit may evaluate the effectiveness of the presenter's gestures. Furthermore, the visual analysis unit may evaluate whether the presenter's gaze is directed toward the audience and suggest improvements in the use of gaze. In this way, the presentation support system may provide feedback regarding the presenter's visual expression and improve the quality of the presentation.

[0052] The presentation support system may further include a real-time translation unit. The real-time translation unit may translate the content of a presentation into different languages ​​in real time, allowing the presentation to be provided to an audience that speaks different languages. For example, the real-time translation unit may translate a presentation given in English into Japanese and provide the presentation to an audience that speaks Japanese. The real-time translation unit may also translate presentation slides into different languages ​​and display the slide content in multiple languages. The real-time translation unit may also translate the presenter's voice into different languages ​​and provide the voice in real time. This allows the presentation support system to provide effective presentations to audiences that speak different languages.

[0053] The presentation support system may further include an interactive question and answer unit. The interactive question and answer unit can accept questions from the audience in real time during the presentation and provide answers to those questions. For example, the interactive question and answer unit allows the audience to submit questions using a smartphone or tablet. The interactive question and answer unit can also help the presenter answer the questions in real time. Furthermore, the interactive question and answer unit can analyze the content of the questions and provide related information. This allows the presentation support system to enhance interaction with the audience and improve the quality of the presentation.

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

[0055] Step 1: The input section inputs the slides of the presentation. The slides of the presentation may include technical content, business content, educational content, etc. The input section can describe the content and structure of the slides in detail. Step 2: The position assignment unit assigns different positions based on the slides input by the input unit. The position assignment unit can assign positions such as expert, novice, critical viewpoint, experts from different industries, people with different cultural backgrounds, etc. Step 3: The generator generates opinions about the slides based on the positions assigned by the position assignment unit. The generator uses a generation AI to generate opinions about the slides based on each position. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI. The generator generates opinions about technical details from an expert's perspective, opinions about understandability from a beginner's perspective, and opinions about areas for improvement from a critical perspective. Step 4: The Revision Team modifies and improves the slides based on the feedback generated by the Generation Team. The Revision Team can change the layout of the slides or add or remove content based on the feedback generated. The Revision Team can add technical details based on the feedback of experts and improve the clarity based on the feedback of beginners.

[0056] (Example 2) A presentation support system according to an embodiment of the present invention is a system for improving the quality of presentations using a generative AI. This presentation support system provides the presenter with a wide variety of opinions on the slides by inputting presentation slides into the generative AI and assigning different perspectives to the generative AI. For example, the generative AI can be assigned perspectives such as expert, novice, critical, experts from different industries, and people with different cultural backgrounds. The generative AI generates opinions on the slides based on each perspective. For example, an expert's perspective may generate opinions on technical details, a beginner's perspective may generate opinions on understandability, and a critical perspective may generate opinions on areas for improvement. The presentation slides can then be modified and improved based on the generated opinions. This is expected to improve the quality of the presentation and enhance audience response. For example, when inputting presentation slides into the generative AI, the slide content and structure are described in detail. Next, different perspectives are assigned to the generative AI. The generative AI generates opinions on the slides based on each perspective. The presentation slides are then modified and improved based on the generated opinions. For example, technical details may be added to reflect the expert's opinion, or understandability may be improved to reflect the beginner's opinion. This is expected to improve the quality of presentations and result in better audience responses. Furthermore, it is important to have a mechanism to ensure the quality of the opinions generated by the generative AI. For example, one possible method would be for the generative AI to learn from past presentation data and generate opinions based on that data. This is expected to improve the quality of the opinions generated, and therefore the quality of the presentation. In this way, the presentation support system can improve the quality of presentations.

[0057] A presentation support system according to an embodiment includes an input unit, a position assignment unit, a generation unit, and a correction unit. The input unit inputs presentation slides. The presentation slides may include, but are not limited to, technical content, business content, and educational content. The input unit may, for example, describe the content and structure of the slides in detail. The position assignment unit assigns different positions based on the slides input by the input unit. The position assignment unit may assign positions such as expert, novice, critical viewpoint, experts in different industries, and people with different cultural backgrounds. The generation unit generates opinions about the slides based on the positions assigned by the position assignment unit. The generation unit generates opinions about the slides based on each position using, for example, a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the generation unit may generate opinions about technical details from an expert's perspective, opinions about understandability from a beginner's perspective, and opinions about areas for improvement from a critical viewpoint. The correction unit corrects and improves slides based on the opinions generated by the generation unit. The correction unit may, for example, change the layout of slides or add or delete content based on the generated opinions. The correction unit may, for example, add technical details based on the opinions of experts or improve understandability based on the opinions of beginners. This allows the presentation support system according to the embodiment to improve the quality of presentations. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI. For example, the generation unit may learn past presentation data and generate opinions based on the data. Some or all of the above-described processing in the correction unit may be performed using, for example, an AI. For example, the correction unit may correct and improve slides using an AI model that corrects and improves slides based on the generated opinions. This allows the presentation support system according to the embodiment to improve the quality of presentations.

[0058] The position assignment unit can assign the positions of experts, beginners, critical viewpoints, experts in different industries, and people with different cultural backgrounds. The position assignment unit can assign, for example, the position of an expert. The expert's position is an expert in a specific field or an industry expert. For example, in the case of a technical topic, the position of a technical expert can be assigned. The position assignment unit can also assign the position of a beginner. The beginner's position is a beginner in a specific field or a general beginner. For example, in the case of an educational topic, the position of an educational beginner can be assigned. Furthermore, the position assignment unit can also assign a critical viewpoint. A critical viewpoint requires clarification of the perspective from which criticism is made and the criteria for criticism. For example, in the case of a business topic, a critical business viewpoint can be assigned. This allows the position assignment unit to generate opinions from a variety of viewpoints. Some or all of the above-described processing in the position assignment unit may be performed using, for example, AI, or may be performed without AI. For example, the position assignment unit can estimate a user's emotions and adjust the method of assigning a position based on the estimated user emotions. This allows the position assigning unit to provide a method for assigning a position according to the user's feelings.

[0059] The generation unit can learn past presentation data and generate opinions based on that data. The generation unit can generate opinions based on, for example, past presentation data. Past presentation data includes data from a specific period or data on a specific theme. For example, the generation unit can analyze past presentation data to generate effective opinions. The generation unit can also generate optimal opinions by referring to past presentation data. This allows the generation unit to improve the quality of the generated opinions. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can generate opinions using a generation AI model that generates opinions based on past presentation data. This allows the generation unit to generate highly accurate opinions based on past data.

[0060] The correction unit may correct and improve the slides based on the generated opinions. For example, the correction unit may change the layout of the slides based on the generated opinions. For example, the correction unit may change the layout of the slides to improve visibility. The correction unit may also add or delete content from the slides based on the generated opinions. For example, the correction unit may add technical details based on the opinions of experts and improve understandability based on the opinions of beginners. In this way, the correction unit can improve the presentation slides based on the opinions. Some or all of the above-described processing in the correction unit may be performed using, for example, AI, or may be performed without using AI. For example, the correction unit may correct and improve the slides using an AI model that corrects and improves the slides based on the generated opinions. In this way, the correction unit can correct and improve the presentation slides based on the generated opinions.

[0061] The input unit can estimate the user's emotions and adjust the timing of slide input based on the estimated user's emotions. For example, if the user is nervous, the input unit can delay the timing of slide input to provide the user with time to relax. Furthermore, if the user is relaxed, the input unit can smoothly input slides and maintain the flow of the presentation. Furthermore, if the user is impatient, the input unit can speed up the timing of slide input to quickly progress the presentation. This allows the input unit to input slides at an appropriate timing according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the input unit may be performed using, for example, AI, or may be performed without using AI. For example, the input unit can adjust the timing of slide input using an AI model that adjusts the timing of slide input based on the user's emotion data. This allows the input unit to input slides at an appropriate timing according to the user's emotions.

[0062] The input unit can analyze the user's past presentation history and select an appropriate input method. The input unit can suggest an optimal input method based on, for example, the layout and design of slides used by the user in the past. The input unit can also analyze the success rate of the user's past presentations and select an effective input method. Furthermore, the input unit can suggest an optimal input method based on presentation tools and software used by the user in the past. This allows the input unit to provide an optimal input method based on the past history. Some or all of the above-described processing in the input unit may be performed using, for example, AI, or may be performed without using AI. For example, the input unit can select an input method using an AI model that selects an optimal input method based on the user's past presentation history. This allows the input unit to provide an optimal input method based on the past history.

[0063] When inputting slides, the input unit can filter slides based on the user's current project or areas of interest. For example, the input unit can prioritize input of slides related to a project the user is currently working on. The input unit can also filter and input related slides based on the user's areas of interest. Furthermore, the input unit can select and input slides based on topics in which the user has previously shown interest. This allows the input unit to prioritize input of slides based on the user's interests. Some or all of the above-described processing in the input unit may be performed using, for example, AI, or may be performed without using AI. For example, the input unit can input slides using an AI model that filters slides based on the user's current project or areas of interest. This allows the input unit to prioritize input of slides based on the user's interests.

[0064] The input unit can estimate the user's emotions and determine the priority of slides to be input based on the estimated user's emotions. For example, if the user is nervous, the input unit can postpone important slides and input slides that allow the user to relax. Furthermore, if the user is relaxed, the input unit can prioritize input of important slides. Furthermore, if the user is impatient, the input unit can prioritize input of slides that can be input quickly. This allows the input unit to input slides in a priority order according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the input unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the input unit can determine the priority of slides using an AI model that determines the priority of slides based on the user's emotion data. This allows the input unit to input slides in a priority order according to the user's emotions.

[0065] When inputting slides, the input unit can prioritize inputting highly relevant slides taking into account the user's geographical location information. For example, if the user is in a specific area, the input unit can prioritize inputting slides related to that area. Furthermore, if the user is traveling, the input unit can prioritize inputting slides related to the travel destination. Furthermore, if the user is participating in a specific event, the input unit can prioritize inputting slides related to the event. This allows the input unit to input highly relevant slides based on the geographical location information. Some or all of the above-described processing in the input unit may be performed using, for example, AI, or may be performed without using AI. For example, the input unit can input slides using an AI model that selects highly relevant slides based on the user's geographical location information. This allows the input unit to input highly relevant slides based on the geographical location information.

[0066] The input unit can analyze the user's social media activity and input relevant slides when inputting slides. For example, the input unit can input relevant slides based on content shared by the user on social media. The input unit can also input relevant slides based on content of accounts the user follows on social media. Furthermore, the input unit can select and input slides based on groups or events the user participates in on social media. In this way, the input unit can input relevant slides based on social media activity. Some or all of the above-described processing in the input unit may be performed using, for example, AI, or may be performed without using AI. For example, the input unit can input slides using an AI model that selects relevant slides based on the user's social media activity. In this way, the input unit can input relevant slides based on social media activity.

[0067] The position assignment unit can estimate the user's emotions and adjust the position assignment method based on the estimated user's emotions. For example, if the user is nervous, the position assignment unit can assign a relaxed position (e.g., a friendly perspective). Furthermore, if the user is relaxed, the position assignment unit can assign a critical position to elicit a deeper opinion. Furthermore, if the user is impatient, the position assignment unit can assign a position that allows for quick generation of an opinion. This allows the position assignment unit to provide a position assignment method that corresponds to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the position assignment unit may be performed using, for example, AI, or may be performed without using AI. For example, the position assignment unit can adjust the position assignment method using an AI model that adjusts the position assignment method based on the user's emotion data. This allows the position assignment unit to provide a position assignment method that corresponds to the user's emotions.

[0068] When assigning a position, the position assigning unit can select an appropriate position based on the theme of the presentation. For example, in the case of a technical theme, the position assigning unit can assign an expert position. Furthermore, in the case of an educational theme, the position assigning unit can assign a beginner position. Furthermore, in the case of a business theme, the position assigning unit can assign the position of an expert in a different industry. This allows the position assigning unit to select an optimal position based on the theme of the presentation. Some or all of the above-mentioned processing in the position assigning unit may be performed using, for example, AI, or may be performed without using AI. For example, the position assigning unit can select a position using an AI model that selects an optimal position based on the theme of the presentation. This allows the position assigning unit to select an optimal position based on the theme of the presentation.

[0069] When assigning a position, the position assigning unit can select a position by referring to past presentation data. For example, the position assigning unit can select an optimal position based on positions that were successful in past presentations. The position assigning unit can also select an optimal position by avoiding positions that were unsuccessful in past presentations. Furthermore, the position assigning unit can analyze past presentation data and select the most effective position. This allows the position assigning unit to select an optimal position based on past data. Some or all of the above-described processing in the position assigning unit may be performed using, for example, AI, or may be performed without using AI. For example, the position assigning unit can select a position using an AI model that selects an optimal position based on past presentation data. This allows the position assigning unit to select an optimal position based on past data.

[0070] The position assignment unit can estimate the user's emotions and determine the priority of positions based on the estimated user's emotions. For example, if the user is nervous, the position assignment unit can prioritize a friendly position. Furthermore, if the user is relaxed, the position assignment unit can prioritize a critical position. Furthermore, if the user is impatient, the position assignment unit can prioritize a position that can quickly generate an opinion. This allows the position assignment unit to assign positions in a priority order according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the position assignment unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the position assignment unit can determine the priority of positions using an AI model that determines the priority of positions based on the user's emotion data. This allows the position assignment unit to assign positions in a priority order according to the user's emotions.

[0071] When assigning a position, the position assigning unit can select a position based on the user's occupation or field of expertise. For example, if the user is an engineer, the position assigning unit can assign a technical position. Furthermore, if the user is an educator, the position assigning unit can assign an educational position. Furthermore, if the user is a businessman, the position assigning unit can assign a business position. This allows the position assigning unit to select an optimal position based on the user's occupation or field of expertise. Some or all of the above-mentioned processing in the position assigning unit may be performed using AI, for example, or may be performed without using AI. For example, the position assigning unit can select a position using an AI model that selects an optimal position based on the user's occupation or field of expertise. This allows the position assigning unit to select an optimal position based on the user's occupation or field of expertise.

[0072] When assigning a position, the position assigning unit can select a position based on the user's cultural background. For example, if the user has a different cultural background, the position assigning unit can assign a position related to that culture. Furthermore, if the user works in a multicultural environment, the position assigning unit can assign a multicultural position. Furthermore, if the user has a strong interest in a particular culture, the position assigning unit can assign a position related to that culture. This allows the position assigning unit to select an optimal position based on the cultural background. Some or all of the above-described processing in the position assigning unit may be performed using, for example, AI, or may be performed without using AI. For example, the position assigning unit can select a position using an AI model that selects an optimal position based on the user's cultural background. This allows the position assigning unit to select an optimal position based on the cultural background.

[0073] The generation unit can estimate the user's emotions and adjust the opinion generation method based on the estimated user emotions. For example, if the user is relaxed, the generation unit can generate opinions at a leisurely pace. Furthermore, if the user is in a hurry, the generation unit can generate opinions quickly. Furthermore, if the user is excited, the generation unit can generate opinions with visually stimulating effects. This allows the generation unit to provide an opinion generation method that corresponds to the user's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation 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 processing in the generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the generation unit can adjust the opinion generation method using an AI model that adjusts the opinion generation method based on the user's emotion data. This allows the generation unit to provide an opinion generation method that corresponds to the user's emotions.

[0074] When generating an opinion, the generation unit can adjust the level of detail of the opinion based on the purpose of the presentation. For example, if the purpose of the presentation is educational, the generation unit can generate an opinion that includes detailed explanations. Furthermore, if the purpose of the presentation is business, the generation unit can generate an opinion that focuses on the main points. Furthermore, if the purpose of the presentation is technical, the generation unit can generate an opinion that includes technical details. This allows the generation unit to generate an opinion that matches the purpose of the presentation. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can adjust the level of detail of the opinion using an AI model that adjusts the level of detail of the opinion based on the purpose of the presentation. This allows the generation unit to generate an opinion that matches the purpose of the presentation.

[0075] When generating opinions, the generation unit can improve the accuracy of the opinions by referring to past presentation data. The generation unit can, for example, generate highly accurate opinions based on past presentation data. The generation unit can also analyze past presentation data and generate effective opinions. Furthermore, the generation unit can generate optimal opinions by referring to past presentation data. This allows the generation unit to generate highly accurate opinions based on past data. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can generate opinions using a generation AI model that generates opinions based on past presentation data. This allows the generation unit to generate highly accurate opinions based on past data.

[0076] The generation unit can estimate the user's emotions and adjust the display method of the opinions based on the estimated user emotions. For example, if the user is nervous, the generation unit can provide a simple, highly visible display method. Furthermore, if the user is relaxed, the generation unit can provide a display method including detailed information. Furthermore, if the user is in a hurry, the generation unit can provide a display method that focuses on the main points. This allows the generation unit to provide an appropriate display method according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation 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 processing in the generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the generation unit can adjust the display method of the opinions using an AI model that adjusts the display method of the opinions based on the user's emotion data. This allows the generation unit to provide an appropriate display method according to the user's emotions.

[0077] When generating opinions, the generation unit can adjust the content of the opinions based on the target audience of the presentation. For example, if the audience is experts, the generation unit can generate opinions that include technical details. Furthermore, if the audience is beginners, the generation unit can generate opinions that include easy-to-understand explanations. Furthermore, if the audience is business people, the generation unit can generate opinions that include a business perspective. This allows the generation unit to provide opinions that are appropriate for the target audience. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can adjust the content of the opinions using an AI model that adjusts the content of the opinions based on the target audience of the presentation. This allows the generation unit to provide opinions that are appropriate for the target audience.

[0078] When generating an opinion, the generation unit can adjust the length of the opinion based on the time constraints of the presentation. For example, if the presentation time is short, the generation unit can generate a short opinion that covers the main points. Furthermore, if the presentation time is long, the generation unit can generate a long opinion that includes detailed explanations. Furthermore, the generation unit can generate an opinion of an appropriate length based on the time constraints of the presentation. This allows the generation unit to provide an opinion of an appropriate length based on the time constraints. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can adjust the length of the opinion using an AI model that adjusts the length of the opinion based on the time constraints of the presentation. This allows the generation unit to provide an opinion of an appropriate length based on the time constraints.

[0079] The correction unit can estimate the user's emotions and adjust the slide correction method based on the estimated user's emotions. For example, if the user is nervous, the correction unit can provide a simple correction method. Furthermore, if the user is relaxed, the correction unit can provide a detailed correction method. Furthermore, if the user is impatient, the correction unit can provide a quick correction method. This allows the correction unit to provide an appropriate correction method according to the user's emotions. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the correction unit may be performed using, for example, AI, or may be performed without using AI. For example, the correction unit can adjust the correction method using an AI model that adjusts the slide correction method based on the user's emotion data. This allows the correction unit to provide an appropriate correction method according to the user's emotions.

[0080] During revision, the revision unit can determine the priority of revisions based on the importance of the generated opinions. For example, the revision unit can revise the slide by preferentially reflecting important opinions. The revision unit can also revise the slide while leaving opinions with low importance for later. Furthermore, the revision unit can determine the order of revisions based on the importance of the opinions. This allows the revision unit to make revisions in an appropriate order based on the importance of the opinions. Some or all of the above-described processing in the revision unit may be performed using, for example, AI, or may be performed without using AI. For example, the revision unit can determine the priority of revisions using an AI model that determines the priority of revisions based on the importance of the generated opinions. This allows the revision unit to make revisions in an appropriate order based on the importance of the opinions.

[0081] The correction unit can improve the accuracy of correction by referring to past presentation data during correction. The correction unit can perform highly accurate correction based on, for example, past presentation data. The correction unit can also analyze past presentation data and suggest an effective correction method. Furthermore, the correction unit can select an optimal correction method by referring to past presentation data. This allows the correction unit to perform highly accurate correction based on past data. Some or all of the above-described processing in the correction unit may be performed using, for example, AI, or may be performed without using AI. For example, the correction unit can improve the accuracy of correction by using an AI model that improves the accuracy of correction based on past presentation data. This allows the correction unit to perform highly accurate correction based on past data.

[0082] The correction unit can estimate the user's emotions and adjust the display method of the corrections based on the estimated user's emotions. For example, if the user is nervous, the correction unit can provide a simple, highly visible display method. Furthermore, if the user is relaxed, the correction unit can provide a display method including detailed information. Furthermore, if the user is in a hurry, the correction unit can provide a display method that focuses on the main points. This allows the correction unit to provide an appropriate display method according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation 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 processing in the correction unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the correction unit can adjust the display method of the corrections using an AI model that adjusts the display method of the corrections based on the user's emotion data. This allows the correction unit to provide an appropriate display method according to the user's emotions.

[0083] During revision, the correction unit can adjust the content of the revision based on the target audience of the presentation. For example, if the audience is experts, the correction unit can make revisions that include technical details. Furthermore, if the audience is beginners, the correction unit can make revisions that include easy-to-understand explanations. Furthermore, if the audience is business people, the correction unit can make revisions that include a business perspective. This allows the correction unit to make appropriate revisions according to the target audience. Some or all of the above-mentioned processing in the correction unit may be performed using, for example, AI, or may be performed without using AI. For example, the correction unit can adjust the content of the revision using an AI model that adjusts the content of the revision based on the target audience of the presentation. This allows the correction unit to make appropriate revisions according to the target audience.

[0084] During revision, the correction unit can adjust the scope of revision based on the time constraints of the presentation. For example, if the presentation time is short, the correction unit can make revisions that focus on the main points. Furthermore, if the presentation time is long, the correction unit can make revisions that include detailed explanations. Furthermore, the correction unit can make revisions to an appropriate extent based on the time constraints of the presentation. This allows the correction unit to make revisions to an appropriate extent based on the time constraints. Some or all of the above-described processing in the correction unit may be performed using, for example, AI, or may be performed without using AI. For example, the correction unit can adjust the scope of revisions using an AI model that adjusts the scope of revisions based on the time constraints of the presentation. This allows the correction unit to make revisions to an appropriate extent based on the time constraints. === Hard Collateral 1-1 === Each of the multiple elements including the input unit, position assignment unit, generation unit, and correction unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the input unit inputs presentation slides using the reception device 38 of the smart device 14. The position assignment unit is realized by the specific processing unit 290 of the data processing device 12 and assigns different positions based on the input slides. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates opinions on the slides based on each position using a generation AI. The correction unit is realized by the control unit 46A of the smart device 14 and corrects and improves the slides based on the generated opinions. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned input unit, position assignment unit, generation unit, and correction unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the input unit inputs presentation slides using the microphone 238 of the smart glasses 214. The position assignment unit is realized by the specific processing unit 290 of the data processing device 12 and assigns different positions based on the input slides. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates opinions on the slides based on each position using a generation AI. The correction unit is realized by the control unit 46A of the smart glasses 214 and corrects and improves the slides based on the generated opinions. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned input unit, position assignment unit, generation unit, and correction unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the input unit inputs presentation slides using the microphone 238 of the headset type terminal 314. The position assignment unit is realized by the specific processing unit 290 of the data processing device 12 and assigns different positions based on the input slides. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates opinions on the slides based on each position using a generation AI. The correction unit is realized by the control unit 46A of the headset type terminal 314 and corrects and improves the slides based on the generated opinions. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned input unit, position assignment unit, generation unit, and correction unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the input unit inputs presentation slides using the microphone 238 of the robot 414. The position assignment unit is realized by the specific processing unit 290 of the data processing device 12 and assigns different positions based on the input slides. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates opinions on the slides based on each position using a generation AI. The correction unit is realized by the control unit 46A of the robot 414 and corrects and improves the slides based on the generated opinions.

[0085] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0086] The presentation support system can further include a feedback collection unit. The feedback collection unit can collect feedback from the audience after a presentation, analyze the feedback, and reflect it in the next presentation. For example, the feedback collection unit can identify which parts of the presentation the audience found interesting and which parts were difficult to understand. The feedback collection unit can also estimate the audience's emotions and analyze their emotional reactions to each part of the presentation. Furthermore, the feedback collection unit can suggest improvements to the presentation based on the audience's feedback. In this way, the presentation support system can improve the quality of the presentation by utilizing the audience's feedback.

[0087] The presentation support system can further include a voice analysis unit. The voice analysis unit can analyze the presenter's voice and evaluate the clarity of pronunciation, speaking speed, intonation, etc. For example, if the presenter is speaking too quickly, the voice analysis unit can advise the presenter to slow down. If the presenter's voice is too quiet, the voice analysis unit can also suggest that the presenter increase the volume of their voice. Furthermore, if the presenter's intonation is monotonous, the voice analysis unit can advise the presenter to use more intonation. In this way, the presentation support system can provide feedback on the presenter's voice and improve the quality of the presentation.

[0088] The presentation support system may further include a visual analysis unit. The visual analysis unit may analyze the presenter's facial expressions and gestures to evaluate the effectiveness of the presentation. For example, if the presenter is smiling while speaking, the visual analysis unit may evaluate the presenter's friendliness toward the audience. In addition, if the presenter is using his or her hands to explain something, the visual analysis unit may evaluate the effectiveness of the presenter's gestures. Furthermore, the visual analysis unit may evaluate whether the presenter's gaze is directed toward the audience and suggest improvements in the use of gaze. In this way, the presentation support system may provide feedback regarding the presenter's visual expression and improve the quality of the presentation.

[0089] The presentation support system may further include a real-time translation unit. The real-time translation unit may translate the content of a presentation into different languages ​​in real time, allowing the presentation to be provided to an audience that speaks different languages. For example, the real-time translation unit may translate a presentation given in English into Japanese and provide the presentation to an audience that speaks Japanese. The real-time translation unit may also translate presentation slides into different languages ​​and display the slide content in multiple languages. The real-time translation unit may also translate the presenter's voice into different languages ​​and provide the voice in real time. This allows the presentation support system to provide effective presentations to audiences that speak different languages.

[0090] The presentation support system may further include an interactive question and answer unit. The interactive question and answer unit can accept questions from the audience in real time during the presentation and provide answers to those questions. For example, the interactive question and answer unit allows the audience to submit questions using a smartphone or tablet. The interactive question and answer unit can also help the presenter answer the questions in real time. Furthermore, the interactive question and answer unit can analyze the content of the questions and provide related information. This allows the presentation support system to enhance interaction with the audience and improve the quality of the presentation.

[0091] The presentation support system may further include an emotional feedback unit. The emotional feedback unit may monitor the emotions of the audience in real time during the presentation and adjust the progress of the presentation based on the emotions. For example, the emotional feedback unit may dig deeper into the content of the presentation if the audience is interested. The emotional feedback unit may also speed up the pace of the presentation if the audience is bored. Furthermore, the emotional feedback unit may provide additional explanations if the audience is confused. This allows the presentation support system to provide a flexible presentation that corresponds to the emotions of the audience.

[0092] The presentation support system can further include an emotion estimation unit. The emotion estimation unit can estimate the emotion of the presenter in real time and adjust the progress of the presentation based on the emotion. For example, if the presenter is nervous, the emotion estimation unit can provide advice to relax. Also, if the presenter is confident, the emotion estimation unit can provide support to help the presenter maintain that confidence. Furthermore, if the presenter is feeling impatient, the emotion estimation unit can adjust the pace of the presentation. In this way, the presentation support system can provide support according to the presenter's emotions and improve the quality of the presentation.

[0093] The presentation support system can further include a sentiment analysis unit. The sentiment analysis unit can analyze the emotions of the audience during the presentation and adjust the content of the presentation based on the analysis results. For example, if the audience is excited, the sentiment analysis unit can make the content of the presentation more stimulating. If the audience is feeling anxious, the sentiment analysis unit can also add content that reassures them. Furthermore, if the audience is losing interest, the sentiment analysis unit can change the content of the presentation to re-engage them. This allows the presentation support system to provide flexible presentations that correspond to the emotions of the audience.

[0094] The presentation support system may further include an emotion prediction unit. The emotion prediction unit may predict the emotions of the audience based on the content of the presentation and adjust the progress of the presentation based on the prediction result. For example, if the emotion prediction unit predicts that a particular slide will excite the audience, it may emphasize the slide. Also, if the emotion prediction unit predicts that particular content will cause anxiety in the audience, it may adjust the content to be more toned down. Furthermore, if the emotion prediction unit predicts that a particular topic will interest the audience, it may delve deeper into the topic. In this way, the presentation support system can predict the emotions of the audience and improve the quality of the presentation.

[0095] The presentation support system may further include an emotion adjustment unit. The emotion adjustment unit adjusts the presenter's emotions during the presentation and supports the progress of the presentation based on the adjustment results. For example, if the presenter is nervous, the emotion adjustment unit may provide breathing exercises or mental techniques to help the presenter relax. If the presenter is confident, the emotion adjustment unit may provide positive feedback to help the presenter maintain their confidence. Furthermore, if the presenter is feeling impatient, the emotion adjustment unit may provide advice to help the presenter stay calm. In this way, the presentation support system can adjust the presenter's emotions and improve the quality of the presentation.

[0096] The processing flow of the second embodiment will be briefly explained below.

[0097] Step 1: The input section inputs the slides of the presentation. The slides of the presentation may include technical content, business content, educational content, etc. The input section can describe the content and structure of the slides in detail. Step 2: The position assignment unit assigns different positions based on the slides input by the input unit. The position assignment unit can assign positions such as expert, novice, critical viewpoint, experts from different industries, people with different cultural backgrounds, etc. Step 3: The generator generates opinions about the slides based on the positions assigned by the position assignment unit. The generator uses a generation AI to generate opinions about the slides based on each position. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI. The generator generates opinions about technical details from an expert's perspective, opinions about understandability from a beginner's perspective, and opinions about areas for improvement from a critical perspective. Step 4: The Revision Team modifies and improves the slides based on the feedback generated by the Generation Team. The Revision Team can change the layout of the slides or add or remove content based on the feedback generated. The Revision Team can add technical details based on the feedback of experts and improve the clarity based on the feedback of beginners.

[0098] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0099] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0100] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0101] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0102] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0103] 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.

[0104] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0105] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0106] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0107] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0108] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0109] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0110] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0111] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0112] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0113] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0114] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0115] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0116] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0117] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0118] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0119] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0120] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0121] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0122] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0123] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0124] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0125] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0126] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0127] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0128] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0129] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0130] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0131] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0132] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0133] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0134] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0135] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0136] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0137] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0138] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0139] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0140] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0141] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0142] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0143] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0144] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0145] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0146] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0147] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0148] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0149] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0150] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0151] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0152] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0153] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0154] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0155] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0156] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0157] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0158] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0159] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0160] 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.

[0161] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0162] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0163] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0164] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0165] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0166] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0167] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0168] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0169] [Explanation of symbols]

[0170] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an input section for inputting presentation slides; a position assigning unit that assigns different positions based on the slides input by the input unit; a generation unit that generates opinions about the slides based on the positions assigned by the position assignment unit; a correction unit that corrects and improves the slide based on the opinions generated by the generation unit. A system characterized by:

2. The position assignment unit It gives perspective to experts, novices, critical thinkers, professionals from different industries, and people from different cultural backgrounds.

2. The system of claim 1.

3. The generation unit Learn from past presentation data and generate opinions based on that data 2. The system of claim 1.

4. The correction unit Modify and improve your slides based on the feedback generated 2. The system of claim 1.

5. The input unit Estimate the user's emotions and adjust the timing of slide input based on the estimated user emotions 2. The system of claim 1.

6. The input unit Analyze the user's past presentation history and select the appropriate input method 2. The system of claim 1.

7. The input unit Filtering based on the user's current projects and interests as they populate slides 2. The system of claim 1.

8. The input unit Infer the user's emotions and prioritize the slides to be entered based on the estimated user emotions.

2. The system of claim 1.

9. The input unit When entering slides, the system considers the user's geographic location and prioritizes the most relevant slides.

2. The system of claim 1.

Images