system

Abstract

The system according to this embodiment aims to create materials efficiently and accurately by learning from past materials and automatically adjusting the length according to the presentation time and adding necessary items. [Solution] The system according to the embodiment comprises a learning unit, a creation unit, a volume adjustment unit, an item addition unit, and an information acquisition unit. The learning unit learns from past materials. The creation unit creates materials based on the know-how learned by the learning unit. The volume adjustment unit adjusts the volume of the materials created by the creation unit according to the presentation time. The item addition unit automatically adds specified items to the materials adjusted by the volume adjustment unit. The information acquisition unit reflects real-time information in the materials added by the item addition unit.

Description

Technical Field

[0006] , ,

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, it is difficult to utilize past data in creating financial documents, and there is a risk of excess or deficiency of necessary information and items.

[0005] The system according to the embodiment aims to create documents efficiently and accurately by learning past documents and performing adjustment of the quantity according to the presentation time and automatic addition of necessary items.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a learning unit, a creation unit, a volume adjustment unit, an item addition unit, and an information acquisition unit. The learning unit learns from past materials. The creation unit creates materials based on the know-how learned by the learning unit. The volume adjustment unit adjusts the volume of the materials created by the creation unit according to the presentation time. The item addition unit automatically adds specified items to the materials adjusted by the volume adjustment unit. The information acquisition unit reflects real-time information in the materials added by the item addition unit. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently and accurately create materials by learning from past materials and automatically adjusting the length according to the presentation time and adding necessary items. [Brief explanation of the drawing]

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

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

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

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

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

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

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between multiple computers. Examples of communication standards applicable to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The financial document creation system according to an embodiment of the present invention is a system that utilizes an AI agent to streamline financial document creation, adjust the volume according to the presentation time, automatically determine necessary items, and incorporate real-time information. This financial document creation system first trains the AI ​​with past documents and makes proposals that leverage know-how. Next, it automatically adjusts the volume to fit within the presentation time. Furthermore, it checks for the presence of items required by regulations and automatically adds them to the document. Finally, it obtains the latest stock price information from the internet and reflects it in the document. This mechanism shortens the time and improves the accuracy of document creation, enabling effective presentations at presentations and providing a sense of security by including all necessary information. For example, the financial document creation system trains the AI ​​with past documents. In this process, the AI ​​extracts patterns and know-how from past documents and utilizes them in creating new documents. For example, based on past documents, the AI ​​determines which items are important and reflects them in the new document. This enables proposals that leverage past know-how. Next, the financial document creation system automatically adjusts the volume to fit within the presentation time. The AI ​​optimizes the content of the document according to the presentation time. For example, if the presentation time is short, the system will focus on essential items in the materials, while for longer presentations, it will create materials that include detailed information. This enables effective presentations at conferences. Furthermore, the financial document creation system checks for the presence of required items according to regulations and automatically adds them to the materials. The AI ​​checks whether the necessary items are included in the materials based on the regulations and automatically adds any missing items. For example, if the financial statements are missing required items, the AI ​​will automatically add them. This ensures that all necessary information is included. Finally, the financial document creation system retrieves the latest stock price information from the internet and incorporates it into the materials. The AI ​​retrieves the latest stock price information in real time and incorporates it into the materials. For example, by retrieving the latest stock price information just before the presentation and incorporating it into the materials, it is possible to create materials that include the latest information. This improves the accuracy of the materials and provides a sense of security. In summary, the financial document creation system reduces the time and improves the accuracy of materials, enabling effective presentations at conferences and providing a sense of security by ensuring that all necessary information is included.

[0029] The financial document creation system according to this embodiment comprises a learning unit, a creation unit, a volume adjustment unit, an item addition unit, and an information acquisition unit. The learning unit learns from past documents. For example, the learning unit learns from past technical documents, presentation materials, reports, etc. The learning unit extracts patterns and know-how from past documents using machine learning algorithms. For example, the learning unit extracts important keywords and phrases from past documents using text mining technology. The learning unit can also learn the structure and layout of past documents using pattern recognition technology. The creation unit creates documents based on the know-how learned by the learning unit. For example, the creation unit creates documents using templates. The creation unit constructs the content of the documents based on the know-how extracted by the learning unit. For example, the creation unit creates documents by referring to past success stories and best practices. The creation unit can also analyze failure stories and create documents to avoid the same mistakes. The volume adjustment unit adjusts the volume of the documents according to the presentation time. For example, the volume adjustment unit adjusts the proportion of content to the presentation time. The volume adjustment unit adjusts the content of the documents based on importance. For example, the volume adjustment unit creates materials focusing on essential items when the presentation time is short. Conversely, the volume adjustment unit can also create materials including detailed information when the presentation time is long. The item addition unit checks for the presence of specified items and automatically adds them to the materials. For example, the item addition unit checks for mandatory and recommended items. Based on the regulations, the item addition unit verifies that the necessary items are included in the materials. For example, if the financial statements are missing necessary items, the item addition unit automatically adds them. The information acquisition unit retrieves the latest stock price information from the internet and reflects it in the materials. For example, the information acquisition unit uses an API to retrieve the latest stock price information. The information acquisition unit retrieves information in real time based on the data update frequency. For example, the information acquisition unit retrieves the latest stock price information immediately before the presentation and reflects it in the materials. As a result, the financial document creation system according to this embodiment shortens the time and improves the accuracy of document creation, enabling effective presentations at meetings and providing a sense of security by ensuring that all necessary information is included.

[0030] The learning unit learns from past materials. For example, it learns from past technical documents, presentation materials, and reports. The learning unit uses machine learning algorithms to extract patterns and know-how from past materials. Specifically, the learning unit uses text mining techniques to extract important keywords and phrases from past materials. Text mining techniques utilize natural language processing (NLP) to deeply understand the content of materials by analyzing the frequency, co-occurrence relationships, and context of words and phrases within a document. The learning unit can also learn the structure and layout of past materials using pattern recognition techniques. Pattern recognition techniques analyze the arrangement of sections and paragraphs, heading styles, and the placement of figures and tables in documents to learn the optimal material structure. Furthermore, the learning unit analyzes successful and unsuccessful examples of past materials to identify what elements enhance the effectiveness of materials. For example, it extracts commonalities from successful presentation materials and uses them to create new materials. It also analyzes the problems of unsuccessful materials and learns areas for improvement to avoid the same mistakes. This allows the learning department to make the most of the knowledge gained from past materials and support the creation of more effective materials.

[0031] The creation team creates materials based on the know-how learned by the learning team. For example, the creation team uses templates to create materials. Templates have a predefined format and style, increasing the efficiency of material creation. The creation team structures the content of the materials based on the know-how extracted by the learning team. Specifically, the creation team creates materials by referring to past success stories and best practices. For example, they refer to the structure and content of successful presentations and apply a similar approach to new materials. The creation team can also analyze failure cases and create materials to avoid the same mistakes. By analyzing failure cases, they identify what elements reduced the effectiveness of the materials and reflect specific measures to improve them in the materials. Furthermore, the creation team effectively uses graphs, charts, and diagrams to make the content of the materials visually easy to understand. This makes the content of the materials easier to understand visually and improves the effectiveness of the presentation. The creation team can create visually appealing materials by paying attention not only to the content but also to the design and layout. This allows the creation team to make the most of the know-how of the learning team and quickly create effective and appealing materials.

[0032] The Quantity Adjustment Unit adjusts the length of the materials according to the presentation time. For example, it adjusts the proportion of content to the presentation time. Specifically, the Quantity Adjustment Unit adjusts the content of the materials based on importance. For example, if the presentation time is short, the materials will be created focusing on important items. Important items are the information necessary to convey the purpose and message of the presentation most effectively, and these will be given priority. If the presentation time is long, materials including detailed information can also be created. Detailed information includes supplementary data, background information, and specific examples, which help to deepen understanding of the presentation. The Quantity Adjustment Unit can dynamically adjust the content of the materials according to the presentation time. For example, even if the presentation time changes, it will quickly readjust the length of the materials to provide optimal content. In addition, the Quantity Adjustment Unit adjusts the number of slides and the density of information to make the content of the materials visually easy to understand. This makes it easier for the audience to understand the information and improves the effectiveness of the presentation. Furthermore, the Quantity Adjustment Unit can also customize the content of the materials according to the purpose and target audience of the presentation. For example, presentations for management might emphasize strategic information and omit technical details, while presentations for engineers might include more detailed technical information. This allows the content adjustment department to provide materials best suited to the purpose and target audience of each presentation, maximizing its effectiveness.

[0033] The item addition function checks for the presence of specified items and automatically adds them to the document. For example, it checks for mandatory and recommended items. Specifically, it checks whether the necessary items are included in the document based on the regulations. For example, if the financial statements are missing necessary items, it will automatically add them. Financial statements should include basic items such as revenue, expenses, profit, assets, liabilities, and equity, and it checks whether these are included without omission. The item addition function also determines whether specific items are necessary based on industry or company regulations. For example, in certain industries, information on environmental impact and social responsibility may be considered important, and these items will be automatically added. Furthermore, the item addition function standardizes the order and format of items to ensure consistency in the document's content. This improves the quality of the document and makes it easier for readers to understand. The item addition function not only increases the efficiency of document creation but also ensures that important information is included without omission, thereby improving the reliability of the document. In this way, the item addition function can ensure the quality and reliability of the document and contribute to the success of the presentation.

[0034] The Information Acquisition Unit obtains the latest stock price information from the internet and incorporates it into documents. For example, the Information Acquisition Unit uses APIs to obtain the latest stock price information. Specifically, the Information Acquisition Unit utilizes APIs provided by financial institutions and stock exchanges to obtain stock price information in real time. The Information Acquisition Unit obtains information in real time based on the data update frequency. For example, the Information Acquisition Unit obtains the latest stock price information immediately before its announcement and incorporates it into documents. This ensures that the information included in the documents is up-to-date. Furthermore, the Information Acquisition Unit automatically generates graphs and charts to visually display the acquired stock price information in an easy-to-understand manner. This allows for a quick grasp of stock price fluctuations and trends. In addition, the Information Acquisition Unit can acquire not only stock price information but also related news and market trends and incorporate them into documents. This provides information on the factors and background of stock price fluctuations, enriching the content of the documents. The Information Acquisition Unit can integrate necessary information not only from the internet but also from internal databases and other systems. This allows the Information Acquisition Unit to quickly and accurately acquire all the information necessary for document creation, improving the accuracy and reliability of the documents.

[0035] The learning unit can learn from past materials and extract know-how. For example, the learning unit can learn from past technical documents, presentation materials, reports, etc. The learning unit uses machine learning algorithms to extract patterns and know-how from past materials. For example, the learning unit can use text mining techniques to extract important keywords and phrases from past materials. The learning unit can also use pattern recognition techniques to learn the structure and layout of past materials. This allows know-how to be extracted from past materials and used to create new materials. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the learning unit can input past materials into a generative AI and have the generative AI perform the extraction of know-how.

[0036] The creation unit can create documents based on the know-how learned by the learning unit. The creation unit can create documents using templates, for example. The creation unit structures the content of the documents based on the know-how extracted by the learning unit. For example, the creation unit can create documents by referring to past success stories and best practices. The creation unit can also analyze failure stories and create documents to avoid the same mistakes. This improves the accuracy of the documents by creating them based on learned know-how. Some or all of the above processes in the creation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the creation unit can input the know-how extracted by the learning unit into a generative AI and have the generative AI create the documents.

[0037] The volume adjustment unit can adjust the length of the materials according to the presentation time. For example, the volume adjustment unit adjusts the proportion of content to the presentation time. The volume adjustment unit adjusts the content of the materials based on importance. For example, if the presentation time is short, the volume adjustment unit will create materials that focus on important items. Conversely, if the presentation time is long, the volume adjustment unit can also create materials that include detailed information. By adjusting the length of the materials according to the presentation time, an effective presentation becomes possible. Some or all of the above processing in the volume adjustment unit may be performed using, for example, a generation AI, or without a generation AI. For example, the volume adjustment unit can input the presentation time and the content of the materials into a generation AI and have the generation AI perform the volume adjustment.

[0038] The item addition unit can check for the presence of specified items and automatically add them to the document. For example, the item addition unit checks for required items and recommended items. The item addition unit checks whether the necessary items are included in the document based on the regulations. For example, if the item addition unit is missing items required for the financial statements, it will automatically add them. This ensures that all necessary information is included by checking for the presence of specified items and adding them automatically. Some or all of the above processing in the item addition unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the item addition unit can input the contents of the document and the specified items into the generation AI and have the generation AI perform the item addition.

[0039] The information acquisition unit can acquire the latest stock price information from the internet and reflect it in the document. The information acquisition unit can acquire the latest stock price information using, for example, an API. The information acquisition unit acquires information in real time based on the data update frequency. For example, the information acquisition unit can acquire the latest stock price information immediately before the announcement and reflect it in the document. This improves the accuracy of the document by acquiring the latest stock price information and reflecting it in the document. Some or all of the above processing in the information acquisition unit may be performed using, for example, a generation AI, or without a generation AI. For example, the information acquisition unit can input stock price information acquired from the internet into a generation AI and have the generation AI perform the reflection in the document.

[0040] The learning unit can consider the intentions and objectives of the document creator when learning from past materials. For example, the learning unit can extract points that the document creator wants to emphasize and reflect them in the learning process. For example, the learning unit can consider the target audience intended by the document creator when learning. For example, the learning unit can incorporate specific expressions and styles used by the document creator into the learning process. This allows for the creation of more effective materials by considering the intentions and objectives of the document creator when learning. Some or all of the above processes in the learning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the learning unit can input the intentions and objectives of the document creator into a generative AI and have the generative AI perform the learning.

[0041] The learning unit can learn not only the content of materials but also their structure and layout during the learning process. For example, the learning unit can learn the placement of headings and paragraphs in materials and reflect that in new materials. For example, the learning unit can learn how to arrange charts and graphs in materials and propose effective layouts. For example, the learning unit can learn the fonts and color schemes of materials and create visually appealing materials. By learning the structure and layout of materials in this way, it can create visually appealing materials. Some or all of the above processes in the learning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the learning unit can input the structure and layout of materials into a generative AI and have the generative AI perform the learning.

[0042] The learning unit can include materials from different industries and fields as learning targets during the learning process. For example, the learning unit can learn successful case studies from different industries and apply them to other industries. For example, the learning unit can learn technical materials from different fields and make crossover proposals. For example, the learning unit can learn trends from different industries and reflect the latest information in its materials. This makes crossover proposals possible by including materials from different industries and fields as learning targets. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the learning unit can input materials from different industries and fields into a generative AI and have the generative AI perform the learning.

[0043] The learning unit can also consider information such as the date and time the document was created and the tools used during the learning process. For example, the learning unit can consider the date and time the document was created and prioritize learning the most recent information. For example, the learning unit can learn the characteristics of the tools used to create the document and suggest the most suitable tool. For example, the learning unit can learn changes over time based on the date and time the document was created. This allows for the creation of more appropriate documents by also considering information such as the date and time the document was created and the tools used. Some or all of the above-described processes in the learning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the learning unit can input information such as the date and time the document was created and the tools used into a generative AI and have the generative AI perform the learning.

[0044] The creation unit can create documents by referring to past success and failure cases. For example, the creation unit can create effective documents based on past success cases. For example, the creation unit can analyze past failure cases and create documents that avoid the same mistakes. For example, the creation unit can compare success and failure cases and derive the optimal method for creating documents. In this way, more effective documents can be created by referring to past success and failure cases. Some or all of the above processes in the creation unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the creation unit can input past success and failure cases into a generation AI and have the generation AI create the documents.

[0045] The creation unit can use different templates when creating documents, depending on the purpose and target audience of the document. For example, the creation unit can use a template that focuses on key points for documents intended for management. For example, the creation unit can use a template that includes detailed technical information for documents intended for engineers. For example, the creation unit can use a visually easy-to-understand template for documents intended for general employees. By using different templates according to the purpose and target audience of the document, more appropriate documents can be created. Some or all of the above processes in the creation unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the creation unit can input information about the purpose and target audience of the document into the generation AI and have the generation AI select a template.

[0046] The creation unit can create materials that are compatible with different languages ​​and cultures when creating documents. For example, the creation unit can create multilingual documents to support international presentations. For example, the creation unit can use expressions that are considerate of different cultures to avoid cultural misunderstandings. For example, the creation unit can create documents that comply with the regulations and standards of each country. In this way, by creating documents that are compatible with different languages ​​and cultures, it can support international presentations. Some or all of the above processes in the creation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the creation unit can input information on different languages ​​and cultures into a generative AI and have the generative AI create the documents.

[0047] The creation unit can enhance the visual elements (such as graphs and charts) of a document during its creation process. For example, the creation unit can make extensive use of graphs and charts to make data visually easier to understand. For example, the creation unit can enhance the visual elements to increase the impact of a presentation. For example, the creation unit can use visual elements to convey complex information concisely. This enhances the visual elements of the document, thereby increasing the impact of the presentation. Some or all of the above-described processes in the creation unit may be performed using, for example, a generative AI, or not. For example, the creation unit can input information about the visual elements into a generative AI and have the generative AI perform the enhancement of the visual elements of the document.

[0048] The volume adjustment unit can reduce or add content based on the importance and priority of the materials during volume adjustment. For example, the volume adjustment unit can prioritize keeping important items and reduce others. For example, the volume adjustment unit can adjust the volume of the materials by adding high-priority information. For example, the volume adjustment unit can optimize the content based on the importance of the materials. This makes it possible to give more effective presentations by adjusting the content based on the importance and priority of the materials. Some or all of the above processing in the volume adjustment unit may be performed using, for example, a generating AI, or not using a generating AI. For example, the volume adjustment unit can input information on the importance and priority of the materials into a generating AI and have the generating AI perform the content adjustment.

[0049] The content adjustment unit can consider not only the presentation time but also the format and location of the presentation when adjusting the content. For example, the content adjustment unit can adjust the number of slides according to the presentation format. For example, the content adjustment unit can enhance visual elements according to the facilities of the presentation venue. For example, the content adjustment unit can adjust the materials considering the presentation format and location in addition to the presentation time. This makes it possible to create more appropriate materials by considering not only the presentation time but also the presentation format and location. Some or all of the above processing in the content adjustment unit may be performed using, for example, a generation AI, or without using a generation AI. For example, the content adjustment unit can input information on the presentation format and location into the generation AI and have the generation AI perform the material adjustments.

[0050] The volume adjustment unit can prioritize adjusting the visual elements of the material during volume adjustment. For example, the volume adjustment unit can adjust the size of graphs and charts to make them visually easier to understand. For example, the volume adjustment unit can enhance the visual elements to increase the impact of the presentation. For example, the volume adjustment unit can use visual elements to convey complex information concisely. In this way, prioritizing the adjustment of the visual elements of the material can increase the impact of the presentation. Some or all of the above processing in the volume adjustment unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the volume adjustment unit can input information about the visual elements into the generative AI and have the generative AI perform the adjustment of the visual elements.

[0051] The volume adjustment unit can summarize the content of the material and provide it in a different format during the volume adjustment process. For example, the volume adjustment unit can summarize the content of the material and provide it in slide format. For example, the volume adjustment unit can summarize the content of the material and provide it in report format. For example, the volume adjustment unit can summarize the content of the material and provide it in a different format. This allows information to be conveyed in a more appropriate format by summarizing the content of the material and providing it in a different format. Some or all of the above processing in the volume adjustment unit may be performed using, for example, a generation AI, or without a generation AI. For example, the volume adjustment unit can input the content of the material into a generation AI and have the generation AI perform summarization and format conversion.

[0052] The item addition unit can automatically add not only the specified items but also related supplementary information when an item is added. For example, the item addition unit can automatically add supplementary information related to the specified items. For example, the item addition unit can automatically add reference materials related to the specified items. For example, the item addition unit can automatically add data related to the specified items. This makes it possible to create more comprehensive materials by automatically adding not only the specified items but also related supplementary information. Some or all of the above processing in the item addition unit may be performed using, for example, a generation AI, or without a generation AI. For example, the item addition unit can input the specified items and related supplementary information into the generation AI and have the generation AI perform the addition of the supplementary information.

[0053] The item addition unit can select items to add while considering the overall balance of the document. For example, the item addition unit can prioritize adding important items while considering the overall balance of the document. For example, the item addition unit can add visually easy-to-understand items while considering the overall balance of the document. For example, the item addition unit can appropriately add supplementary information while considering the overall balance of the document. In this way, by selecting items to add while considering the overall balance of the document, it is possible to create a more effective document. Some or all of the above processing in the item addition unit may be performed using, for example, a generation AI, or without a generation AI. For example, the item addition unit can input information on the overall balance of the document into the generation AI and have the generation AI perform the selection of additional items.

[0054] The item addition unit can automatically add items corresponding to different regulations and standards when adding items. For example, the item addition unit can automatically add necessary items based on different regulations. For example, the item addition unit can automatically add items corresponding to different standards. For example, the item addition unit can automatically add items corresponding to the regulations and standards of each country. This makes it possible to create more appropriate documents by automatically adding items corresponding to different regulations and standards. Some or all of the above processing in the item addition unit may be performed using, for example, a generation AI, or without a generation AI. For example, the item addition unit can input information on different regulations and standards into a generation AI and have the generation AI perform the item addition.

[0055] The item addition unit can clearly indicate the source and basis of the item being added when adding an item. The item addition unit can, for example, clearly indicate the source of the item being added to increase its reliability. The item addition unit can, for example, clearly indicate the basis for the item being added to increase the reliability of the document. The item addition unit can, for example, clearly indicate the source and basis of the item being added to increase the transparency of the document. In this way, the reliability of the document can be increased by clearly indicating the source and basis of the item being added. Some or all of the above processing in the item addition unit may be performed using, for example, a generation AI, or without using a generation AI. For example, the item addition unit can input information on the source and basis of the item being added into the generation AI and have the generation AI perform the display of the source and basis.

[0056] The information acquisition unit can utilize not only the internet but also internal databases and other external data sources when acquiring information. For example, the information acquisition unit can acquire the latest information from the internet. For example, the information acquisition unit can acquire historical data from internal databases. For example, the information acquisition unit can acquire related information from other external data sources. This allows for the provision of more diverse information by utilizing not only the internet but also internal databases and other external data sources. Some or all of the above-described processes in the information acquisition unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the information acquisition unit can input information from the internet, internal databases, and external data sources into a generating AI and have the generating AI perform the information acquisition.

[0057] The information acquisition unit can evaluate the reliability and accuracy of the acquired information at the time of acquisition. For example, the information acquisition unit can verify the source of the acquired information and evaluate its reliability. For example, the information acquisition unit can verify the accuracy of the acquired information and reflect it in the materials. For example, the information acquisition unit can evaluate the reliability and accuracy of the acquired information and select appropriate information. By evaluating the reliability and accuracy of the acquired information, it is possible to provide more reliable information. Some or all of the above processing in the information acquisition unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the information acquisition unit can have a generating AI perform the evaluation of the reliability and accuracy of the acquired information.

[0058] The information acquisition unit can acquire not only real-time information but also past trends and forecast information when acquiring information. For example, the information acquisition unit can acquire real-time stock price information. For example, the information acquisition unit can acquire past stock price trends. For example, the information acquisition unit can acquire stock price forecast information. By acquiring not only real-time information but also past trends and forecast information, it is possible to provide a wider variety of information. Some or all of the above processing in the information acquisition unit may be performed using, for example, a generation AI, or without a generation AI. For example, the information acquisition unit can input real-time information, past trends, and forecast information into a generation AI and have the generation AI perform the information acquisition.

[0059] The information acquisition unit can automatically organize the acquired information and reflect it in the document. For example, the information acquisition unit can automatically organize the acquired information and reflect it in the document. For example, the information acquisition unit can automatically classify the acquired information and place it in the appropriate location. For example, the information acquisition unit can automatically organize the acquired information and display it in a visually easy-to-understand manner. As a result, by automatically organizing the acquired information and reflecting it in the document, information can be provided more efficiently. Some or all of the above processing in the information acquisition unit may be performed using, for example, a generation AI, or without using a generation AI. For example, the information acquisition unit can input the acquired information into a generation AI and have the generation AI perform the organization of the information and reflect it in the document.

[0060] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0061] The creation department can create documents that are compatible with different languages ​​and cultures. For example, it can create multilingual documents to support international presentations. It can also use expressions that are considerate of different cultures to avoid cultural misunderstandings. Furthermore, it can create documents that comply with the regulations and standards of each country. In short, by creating documents that are compatible with different languages ​​and cultures, it can support international presentations.

[0062] The item addition section can automatically add not only the specified items but also related supplementary information when an item is added. For example, it can automatically add supplementary information related to the specified items. It can also automatically add reference materials related to the specified items. Furthermore, it can automatically add data related to the specified items. As a result, by automatically adding not only the specified items but also related supplementary information, it is possible to create more comprehensive documents.

[0063] The learning department allows students to include materials from different industries and fields as part of their learning. For example, they can learn about successful case studies from different industries and apply them to other industries. They can also learn about technical materials from different fields and make crossover proposals. Furthermore, they can learn about trends in different industries and incorporate the latest information into their materials. This enables crossover proposals by including materials from different industries and fields as part of the learning process.

[0064] The content adjustment unit can summarize the content of the material and provide it in a different format during the content adjustment process. For example, the content of the material can be summarized and provided in a slide format. It can also be summarized and provided in a report format. Furthermore, the content of the material can be summarized and provided in a different format. This allows information to be conveyed in a more appropriate format by summarizing the content of the material and providing it in a different format.

[0065] The information acquisition unit can utilize not only the internet but also internal databases and other external data sources when acquiring information. For example, it can acquire the latest information from the internet. It can also acquire historical data from internal databases. Furthermore, it can acquire related information from other external data sources. As a result, by utilizing not only the internet but also internal databases and other external data sources, it can provide a wider variety of information.

[0066] The following briefly describes the processing flow for example form 1.

[0067] Step 1: The learning unit studies past materials. For example, it studies past technical documents, presentation materials, reports, etc., and extracts patterns and know-how using machine learning algorithms. It extracts important keywords and phrases using text mining technology and learns the structure and layout of materials using pattern recognition technology. Step 2: The creation team creates materials based on the know-how learned by the learning team. For example, they create materials using templates and structure them by referring to past success stories and best practices. They can also analyze failure cases and create materials to avoid making the same mistakes. Step 3: The volume adjustment section adjusts the length of the materials according to the presentation time. For example, it adjusts the proportion of content to the presentation time and adjusts the content of the materials based on importance. If the presentation time is short, the materials should focus on important items, and if the presentation time is long, materials should include detailed information. Step 4: The item addition section checks for the presence of required items and automatically adds them to the document. For example, it checks for mandatory and recommended items and verifies that the document includes the necessary items according to the regulations. If any required items are missing, it adds them automatically. Step 5: The information acquisition unit retrieves the latest stock price information from the internet and incorporates it into the document. For example, it uses an API to obtain the latest stock price information and retrieves information in real time based on the data update frequency. It retrieves the latest stock price information just before the announcement and incorporates it into the document.

[0068] (Example of form 2) The financial document creation system according to an embodiment of the present invention is a system that utilizes an AI agent to streamline financial document creation, adjust the volume according to the presentation time, automatically determine necessary items, and incorporate real-time information. This financial document creation system first trains the AI ​​with past documents and makes proposals that leverage know-how. Next, it automatically adjusts the volume to fit within the presentation time. Furthermore, it checks for the presence of items required by regulations and automatically adds them to the document. Finally, it obtains the latest stock price information from the internet and reflects it in the document. This mechanism shortens the time and improves the accuracy of document creation, enabling effective presentations at presentations and providing a sense of security by including all necessary information. For example, the financial document creation system trains the AI ​​with past documents. In this process, the AI ​​extracts patterns and know-how from past documents and utilizes them in creating new documents. For example, based on past documents, the AI ​​determines which items are important and reflects them in the new document. This enables proposals that leverage past know-how. Next, the financial document creation system automatically adjusts the volume to fit within the presentation time. The AI ​​optimizes the content of the document according to the presentation time. For example, if the presentation time is short, the system will focus on essential items in the materials, while for longer presentations, it will create materials that include detailed information. This enables effective presentations at conferences. Furthermore, the financial document creation system checks for the presence of required items according to regulations and automatically adds them to the materials. The AI ​​checks whether the necessary items are included in the materials based on the regulations and automatically adds any missing items. For example, if the financial statements are missing required items, the AI ​​will automatically add them. This ensures that all necessary information is included. Finally, the financial document creation system retrieves the latest stock price information from the internet and incorporates it into the materials. The AI ​​retrieves the latest stock price information in real time and incorporates it into the materials. For example, by retrieving the latest stock price information just before the presentation and incorporating it into the materials, it is possible to create materials that include the latest information. This improves the accuracy of the materials and provides a sense of security. In summary, the financial document creation system reduces the time and improves the accuracy of materials, enabling effective presentations at conferences and providing a sense of security by ensuring that all necessary information is included.

[0069] The financial document creation system according to this embodiment comprises a learning unit, a creation unit, a volume adjustment unit, an item addition unit, and an information acquisition unit. The learning unit learns from past documents. For example, the learning unit learns from past technical documents, presentation materials, reports, etc. The learning unit extracts patterns and know-how from past documents using machine learning algorithms. For example, the learning unit extracts important keywords and phrases from past documents using text mining technology. The learning unit can also learn the structure and layout of past documents using pattern recognition technology. The creation unit creates documents based on the know-how learned by the learning unit. For example, the creation unit creates documents using templates. The creation unit constructs the content of the documents based on the know-how extracted by the learning unit. For example, the creation unit creates documents by referring to past success stories and best practices. The creation unit can also analyze failure stories and create documents to avoid the same mistakes. The volume adjustment unit adjusts the volume of the documents according to the presentation time. For example, the volume adjustment unit adjusts the proportion of content to the presentation time. The volume adjustment unit adjusts the content of the documents based on importance. For example, the volume adjustment unit creates materials focusing on essential items when the presentation time is short. Conversely, the volume adjustment unit can also create materials including detailed information when the presentation time is long. The item addition unit checks for the presence of specified items and automatically adds them to the materials. For example, the item addition unit checks for mandatory and recommended items. Based on the regulations, the item addition unit verifies that the necessary items are included in the materials. For example, if the financial statements are missing necessary items, the item addition unit automatically adds them. The information acquisition unit retrieves the latest stock price information from the internet and reflects it in the materials. For example, the information acquisition unit uses an API to retrieve the latest stock price information. The information acquisition unit retrieves information in real time based on the data update frequency. For example, the information acquisition unit retrieves the latest stock price information immediately before the presentation and reflects it in the materials. As a result, the financial document creation system according to this embodiment shortens the time and improves the accuracy of document creation, enabling effective presentations at meetings and providing a sense of security by ensuring that all necessary information is included.

[0070] The learning unit learns from past materials. For example, it learns from past technical documents, presentation materials, and reports. The learning unit uses machine learning algorithms to extract patterns and know-how from past materials. Specifically, the learning unit uses text mining techniques to extract important keywords and phrases from past materials. Text mining techniques utilize natural language processing (NLP) to deeply understand the content of materials by analyzing the frequency, co-occurrence relationships, and context of words and phrases within a document. The learning unit can also learn the structure and layout of past materials using pattern recognition techniques. Pattern recognition techniques analyze the arrangement of sections and paragraphs, heading styles, and the placement of figures and tables in documents to learn the optimal material structure. Furthermore, the learning unit analyzes successful and unsuccessful examples of past materials to identify what elements enhance the effectiveness of materials. For example, it extracts commonalities from successful presentation materials and uses them to create new materials. It also analyzes the problems of unsuccessful materials and learns areas for improvement to avoid the same mistakes. This allows the learning department to make the most of the knowledge gained from past materials and support the creation of more effective materials.

[0071] The creation team creates materials based on the know-how learned by the learning team. For example, the creation team uses templates to create materials. Templates have a predefined format and style, increasing the efficiency of material creation. The creation team structures the content of the materials based on the know-how extracted by the learning team. Specifically, the creation team creates materials by referring to past success stories and best practices. For example, they refer to the structure and content of successful presentations and apply a similar approach to new materials. The creation team can also analyze failure cases and create materials to avoid the same mistakes. By analyzing failure cases, they identify what elements reduced the effectiveness of the materials and reflect specific measures to improve them in the materials. Furthermore, the creation team effectively uses graphs, charts, and diagrams to make the content of the materials visually easy to understand. This makes the content of the materials easier to understand visually and improves the effectiveness of the presentation. The creation team can create visually appealing materials by paying attention not only to the content but also to the design and layout. This allows the creation team to make the most of the know-how of the learning team and quickly create effective and appealing materials.

[0072] The Quantity Adjustment Unit adjusts the length of the materials according to the presentation time. For example, it adjusts the proportion of content to the presentation time. Specifically, the Quantity Adjustment Unit adjusts the content of the materials based on importance. For example, if the presentation time is short, the materials will be created focusing on important items. Important items are the information necessary to convey the purpose and message of the presentation most effectively, and these will be given priority. If the presentation time is long, materials including detailed information can also be created. Detailed information includes supplementary data, background information, and specific examples, which help to deepen understanding of the presentation. The Quantity Adjustment Unit can dynamically adjust the content of the materials according to the presentation time. For example, even if the presentation time changes, it will quickly readjust the length of the materials to provide optimal content. In addition, the Quantity Adjustment Unit adjusts the number of slides and the density of information to make the content of the materials visually easy to understand. This makes it easier for the audience to understand the information and improves the effectiveness of the presentation. Furthermore, the Quantity Adjustment Unit can also customize the content of the materials according to the purpose and target audience of the presentation. For example, presentations for management might emphasize strategic information and omit technical details, while presentations for engineers might include more detailed technical information. This allows the content adjustment department to provide materials best suited to the purpose and target audience of each presentation, maximizing its effectiveness.

[0073] The item addition function checks for the presence of specified items and automatically adds them to the document. For example, it checks for mandatory and recommended items. Specifically, it checks whether the necessary items are included in the document based on the regulations. For example, if the financial statements are missing necessary items, it will automatically add them. Financial statements should include basic items such as revenue, expenses, profit, assets, liabilities, and equity, and it checks whether these are included without omission. The item addition function also determines whether specific items are necessary based on industry or company regulations. For example, in certain industries, information on environmental impact and social responsibility may be considered important, and these items will be automatically added. Furthermore, the item addition function standardizes the order and format of items to ensure consistency in the document's content. This improves the quality of the document and makes it easier for readers to understand. The item addition function not only increases the efficiency of document creation but also ensures that important information is included without omission, thereby improving the reliability of the document. In this way, the item addition function can ensure the quality and reliability of the document and contribute to the success of the presentation.

[0074] The Information Acquisition Unit obtains the latest stock price information from the internet and incorporates it into documents. For example, the Information Acquisition Unit uses APIs to obtain the latest stock price information. Specifically, the Information Acquisition Unit utilizes APIs provided by financial institutions and stock exchanges to obtain stock price information in real time. The Information Acquisition Unit obtains information in real time based on the data update frequency. For example, the Information Acquisition Unit obtains the latest stock price information immediately before its announcement and incorporates it into documents. This ensures that the information included in the documents is up-to-date. Furthermore, the Information Acquisition Unit automatically generates graphs and charts to visually display the acquired stock price information in an easy-to-understand manner. This allows for a quick grasp of stock price fluctuations and trends. In addition, the Information Acquisition Unit can acquire not only stock price information but also related news and market trends and incorporate them into documents. This provides information on the factors and background of stock price fluctuations, enriching the content of the documents. The Information Acquisition Unit can integrate necessary information not only from the internet but also from internal databases and other systems. This allows the Information Acquisition Unit to quickly and accurately acquire all the information necessary for document creation, improving the accuracy and reliability of the documents.

[0075] The learning unit can learn from past materials and extract know-how. For example, the learning unit can learn from past technical documents, presentation materials, reports, etc. The learning unit uses machine learning algorithms to extract patterns and know-how from past materials. For example, the learning unit can use text mining techniques to extract important keywords and phrases from past materials. The learning unit can also use pattern recognition techniques to learn the structure and layout of past materials. This allows know-how to be extracted from past materials and used to create new materials. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the learning unit can input past materials into a generative AI and have the generative AI perform the extraction of know-how.

[0076] The creation unit can create documents based on the know-how learned by the learning unit. The creation unit can create documents using templates, for example. The creation unit structures the content of the documents based on the know-how extracted by the learning unit. For example, the creation unit can create documents by referring to past success stories and best practices. The creation unit can also analyze failure stories and create documents to avoid the same mistakes. This improves the accuracy of the documents by creating them based on learned know-how. Some or all of the above processes in the creation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the creation unit can input the know-how extracted by the learning unit into a generative AI and have the generative AI create the documents.

[0077] The volume adjustment unit can adjust the length of the materials according to the presentation time. For example, the volume adjustment unit adjusts the proportion of content to the presentation time. The volume adjustment unit adjusts the content of the materials based on importance. For example, if the presentation time is short, the volume adjustment unit will create materials that focus on important items. Conversely, if the presentation time is long, the volume adjustment unit can also create materials that include detailed information. By adjusting the length of the materials according to the presentation time, an effective presentation becomes possible. Some or all of the above processing in the volume adjustment unit may be performed using, for example, a generation AI, or without a generation AI. For example, the volume adjustment unit can input the presentation time and the content of the materials into a generation AI and have the generation AI perform the volume adjustment.

[0078] The item addition unit can check for the presence of specified items and automatically add them to the document. For example, the item addition unit checks for required items and recommended items. The item addition unit checks whether the necessary items are included in the document based on the regulations. For example, if the item addition unit is missing items required for the financial statements, it will automatically add them. This ensures that all necessary information is included by checking for the presence of specified items and adding them automatically. Some or all of the above processing in the item addition unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the item addition unit can input the contents of the document and the specified items into the generation AI and have the generation AI perform the item addition.

[0079] The information acquisition unit can acquire the latest stock price information from the internet and reflect it in the document. The information acquisition unit can acquire the latest stock price information using, for example, an API. The information acquisition unit acquires information in real time based on the data update frequency. For example, the information acquisition unit can acquire the latest stock price information immediately before the announcement and reflect it in the document. This improves the accuracy of the document by acquiring the latest stock price information and reflecting it in the document. Some or all of the above processing in the information acquisition unit may be performed using, for example, a generation AI, or without a generation AI. For example, the information acquisition unit can input stock price information acquired from the internet into a generation AI and have the generation AI perform the reflection in the document.

[0080] The learning unit can estimate the user's emotions and select training data based on the estimated emotions. For example, if the user is stressed, the learning unit will prioritize learning materials that promote relaxation. For example, if the user is focused, the learning unit can prioritize learning detailed technical documents. For example, if the user is tired, the learning unit can prioritize learning concise and easy-to-understand materials. This allows for the creation of more appropriate materials by selecting training data based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the learning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the learning unit can input user emotion data into a generative AI and have the generative AI perform the selection of training data.

[0081] The learning unit can consider the intentions and objectives of the document creator when learning from past materials. For example, the learning unit can extract points that the document creator wants to emphasize and reflect them in the learning process. For example, the learning unit can consider the target audience intended by the document creator when learning. For example, the learning unit can incorporate specific expressions and styles used by the document creator into the learning process. This allows for the creation of more effective materials by considering the intentions and objectives of the document creator when learning. Some or all of the above processes in the learning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the learning unit can input the intentions and objectives of the document creator into a generative AI and have the generative AI perform the learning.

[0082] The learning unit can learn not only the content of materials but also their structure and layout during the learning process. For example, the learning unit can learn the placement of headings and paragraphs in materials and reflect that in new materials. For example, the learning unit can learn how to arrange charts and graphs in materials and propose effective layouts. For example, the learning unit can learn the fonts and color schemes of materials and create visually appealing materials. By learning the structure and layout of materials in this way, it can create visually appealing materials. Some or all of the above processes in the learning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the learning unit can input the structure and layout of materials into a generative AI and have the generative AI perform the learning.

[0083] The learning unit can estimate the user's emotions and determine learning priorities based on the estimated emotions. For example, if the user is relaxed, the learning unit may prioritize learning detailed materials. If the user is in a hurry, the learning unit may prioritize learning concise materials. If the user is excited, the learning unit may prioritize learning visually stimulating materials. This allows for the creation of more appropriate materials by determining learning priorities based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the learning unit may be performed using a generative AI, or not. For example, the learning unit can input user emotion data into a generative AI and have the generative AI determine the learning priorities.

[0084] The learning unit can include materials from different industries and fields as learning targets during the learning process. For example, the learning unit can learn successful case studies from different industries and apply them to other industries. For example, the learning unit can learn technical materials from different fields and make crossover proposals. For example, the learning unit can learn trends from different industries and reflect the latest information in its materials. This makes crossover proposals possible by including materials from different industries and fields as learning targets. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the learning unit can input materials from different industries and fields into a generative AI and have the generative AI perform the learning.

[0085] The learning unit can also consider information such as the date and time the document was created and the tools used during the learning process. For example, the learning unit can consider the date and time the document was created and prioritize learning the most recent information. For example, the learning unit can learn the characteristics of the tools used to create the document and suggest the most suitable tool. For example, the learning unit can learn changes over time based on the date and time the document was created. This allows for the creation of more appropriate documents by also considering information such as the date and time the document was created and the tools used. Some or all of the above-described processes in the learning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the learning unit can input information such as the date and time the document was created and the tools used into a generative AI and have the generative AI perform the learning.

[0086] The creation unit can estimate the user's emotions and adjust the presentation of the material based on the estimated emotions. For example, if the user is relaxed, the creation unit can create a material with detailed explanations. For example, if the user is in a hurry, the creation unit can create a concise material that gets straight to the point. For example, if the user is excited, the creation unit can create a visually stimulating material. This allows for the creation of more appropriate materials by adjusting the presentation based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the creation unit may be performed using a generative AI, or not. For example, the creation unit can input user emotion data into a generative AI and have the generative AI adjust the presentation of the material.

[0087] The creation unit can create documents by referring to past success and failure cases. For example, the creation unit can create effective documents based on past success cases. For example, the creation unit can analyze past failure cases and create documents that avoid the same mistakes. For example, the creation unit can compare success and failure cases and derive the optimal method for creating documents. In this way, more effective documents can be created by referring to past success and failure cases. Some or all of the above processes in the creation unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the creation unit can input past success and failure cases into a generation AI and have the generation AI create the documents.

[0088] The creation unit can use different templates when creating documents, depending on the purpose and target audience of the document. For example, the creation unit can use a template that focuses on key points for documents intended for management. For example, the creation unit can use a template that includes detailed technical information for documents intended for engineers. For example, the creation unit can use a visually easy-to-understand template for documents intended for general employees. By using different templates according to the purpose and target audience of the document, more appropriate documents can be created. Some or all of the above processes in the creation unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the creation unit can input information about the purpose and target audience of the document into the generation AI and have the generation AI select a template.

[0089] The creation unit can estimate the user's emotions and adjust the level of detail in the materials based on the estimated emotions. For example, if the user is relaxed, the creation unit can create materials with detailed explanations. For example, if the user is in a hurry, the creation unit can create concise materials that get straight to the point. For example, if the user is excited, the creation unit can create visually stimulating materials. By adjusting the level of detail in the materials based on the user's emotions, more appropriate materials can be created. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the creation unit may be performed using a generative AI, or not using a generative AI. For example, the creation unit can input user emotion data into a generative AI and have the generative AI adjust the level of detail in the materials.

[0090] The creation unit can create materials that are compatible with different languages ​​and cultures when creating documents. For example, the creation unit can create multilingual documents to support international presentations. For example, the creation unit can use expressions that are considerate of different cultures to avoid cultural misunderstandings. For example, the creation unit can create documents that comply with the regulations and standards of each country. In this way, by creating documents that are compatible with different languages ​​and cultures, it can support international presentations. Some or all of the above processes in the creation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the creation unit can input information on different languages ​​and cultures into a generative AI and have the generative AI create the documents.

[0091] The creation unit can enhance the visual elements (such as graphs and charts) of a document during its creation process. For example, the creation unit can make extensive use of graphs and charts to make data visually easier to understand. For example, the creation unit can enhance the visual elements to increase the impact of a presentation. For example, the creation unit can use visual elements to convey complex information concisely. This enhances the visual elements of the document, thereby increasing the impact of the presentation. Some or all of the above-described processes in the creation unit may be performed using, for example, a generative AI, or not. For example, the creation unit can input information about the visual elements into a generative AI and have the generative AI perform the enhancement of the visual elements of the document.

[0092] The volume adjustment unit can estimate the user's emotions and set volume adjustment criteria based on the estimated user emotions. For example, if the user is relaxed, the volume adjustment unit can create materials containing detailed information. For example, if the user is in a hurry, the volume adjustment unit can create concise materials that get straight to the point. For example, if the user is excited, the volume adjustment unit can create visually stimulating materials. This allows for the creation of more appropriate materials by setting volume adjustment criteria based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the volume adjustment unit may be performed using a generative AI, or not using a generative AI. For example, the volume adjustment unit can input user emotion data into a generative AI and have the generative AI set the volume adjustment criteria.

[0093] The volume adjustment unit can reduce or add content based on the importance and priority of the materials during volume adjustment. For example, the volume adjustment unit can prioritize keeping important items and reduce others. For example, the volume adjustment unit can adjust the volume of the materials by adding high-priority information. For example, the volume adjustment unit can optimize the content based on the importance of the materials. This makes it possible to give more effective presentations by adjusting the content based on the importance and priority of the materials. Some or all of the above processing in the volume adjustment unit may be performed using, for example, a generating AI, or not using a generating AI. For example, the volume adjustment unit can input information on the importance and priority of the materials into a generating AI and have the generating AI perform the content adjustment.

[0094] The content adjustment unit can consider not only the presentation time but also the format and location of the presentation when adjusting the content. For example, the content adjustment unit can adjust the number of slides according to the presentation format. For example, the content adjustment unit can enhance visual elements according to the facilities of the presentation venue. For example, the content adjustment unit can adjust the materials considering the presentation format and location in addition to the presentation time. This makes it possible to create more appropriate materials by considering not only the presentation time but also the presentation format and location. Some or all of the above processing in the content adjustment unit may be performed using, for example, a generation AI, or without using a generation AI. For example, the content adjustment unit can input information on the presentation format and location into the generation AI and have the generation AI perform the material adjustments.

[0095] The content adjustment unit can estimate the user's emotions and adjust the order in which the content adjustment results are displayed based on the estimated user emotions. For example, if the user is relaxed, the content adjustment unit can display detailed information first. For example, if the user is in a hurry, the content adjustment unit can display the main points first. For example, if the user is excited, the content adjustment unit can display visually stimulating information first. This allows for the creation of more appropriate materials by adjusting the order in which the content adjustment results are displayed based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the content adjustment unit may be performed using a generative AI, or not using a generative AI. For example, the content adjustment unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the display order.

[0096] The volume adjustment unit can prioritize adjusting the visual elements of the material during volume adjustment. For example, the volume adjustment unit can adjust the size of graphs and charts to make them visually easier to understand. For example, the volume adjustment unit can enhance the visual elements to increase the impact of the presentation. For example, the volume adjustment unit can use visual elements to convey complex information concisely. In this way, prioritizing the adjustment of the visual elements of the material can increase the impact of the presentation. Some or all of the above processing in the volume adjustment unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the volume adjustment unit can input information about the visual elements into the generative AI and have the generative AI perform the adjustment of the visual elements.

[0097] The volume adjustment unit can summarize the content of the material and provide it in a different format during the volume adjustment process. For example, the volume adjustment unit can summarize the content of the material and provide it in slide format. For example, the volume adjustment unit can summarize the content of the material and provide it in report format. For example, the volume adjustment unit can summarize the content of the material and provide it in a different format. This allows information to be conveyed in a more appropriate format by summarizing the content of the material and providing it in a different format. Some or all of the above processing in the volume adjustment unit may be performed using, for example, a generation AI, or without a generation AI. For example, the volume adjustment unit can input the content of the material into a generation AI and have the generation AI perform summarization and format conversion.

[0098] The item addition unit can estimate the user's emotions and determine the priority of items to add based on the estimated emotions. For example, if the user is relaxed, the item addition unit may prioritize adding detailed information. If the user is in a hurry, the item addition unit may prioritize adding key points. If the user is excited, the item addition unit may prioritize adding visually stimulating information. This allows for the provision of more appropriate information by prioritizing items based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the item addition unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the item addition unit can input user emotion data into a generative AI and have the generative AI determine the priority of items to add.

[0099] The item addition unit can automatically add not only the specified items but also related supplementary information when an item is added. For example, the item addition unit can automatically add supplementary information related to the specified items. For example, the item addition unit can automatically add reference materials related to the specified items. For example, the item addition unit can automatically add data related to the specified items. This makes it possible to create more comprehensive materials by automatically adding not only the specified items but also related supplementary information. Some or all of the above processing in the item addition unit may be performed using, for example, a generation AI, or without a generation AI. For example, the item addition unit can input the specified items and related supplementary information into the generation AI and have the generation AI perform the addition of the supplementary information.

[0100] The item addition unit can select items to add while considering the overall balance of the document. For example, the item addition unit can prioritize adding important items while considering the overall balance of the document. For example, the item addition unit can add visually easy-to-understand items while considering the overall balance of the document. For example, the item addition unit can appropriately add supplementary information while considering the overall balance of the document. In this way, by selecting items to add while considering the overall balance of the document, it is possible to create a more effective document. Some or all of the above processing in the item addition unit may be performed using, for example, a generation AI, or without a generation AI. For example, the item addition unit can input information on the overall balance of the document into the generation AI and have the generation AI perform the selection of additional items.

[0101] The item addition section can estimate the user's emotions and adjust how the added items are displayed based on the estimated emotions. For example, if the user is relaxed, the item addition section can display detailed information in a visually clear manner. If the user is in a hurry, the item addition section can display the main points concisely. If the user is excited, the item addition section can use a visually stimulating display method. This allows for the provision of more appropriate information by adjusting how the added items are displayed based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the item addition section may be performed using a generative AI, or not. For example, the item addition section can input user emotion data into a generative AI and have the generative AI adjust the display method.

[0102] The item addition unit can automatically add items corresponding to different regulations and standards when adding items. For example, the item addition unit can automatically add necessary items based on different regulations. For example, the item addition unit can automatically add items corresponding to different standards. For example, the item addition unit can automatically add items corresponding to the regulations and standards of each country. This makes it possible to create more appropriate documents by automatically adding items corresponding to different regulations and standards. Some or all of the above processing in the item addition unit may be performed using, for example, a generation AI, or without a generation AI. For example, the item addition unit can input information on different regulations and standards into a generation AI and have the generation AI perform the item addition.

[0103] The item addition unit can clearly indicate the source and basis of the item being added when adding an item. The item addition unit can, for example, clearly indicate the source of the item being added to increase its reliability. The item addition unit can, for example, clearly indicate the basis for the item being added to increase the reliability of the document. The item addition unit can, for example, clearly indicate the source and basis of the item being added to increase the transparency of the document. In this way, the reliability of the document can be increased by clearly indicating the source and basis of the item being added. Some or all of the above processing in the item addition unit may be performed using, for example, a generation AI, or without using a generation AI. For example, the item addition unit can input information on the source and basis of the item being added into the generation AI and have the generation AI perform the display of the source and basis.

[0104] The information acquisition unit can estimate the user's emotions and determine the priority of information to acquire based on the estimated user emotions. For example, if the user is relaxed, the information acquisition unit may prioritize acquiring detailed information. For example, if the user is in a hurry, the information acquisition unit may prioritize acquiring key points. For example, if the user is excited, the information acquisition unit may prioritize acquiring visually stimulating information. In this way, by determining the priority of information to acquire based on the user's emotions, more appropriate information can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the information acquisition unit may be performed using a generative AI, or not using a generative AI. For example, the information acquisition unit can input user emotion data into a generative AI and have the generative AI perform the determination of information priorities.

[0105] The information acquisition unit can utilize not only the internet but also internal databases and other external data sources when acquiring information. For example, the information acquisition unit can acquire the latest information from the internet. For example, the information acquisition unit can acquire historical data from internal databases. For example, the information acquisition unit can acquire related information from other external data sources. This allows for the provision of more diverse information by utilizing not only the internet but also internal databases and other external data sources. Some or all of the above-described processes in the information acquisition unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the information acquisition unit can input information from the internet, internal databases, and external data sources into a generating AI and have the generating AI perform the information acquisition.

[0106] The information acquisition unit can evaluate the reliability and accuracy of the acquired information at the time of acquisition. For example, the information acquisition unit can verify the source of the acquired information and evaluate its reliability. For example, the information acquisition unit can verify the accuracy of the acquired information and reflect it in the materials. For example, the information acquisition unit can evaluate the reliability and accuracy of the acquired information and select appropriate information. By evaluating the reliability and accuracy of the acquired information, it is possible to provide more reliable information. Some or all of the above processing in the information acquisition unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the information acquisition unit can have a generating AI perform the evaluation of the reliability and accuracy of the acquired information.

[0107] The information acquisition unit can estimate the user's emotions and adjust the display method of the acquired information based on the estimated user emotions. For example, if the user is relaxed, the information acquisition unit can display detailed information in a visually easy-to-understand manner. For example, if the user is in a hurry, the information acquisition unit can display the main points concisely. For example, if the user is excited, the information acquisition unit can use a visually stimulating display method. In this way, by adjusting the display method of acquired information based on the user's emotions, more appropriate information can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is 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 processing in the information acquisition unit may be performed using a generative AI, or not using a generative AI. For example, the information acquisition unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the display method.

[0108] The information acquisition unit can acquire not only real-time information but also past trends and forecast information when acquiring information. For example, the information acquisition unit can acquire real-time stock price information. For example, the information acquisition unit can acquire past stock price trends. For example, the information acquisition unit can acquire stock price forecast information. By acquiring not only real-time information but also past trends and forecast information, it is possible to provide a wider variety of information. Some or all of the above processing in the information acquisition unit may be performed using, for example, a generation AI, or without a generation AI. For example, the information acquisition unit can input real-time information, past trends, and forecast information into a generation AI and have the generation AI perform the information acquisition.

[0109] The information acquisition unit can automatically organize the acquired information and reflect it in the document. For example, the information acquisition unit can automatically organize the acquired information and reflect it in the document. For example, the information acquisition unit can automatically classify the acquired information and place it in the appropriate location. For example, the information acquisition unit can automatically organize the acquired information and display it in a visually easy-to-understand manner. As a result, by automatically organizing the acquired information and reflecting it in the document, information can be provided more efficiently. Some or all of the above processing in the information acquisition unit may be performed using, for example, a generation AI, or without using a generation AI. For example, the information acquisition unit can input the acquired information into a generation AI and have the generation AI perform the organization of the information and reflect it in the document.

[0110] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0111] The learning unit can estimate the user's emotions and select training data based on those emotions. For example, if the user is stressed, it can prioritize learning materials that promote relaxation. If the user is focused, it can prioritize learning detailed technical materials. Furthermore, if the user is tired, it can prioritize learning concise and easy-to-understand materials. By selecting training data based on the user's emotions, it is possible to create more appropriate materials.

[0112] The creation department can create documents that are compatible with different languages ​​and cultures. For example, it can create multilingual documents to support international presentations. It can also use expressions that are considerate of different cultures to avoid cultural misunderstandings. Furthermore, it can create documents that comply with the regulations and standards of each country. In short, by creating documents that are compatible with different languages ​​and cultures, it can support international presentations.

[0113] The content adjustment unit can estimate the user's emotions and set criteria for content adjustment based on those emotions. For example, if the user is relaxed, it can create materials containing detailed information. If the user is in a hurry, it can create concise materials that get straight to the point. Furthermore, if the user is excited, it can create visually stimulating materials. In this way, by setting criteria for content adjustment based on the user's emotions, more appropriate materials can be created.

[0114] The item addition section can automatically add not only the specified items but also related supplementary information when an item is added. For example, it can automatically add supplementary information related to the specified items. It can also automatically add reference materials related to the specified items. Furthermore, it can automatically add data related to the specified items. As a result, by automatically adding not only the specified items but also related supplementary information, it is possible to create more comprehensive documents.

[0115] The information acquisition unit can estimate the user's emotions and determine the priority of information to acquire based on those emotions. For example, if the user is relaxed, detailed information can be prioritized. If the user is in a hurry, key points can be prioritized. Furthermore, if the user is excited, visually stimulating information can be prioritized. By prioritizing information acquisition based on the user's emotions, more appropriate information can be provided.

[0116] The learning department allows students to include materials from different industries and fields as part of their learning. For example, they can learn about successful case studies from different industries and apply them to other industries. They can also learn about technical materials from different fields and make crossover proposals. Furthermore, they can learn about trends in different industries and incorporate the latest information into their materials. This enables crossover proposals by including materials from different industries and fields as part of the learning process.

[0117] The creation unit can estimate the user's emotions and adjust the presentation of the materials based on those emotions. For example, if the user is relaxed, it can create materials with detailed explanations. If the user is in a hurry, it can create concise materials that get straight to the point. Furthermore, if the user is excited, it can create visually stimulating materials. In this way, by adjusting the presentation of materials based on the user's emotions, more appropriate materials can be created.

[0118] The content adjustment unit can summarize the content of the material and provide it in a different format during the content adjustment process. For example, the content of the material can be summarized and provided in a slide format. It can also be summarized and provided in a report format. Furthermore, the content of the material can be summarized and provided in a different format. This allows information to be conveyed in a more appropriate format by summarizing the content of the material and providing it in a different format.

[0119] The item addition section can estimate the user's emotions and adjust how the added items are displayed based on those emotions. For example, if the user is relaxed, detailed information can be displayed in a visually clear manner. If the user is in a hurry, the main points can be displayed concisely. Furthermore, if the user is excited, a visually stimulating display method can be used. In this way, by adjusting how the added items are displayed based on the user's emotions, more appropriate information can be provided.

[0120] The information acquisition unit can utilize not only the internet but also internal databases and other external data sources when acquiring information. For example, it can acquire the latest information from the internet. It can also acquire historical data from internal databases. Furthermore, it can acquire related information from other external data sources. As a result, by utilizing not only the internet but also internal databases and other external data sources, it can provide a wider variety of information.

[0121] The following briefly describes the processing flow for example form 2.

[0122] Step 1: The learning unit studies past materials. For example, it studies past technical documents, presentation materials, reports, etc., and extracts patterns and know-how using machine learning algorithms. It extracts important keywords and phrases using text mining technology and learns the structure and layout of materials using pattern recognition technology. Step 2: The creation team creates materials based on the know-how learned by the learning team. For example, they create materials using templates and structure them by referring to past success stories and best practices. They can also analyze failure cases and create materials to avoid making the same mistakes. Step 3: The volume adjustment section adjusts the length of the materials according to the presentation time. For example, it adjusts the proportion of content to the presentation time and adjusts the content of the materials based on importance. If the presentation time is short, the materials should focus on important items, and if the presentation time is long, materials should include detailed information. Step 4: The item addition section checks for the presence of required items and automatically adds them to the document. For example, it checks for mandatory and recommended items and verifies that the document includes the necessary items according to the regulations. If any required items are missing, it adds them automatically. Step 5: The information acquisition unit retrieves the latest stock price information from the internet and incorporates it into the document. For example, it uses an API to obtain the latest stock price information and retrieves information in real time based on the data update frequency. It retrieves the latest stock price information just before the announcement and incorporates it into the document.

[0123] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0124] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0125] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0126] Each of the multiple elements described above, including the learning unit, creation unit, volume adjustment unit, item addition unit, and information acquisition unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the learning unit is implemented by the specific processing unit 290 of the data processing device 12 and learns from past materials. The creation unit is implemented by the control unit 46A of the smart device 14 and creates materials based on the know-how learned by the learning unit. The volume adjustment unit is implemented by the specific processing unit 290 of the data processing device 12 and adjusts the volume of the materials according to the presentation time. The item addition unit is implemented by the control unit 46A of the smart device 14 and checks for the presence or absence of specified items and automatically adds them to the materials. The information acquisition unit is implemented by the specific processing unit 290 of the data processing device 12 and acquires the latest stock price information from the internet and reflects it in the materials. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0127] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0128] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

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

[0130] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

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

[0132] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0133] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0134] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0135] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0136] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0137] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0138] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0139] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0140] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0141] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0142] Each of the multiple elements described above, including the learning unit, creation unit, volume adjustment unit, item addition unit, and information acquisition unit, is implemented in at least one of the smart glasses 214 and the data processing device 12. For example, the learning unit is implemented by the specific processing unit 290 of the data processing device 12 and learns past materials. The creation unit is implemented by the control unit 46A of the smart glasses 214 and creates materials based on the know-how learned by the learning unit. The volume adjustment unit is implemented by the specific processing unit 290 of the data processing device 12 and adjusts the volume of the materials according to the presentation time. The item addition unit is implemented by the control unit 46A of the smart glasses 214 and checks for the presence or absence of specified items and automatically adds them to the materials. The information acquisition unit is implemented by the specific processing unit 290 of the data processing device 12 and acquires the latest stock price information from the internet and reflects it in the materials. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0143] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0144] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0145] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0146] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0147] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0148] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0149] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0150] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0151] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0152] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0153] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0154] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0155] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0156] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0157] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0158] Each of the multiple elements described above, including the learning unit, creation unit, volume adjustment unit, item addition unit, and information acquisition unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns past materials. The creation unit is implemented by the control unit 46A of the headset terminal 314 and creates materials based on the know-how learned by the learning unit. The volume adjustment unit is implemented by the specific processing unit 290 of the data processing unit 12 and adjusts the volume of the materials according to the presentation time. The item addition unit is implemented by the control unit 46A of the headset terminal 314 and checks for the presence of specified items and automatically adds them to the materials. The information acquisition unit is implemented by the specific processing unit 290 of the data processing unit 12 and acquires the latest stock price information from the internet and reflects it in the materials. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0159] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0160] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0161] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0162] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0163] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0164] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0165] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0166] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0167] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0168] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0169] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0170] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0171] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0172] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0173] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0174] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0175] Each of the multiple elements described above, including the learning unit, creation unit, volume adjustment unit, item addition unit, and information acquisition unit, is implemented in at least one of the following: the robot 414 and the data processing unit 12. For example, the learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns from past materials. The creation unit is implemented by the control unit 46A of the robot 414 and creates materials based on the know-how learned by the learning unit. The volume adjustment unit is implemented by the specific processing unit 290 of the data processing unit 12 and adjusts the volume of the materials according to the presentation time. The item addition unit is implemented by the control unit 46A of the robot 414 and checks for the presence or absence of specified items and automatically adds them to the materials. The information acquisition unit is implemented by the specific processing unit 290 of the data processing unit 12 and acquires the latest stock price information from the internet and reflects it in the materials. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0176] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0177] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0178] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0179] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0180] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0181] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0182] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0183] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0184] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0185] 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.

[0186] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0187] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0188] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0189] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0190] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0191] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0192] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0193] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0194] (Note 1) The learning section, where students study past materials, A creation unit that creates materials based on the know-how learned by the aforementioned learning unit, A volume adjustment unit adjusts the volume of materials created by the aforementioned creation unit according to the presentation time, An item addition unit that automatically adds specified items to the material adjusted by the aforementioned quantity adjustment unit, The system includes an information acquisition unit that reflects real-time information in the materials added by the item addition unit. A system characterized by the following features. (Note 2) The aforementioned learning unit, Learn from past documents and extract know-how. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned creation unit, Materials are created based on the know-how learned by the aforementioned learning unit. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned quantity adjustment unit is Adjust the amount of material according to the presentation time. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned item addition section is, Check for the presence of required items and automatically add them to the document. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned information acquisition unit, Obtain the latest stock price information from the internet and incorporate it into the document. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned learning unit, When studying past materials, consider the intentions and objectives of the material's creator. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned learning unit, When studying, learn not only the content of the materials, but also their structure and layout. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned learning unit, It estimates the user's emotions and determines learning priorities based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned learning unit, When studying, include materials from different industries and fields as part of your learning. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned learning unit, When studying, also consider information such as the date the materials were created and the tools used. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned creation unit, It estimates the user's emotions and adjusts the way the material is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned creation unit, When creating documents, refer to past success stories and failures. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned creation unit, When creating documents, use different templates depending on the purpose and target audience of the document. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned creation unit, It estimates the user's emotions and adjusts the level of detail in the materials based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned creation unit, When creating documents, create documents that are compatible with different languages ​​and cultures. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned creation unit, When creating documents, enhance the visual elements of the document. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned quantity adjustment unit is The system estimates the user's emotions and sets criteria for adjusting the quantity based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned quantity adjustment unit is When adjusting the length, reduce or add content based on the importance and priority of the materials. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned quantity adjustment unit is When adjusting the length of the presentation, consider not only the presentation time but also the format and location. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned quantity adjustment unit is It estimates the user's emotions and adjusts the order in which the results of the quantity adjustment are displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned quantity adjustment unit is When adjusting the length, prioritize adjusting the visual elements of the material. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned quantity adjustment unit is When adjusting the length of the document, summarize the content and provide it in a different format. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned item addition section is, It estimates the user's emotions and determines the priority of items to add based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned item addition section is, When adding an item, not only the specified item but also related supplementary information will be automatically added. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned item addition section is, When adding items, select the items to add while considering the overall balance of the document. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned item addition section is, It estimates the user's emotions and adjusts how additional items are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned item addition section is, When adding an item, automatically add items that correspond to different regulations or standards. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned item addition section is, When adding an item, clearly indicate the source or basis for the item being added. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned information acquisition unit, It estimates the user's emotions and determines the priority of information to acquire based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned information acquisition unit, When acquiring information, we utilize not only the internet but also internal databases and other external data sources. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned information acquisition unit, When acquiring information, evaluate the reliability and accuracy of the acquired information. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned information acquisition unit, It estimates the user's emotions and adjusts how the retrieved information is displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned information acquisition unit, When acquiring information, we obtain not only real-time information but also past trends and forecast information. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned information acquisition unit, When acquiring information, the system automatically organizes the acquired information and reflects it in the document. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0195] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The learning section, where students study past materials, A creation unit that creates materials based on the know-how learned by the aforementioned learning unit, A volume adjustment unit adjusts the volume of materials created by the aforementioned creation unit according to the presentation time, An item addition unit that automatically adds specified items to the material adjusted by the aforementioned quantity adjustment unit, The system includes an information acquisition unit that reflects real-time information in the materials added by the item addition unit. A system characterized by the following features.

2. The aforementioned learning unit, Learn from past documents and extract know-how. The system according to feature 1.

3. The aforementioned creation unit, Materials are created based on the know-how learned by the aforementioned learning unit. The system according to feature 1.

4. The aforementioned quantity adjustment unit is Adjust the amount of material according to the presentation time. The system according to feature 1.

5. The aforementioned item addition section is, Check for the presence of required items and automatically add them to the document. The system according to feature 1.

6. The aforementioned information acquisition unit, Obtain the latest stock price information from the internet and incorporate it into the document. The system according to feature 1.

7. The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system according to feature 1.

8. The aforementioned learning unit, When studying past materials, consider the intentions and objectives of the material's creator. The system according to feature 1.

Images