system

Abstract

An object of a system according to an embodiment is to efficiently improve the quality of a material before MTG with a superior.SOLUTION: A system includes an indication point comprehensive part, a boss information reflection part, a company state reflection part, and a presentation material constitution part. The indication point covering part covers indication points. The boss information reflection part reflects the information of the boss. The company state reflecting part reflects the state of the company in real time. The presentation material constitution part grasps the material constitution from the viewpoint of the presentation material to the superior of the superior.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, it was difficult to efficiently improve the quality of documents before meetings with superiors.

[0005] The system according to the embodiment aims to efficiently improve the quality of materials before a meeting with a superior. [Means for solving the problem]

[0006] The system according to the embodiment includes a point-of-interest comprehensive unit, a supervisor information reflecting unit, a company status reflecting unit, and a presentation material composing unit. The point-of-interest comprehensive unit covers all the points that have been pointed out. The supervisor information reflecting unit reflects the supervisor's information. The company status reflecting unit reflects the company's status in real time. The presentation material composing unit comprehends the composition of materials from the perspective of presentation materials for the supervisor's supervisor. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently improve the quality of documents before a meeting with a superior. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The document quality improvement system according to an embodiment of the present invention utilizes a generation AI to efficiently improve the quality of documents before meetings with superiors. This system covers all the key points in advance, reflects the information and direction the superior is aware of and is considering, and reflects the company's situation and strategy in real time. Furthermore, it can determine in advance the structure of documents that are easy to talk about from the superior's perspective, from the perspective of presentation materials for the superior's superior. This allows the document quality improvement system to efficiently improve the quality of documents before meetings with superiors.

[0029] The document quality improvement system according to the embodiment includes a point-of-interest comprehensive unit, a supervisor information reflecting unit, a company status reflecting unit, and a presentation material composing unit. The point-of-interest comprehensive unit comprehensively covers all points of interest. For example, the generation AI analyzes past meeting records and feedback data to list all points of interest. The generation AI can also perform sentiment analysis of the points of interest and emphasize positive feedback. The generation AI can also prioritize the points of interest based on the supervisor's past evaluation trends and correct the most important points first. The supervisor information reflecting unit reflects the supervisor's information and thoughts. For example, the generation AI can analyze the supervisor's past statements, notes, and emails to reflect the information the supervisor has and the direction the supervisor is thinking in the document. The generation AI can also estimate the supervisor's emotional state and provide information tailored to that emotion. The generation AI can also analyze the supervisor's past statements and notes and emphasize specific keywords and phrases to create documents that will attract the supervisor's attention. The company status reflecting unit reflects the company's situation and strategy in real time. For example, the generation AI analyzes the latest internal data and reports to reflect the company's situation and strategy in the materials. It can also perform sentiment analysis of the company's situation and strategy to emphasize positive aspects. Furthermore, it can compare the company's situation and strategy with past data to extract trends and patterns. The presentation material composition unit understands the composition of materials from the perspective of a presentation to the boss's boss. For example, the generation AI analyzes the boss's past presentation materials and comments to determine in advance how to structure the materials in a way that is easy to understand from the boss's perspective. The generation AI can also estimate the emotional state of the boss's boss and create presentation materials tailored to that emotion. Furthermore, the generation AI can analyze the boss's boss's past presentation materials and emphasize specific keywords and phrases to create materials that will attract the boss's boss's attention. This allows the document quality improvement system to efficiently improve the quality of materials before meetings with the boss. For example, by covering all the key points raised in advance, feedback from the boss can be incorporated in advance, reducing rework. Furthermore, by incorporating the boss's information and thoughts, materials can be created that meet the boss's expectations.Furthermore, by reflecting the company's situation and strategy in real time, materials can be created based on the latest information, which reduces meeting preparation time and improves the efficiency of document creation.

[0030] The Point of Issue Comprehension Unit prioritizes the points raised based on the supervisor's past evaluation trends, allowing the more important points to be corrected first. The Point of Issue Comprehension Unit, for example, uses generation AI to analyze the supervisor's past evaluation trends and prioritize the points raised. It generates a list for correcting the more important points first. It also develops an algorithm to prioritize the points raised based on the supervisor's past evaluation trends. For example, it identifies the more important points based on past feedback data. It also builds a system for prioritizing the points raised, reflecting the supervisor's past evaluation trends. For example, it automatically displays the more important points at the top of the list. This allows the more important points to be corrected first, improving the quality of the document.

[0031] The point-of-remarks comprehensive unit customizes the points of criticism to suit the individual preferences of the supervisor, enabling more individualized responses. The point-of-remarks comprehensive unit, for example, uses generation AI to analyze the individual preferences and style of the supervisor and customizes the points of criticism. For example, it reflects the expressions and formats preferred by the supervisor. It also builds a system that customizes the points of criticism based on the individual preferences and style of the supervisor. For example, it customizes based on the supervisor's past feedback data. It also generates templates for customizing the points of criticism to reflect the individual preferences and style of the supervisor. For example, it automatically applies the wording and layout preferred by the supervisor. This makes it possible to create more effective materials by customizing them to suit the individual preferences and style of the supervisor.

[0032] The pointed out points comprehensive unit can compare the pointed out points with feedback data from different industries or fields and extract common improvement points. The pointed out points comprehensive unit, for example, uses generative AI to collect feedback data from different industries and fields and compare it with the pointed out points. It extracts common improvement points and reflects them in the materials. It also develops an algorithm that analyzes feedback data from different industries and fields and identifies common points with the pointed out points. For example, it lists common improvement points. It also builds a system that compares the pointed out points with feedback data from different industries and fields and extracts common improvement points. For example, it automatically highlights common improvement points. In this way, by comparing with feedback data from different industries and fields, common improvement points can be extracted and the quality of the materials can be improved.

[0033] The pointed out points comprehensive unit can present the pointed out points in a multimodal format including visual or audio data to deepen understanding. The pointed out points comprehensive unit, for example, uses generative AI to build a system that presents the pointed out points in a multimodal format including visual and audio data. For example, it adds graphs and audio commentary. It also generates templates for presenting the pointed out points in a multimodal format. For example, it creates presentation materials that combine visual data and audio data. It also develops algorithms that present the pointed out points in a multimodal format using visual and audio data. For example, it automatically generates graphs and charts that are visually easy to understand. This allows the use of visual and audio data to deepen understanding of the pointed out points.

[0034] The supervisor information reflection unit can develop an algorithm for tracking the evolution of a supervisor's thoughts over time and reflecting the latest thoughts. The supervisor information reflection unit, for example, uses generative AI to build a system for tracking the evolution of a supervisor's thoughts over time. For example, it organizes the supervisor's comments and notes in chronological order and visualizes the changes. It also develops an algorithm for reflecting the supervisor's latest thoughts. For example, it identifies the latest thoughts based on the supervisor's past comment data and reflects them in documents. It also builds a system for tracking the evolution of a supervisor's thoughts over time and reflecting the latest thoughts. For example, it analyzes the supervisor's comment history and automatically reflects the latest thoughts in documents. In this way, the quality of documents is improved by reflecting the supervisor's latest thoughts.

[0035] The supervisor information reflection unit compares supervisor information with information on supervisors from different cultures or regions to gain insights from a global perspective. The supervisor information reflection unit, for example, uses generative AI to build a system that compares supervisor information with information on supervisors from different cultures or regions. For example, to gain insights from a global perspective, it collects speech data from supervisors from different cultures. It also develops an algorithm that analyzes information on supervisors from different cultures or regions and compares it with the supervisor information. For example, it identifies differences between cultures or regions and reflects them in documents. It also builds a system that compares supervisor information with information on supervisors from different cultures or regions to gain insights from a global perspective. For example, it gains insights based on speech data from supervisors from different cultures. This allows it to gain insights from a global perspective and improve the quality of documents.

[0036] The supervisor information reflection unit can convert the supervisor's information into visual notes or mind maps to make it easier to understand visually. The supervisor information reflection unit, for example, uses generation AI to build a system that converts the supervisor's information into visual notes or mind maps. For example, it visually organizes the supervisor's comments and notes. It also develops an algorithm that automatically generates visual notes and mind maps to make the supervisor's information easier to understand visually. For example, it shows important points with diagrams or icons. It also builds a system that converts the supervisor's information into visual notes or mind maps to make it easier to understand visually. For example, it creates visual materials based on the supervisor's comment data. This makes the supervisor's information easier to understand visually, improving the quality of the materials.

[0037] The Company Situation Reflection Department can compare the company's situation or strategy with past data and extract trends or patterns. The Company Situation Reflection Department, for example, uses generative AI to build a system that compares the company's situation and strategy with past data. For example, it analyzes sales data and market trends over time to extract trends. It also develops algorithms that compare past data with current data and extract trends and patterns. For example, it identifies increases or decreases in sales and fluctuations in market share. It also builds a system that compares the company's situation and strategy with past data and extracts trends and patterns. For example, it identifies trends based on past successes and failures. By comparing with past data, it can extract trends and patterns and improve the quality of the materials.

[0038] The Company Situation Reflection Department can simulate the company's situation or strategy based on different scenarios and propose the optimal strategy. The Company Situation Reflection Department, for example, uses generative AI to build a system that simulates the company's situation and strategy based on different scenarios. For example, it sets multiple scenarios and compares the results of each. It also develops an algorithm that simulates the company's situation and strategy based on different scenarios and proposes the optimal strategy. For example, it sets a risk scenario and a growth scenario and identifies the optimal strategy. It also builds a system that simulates the company's situation and strategy based on different scenarios and proposes the optimal strategy. For example, it visualizes the results of each scenario and selects the optimal strategy. In this way, it can propose the optimal strategy by simulating based on different scenarios and improve the quality of the materials.

[0039] The Company Situation Reflection Department can compare the company's situation or strategy with data from different industries or markets to gain new insights. The Company Situation Reflection Department, for example, uses generative AI to build a system that compares the company's situation and strategy with data from different industries and markets. For example, it collects and compares sales data and market trends from different industries. It also develops algorithms that analyze data from different industries and markets and compare it with the company's situation and strategy. For example, it gains insights based on success stories and failures from different industries. It also builds a system that compares the company's situation and strategy with data from different industries and markets to gain new insights. For example, it adjusts strategies based on trends in different markets. In this way, by comparing with data from different industries and markets, new insights can be gained and the quality of the materials can be improved.

[0040] The Company Situation Reflection Department can convert the company's situation or strategy into visuals or infographics to make it easier to understand visually. The Company Situation Reflection Department, for example, uses generative AI to build a system that converts the company's situation or strategy into visuals or infographics. For example, sales data and market trends are displayed in graphs and charts. The department also develops algorithms that automatically generate visuals and infographics to make the company's situation and strategy easier to understand visually. For example, important data is displayed using diagrams and icons. The department also builds a system that converts the company's situation and strategy into visuals or infographics to make them easier to understand visually. For example, visual materials are created based on data. In this way, the company's situation and strategy can be visually easier to understand by using visuals and infographics.

[0041] The presentation material composition unit can create materials that will attract the interest of the boss's boss by analyzing past presentation materials from the boss's boss and emphasizing specific keywords or phrases. The presentation material composition unit, for example, uses a generation AI to analyze past presentation materials from the boss's boss and build a system that extracts specific keywords and phrases. For example, it highlights words frequently used by the boss's boss. It also develops an algorithm that emphasizes specific keywords and phrases to attract the interest of the boss's boss. For example, it identifies important keywords based on past speech data from the boss's boss. It also builds a system that analyzes past presentation materials from the boss's boss and emphasizes specific keywords and phrases to automatically generate materials that will attract the interest of the boss's boss. For example, it highlights topics that will interest the boss's boss. This improves the quality of the materials by creating materials that will attract the interest of the boss's boss.

[0042] The presentation material composition unit can develop an algorithm for tracking the evolution of the boss's boss's thoughts over time and reflecting the latest thoughts. The presentation material composition unit, for example, uses generative AI to build a system for tracking the evolution of the boss's boss's thoughts over time. For example, it organizes the boss's boss's comments and notes in chronological order and visualizes the changes. It also develops an algorithm for reflecting the boss's boss's latest thoughts. For example, it identifies the latest thoughts based on the boss's boss's past comment data and reflects them in the materials. It also builds a system for tracking the evolution of the boss's boss's thoughts over time and reflecting the latest thoughts. For example, it analyzes the comment history of the boss's boss and automatically reflects the latest thoughts in the materials. In this way, the quality of the materials is improved by reflecting the boss's boss's latest thoughts.

[0043] The presentation material composition unit compares information about the boss's boss with information about the boss's boss from a different culture or region to gain insights from a global perspective. The presentation material composition unit, for example, uses generative AI to build a system that compares information about the boss's boss with information about the boss's boss from a different culture or region. For example, to gain insights from a global perspective, the unit collects speech data from the boss's boss from a different culture. The unit also develops an algorithm that analyzes the information about the boss's boss from a different culture or region and compares it with information about the boss's boss. For example, the unit identifies differences between cultures and regions and reflects them in the materials. The unit also builds a system that compares information about the boss's boss with information about the boss's boss from a different culture or region to gain insights from a global perspective. For example, insights are gained based on speech data from the boss's boss from a different culture. This allows insights from a global perspective to be gained, improving the quality of the materials.

[0044] The presentation material composition unit can convert the information about the boss's boss into visual notes or mind maps to make it easier to understand visually. The presentation material composition unit, for example, uses generation AI to build a system that converts the information about the boss's boss into visual notes or mind maps. For example, it visually organizes the remarks and notes of the boss's boss. It also develops an algorithm that automatically generates visual notes and mind maps to make the information about the boss's boss easier to understand visually. For example, it indicates important points with diagrams and icons. It also builds a system that converts the information about the boss's boss into visual notes or mind maps to make it easier to understand visually. For example, it creates visual materials based on the remarks data of the boss's boss. This makes the information about the boss's boss easier to understand visually, improving the quality of the materials.

[0045] The document revision department can track the revision history of documents and extract the most effective revision patterns. The document revision department, for example, uses generative AI to build a system that tracks the revision history of documents. For example, it records the content of revisions and the number of revisions and extracts effective revision patterns. It also analyzes the revision history of documents and develops an algorithm that extracts the most effective revision patterns. For example, it identifies effective revision patterns based on past revision data. It also builds a system that tracks the revision history of documents and extracts the most effective revision patterns. For example, it visualizes the revision history and highlights effective revision patterns. In this way, it can track the revision history, extract the most effective revision patterns, and improve the quality of documents.

[0046] The document correction unit customizes document corrections to suit the individual preferences of the user, thereby further strengthening the individual response. The document correction unit, for example, uses a generative AI to build a system that customizes document corrections to suit the individual preferences and style of the user. For example, it reflects the user's preferred expressions and formats. It also develops an algorithm that customizes document corrections based on the user's individual preferences and style. For example, it customizes based on the user's past correction data. It also generates templates for customizing document corrections to suit the user's individual preferences and style. For example, it automatically applies the user's preferred wording and layout. This allows more effective documents to be created by customizing the documents to suit the user's individual preferences and style.

[0047] The document correction department can compare the document corrections with feedback data from different industries or fields and extract the common areas for improvement. The document correction department, for example, uses generative AI to collect feedback data from different industries or fields and compare it with the document corrections. It extracts common areas for improvement and reflects them in the document. It also analyzes feedback data from different industries and fields and develops an algorithm to identify commonalities with the document corrections. For example, it lists common areas for improvement. It also builds a system that compares the document corrections with feedback data from different industries and fields and extracts common areas for improvement. For example, it automatically highlights common areas for improvement. In this way, by comparing with feedback data from different industries and fields, common areas for improvement can be extracted and the quality of the document can be improved.

[0048] The document correction unit can present the document corrections in the multimodal format including the visual or audio data to deepen the understanding. The document correction unit, for example, uses a generative AI to build a system that presents the document corrections in a multimodal format including visual and audio data. For example, graphs and audio commentary are added. Also, a template is generated for presenting the document corrections in a multimodal format. For example, a presentation material that combines visual data and audio data is created. Also, an algorithm is developed to present the document corrections in a multimodal format using visual and audio data. For example, graphs and charts that are easy to understand visually are automatically generated. This allows the use of visual and audio data to deepen understanding of the document corrections.

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

[0050] The materials quality improvement system can further include a learning style adaptation unit that analyzes the user's learning history and creates materials tailored to each individual's learning style. For example, the system can identify the user's learning style by analyzing what materials the user has created in the past and the feedback they have received. It can also develop an algorithm that customizes the structure and content of materials based on the user's learning style. For example, it can make extensive use of graphs and charts for visual learners and add audio commentary for auditory learners. The learning style adaptation unit can also generate templates tailored to the user's learning style, supporting efficient material creation. This can improve the quality of materials by creating materials optimized for the user's learning style.

[0051] The document quality improvement system can also include a cultural adaptation section that collects feedback data from different cultures and regions and gains insights from a global perspective. For example, it can analyze feedback data from superiors and colleagues from different cultures to extract common areas for improvement and culturally specific points. The cultural adaptation section can also develop algorithms that adjust the content and structure of documents based on feedback data from different cultures and regions. For example, it can reflect culturally specific expressions and formats. The cultural adaptation section can also generate templates tailored to different cultures and regions, supporting document creation from a global perspective. This can improve the quality of documents by creating documents optimized for different cultures and regions.

[0052] The document quality improvement system can further include a success story analysis unit that analyzes the user's past success stories and failure stories and proposes the optimal method for creating documents. For example, it analyzes documents created by the user in the past and their results to identify the factors that led to success and failure. The success story analysis unit also develops an algorithm that optimizes the structure and content of documents based on past success stories. For example, it uses the structure and expression of successful documents as a reference. The success story analysis unit also generates templates based on the user's past success stories and failure stories to support document creation. This makes it possible to improve the quality of documents by utilizing past success stories and failure stories.

[0053] The document quality improvement system can further include an environment adaptation unit that analyzes the user's work environment and suggests the optimal work environment. For example, it can analyze the volume, lighting, and temperature of the user's work environment to identify the optimal environmental conditions. The environment adaptation unit can also develop an algorithm that makes suggestions to improve the efficiency of document creation based on the user's work environment. For example, it can recommend working in a quiet environment and set appropriate lighting and temperature. The environment adaptation unit can also generate templates tailored to the user's work environment to support efficient document creation. This can improve the quality of documents by providing the optimal work environment.

[0054] The document quality improvement system can further include a work schedule optimization unit that analyzes the user's work patterns and proposes an optimal work schedule. For example, it analyzes the user's past work history and identifies efficient work times and break times. The work schedule optimization unit also develops an algorithm that proposes an optimal work schedule based on the user's work patterns. For example, it places important work during times when concentration is highest, with appropriate breaks between each. The work schedule optimization unit also generates a schedule template that matches the user's work patterns, supporting efficient document creation. This allows the provision of an optimal work schedule to improve the quality of documents.

[0055] The document quality improvement system can further include a history analysis unit that analyzes the user's past document creation history and suggests the optimal document creation method. For example, it analyzes documents created by the user in the past and the results to identify effective document creation methods. The history analysis unit also develops an algorithm that optimizes the structure and content of documents based on the user's past document creation history. For example, it refers to the structure and expression of successful documents. The history analysis unit also generates templates based on the user's past document creation history to assist in document creation. This makes it possible to improve the quality of documents by utilizing the user's past document creation history.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The point-reporting unit covers all the points that have been pointed out. For example, the generation AI analyzes past meeting records and feedback data to list the points that have been pointed out. The generation AI can also perform sentiment analysis of the points that have been pointed out and emphasize positive feedback. Furthermore, the generation AI can prioritize the points that have been pointed out based on the supervisor's past evaluation trends and correct the most important points first. Step 2: The supervisor information reflection unit reflects the supervisor's information and thoughts. For example, the generation AI analyzes the supervisor's past statements, notes, and emails, and reflects the information the supervisor has grasped and the direction of their thinking in the document. The generation AI can also estimate the supervisor's emotional state and provide information tailored to that emotion. Furthermore, the generation AI can analyze the supervisor's past statements and notes, and create documents that will attract the supervisor's attention by emphasizing specific keywords and phrases. Step 3: The company situation reflection unit reflects the company's situation and strategy in real time. For example, the generation AI analyzes the latest internal data and reports and reflects the company's situation and strategy in the materials. The generation AI can also perform sentiment analysis on the company's situation and strategy and emphasize positive aspects. Furthermore, the generation AI can compare the company's situation and strategy with past data to extract trends and patterns. Step 4: The presentation material composition unit determines the composition of the materials from the perspective of presentation materials for the boss's boss. For example, the generation AI analyzes the boss's past presentation materials and statements to determine in advance the composition of materials that will be easy to speak from the boss's perspective. The generation AI can also estimate the emotional state of the boss's boss and create presentation materials that match those emotions. Furthermore, the generation AI can analyze the boss's boss's past presentation materials and emphasize specific keywords and phrases to create materials that will attract the interest of the boss's boss.

[0058] (Example 2) The document quality improvement system according to an embodiment of the present invention utilizes a generation AI to efficiently improve the quality of documents before meetings with superiors. This system covers all the key points in advance, reflects the information and direction the superior is aware of and is considering, and reflects the company's situation and strategy in real time. Furthermore, it can determine in advance the structure of documents that are easy to talk about from the superior's perspective, from the perspective of presentation materials for the superior's superior. This allows the document quality improvement system to efficiently improve the quality of documents before meetings with superiors.

[0059] The document quality improvement system according to the embodiment includes a point-of-interest comprehensive unit, a supervisor information reflecting unit, a company status reflecting unit, and a presentation material composing unit. The point-of-interest comprehensive unit comprehensively covers all points of interest. For example, the generation AI analyzes past meeting records and feedback data to list all points of interest. The generation AI can also perform sentiment analysis of the points of interest and emphasize positive feedback. The generation AI can also prioritize the points of interest based on the supervisor's past evaluation trends and correct the most important points first. The supervisor information reflecting unit reflects the supervisor's information and thoughts. For example, the generation AI can analyze the supervisor's past statements, notes, and emails to reflect the information the supervisor has and the direction the supervisor is thinking in the document. The generation AI can also estimate the supervisor's emotional state and provide information tailored to that emotion. The generation AI can also analyze the supervisor's past statements and notes and emphasize specific keywords and phrases to create documents that will attract the supervisor's attention. The company status reflecting unit reflects the company's situation and strategy in real time. For example, the generation AI analyzes the latest internal data and reports to reflect the company's situation and strategy in the materials. It can also perform sentiment analysis of the company's situation and strategy to emphasize positive aspects. Furthermore, it can compare the company's situation and strategy with past data to extract trends and patterns. The presentation material composition unit understands the composition of materials from the perspective of a presentation to the boss's boss. For example, the generation AI analyzes the boss's past presentation materials and comments to determine in advance how to structure the materials in a way that is easy to understand from the boss's perspective. The generation AI can also estimate the emotional state of the boss's boss and create presentation materials tailored to that emotion. Furthermore, the generation AI can analyze the boss's boss's past presentation materials and emphasize specific keywords and phrases to create materials that will attract the boss's boss's attention. This allows the document quality improvement system to efficiently improve the quality of materials before meetings with the boss. For example, by covering all the key points raised in advance, feedback from the boss can be incorporated in advance, reducing rework. Furthermore, by incorporating the boss's information and thoughts, materials can be created that meet the boss's expectations.Furthermore, by reflecting the company's situation and strategy in real time, materials can be created based on the latest information, which reduces meeting preparation time and improves the efficiency of document creation.

[0060] The pointed out points comprehensive unit can perform sentiment analysis of the pointed out points and emphasize positive feedback. The pointed out points comprehensive unit, for example, uses generation AI to analyze past meeting records and feedback data and perform sentiment analysis of the pointed out points. In order to emphasize positive feedback, the feedback content is reconstructed based on the sentiment score. In addition, sentiment analysis is performed on the pointed out points and a template for emphasizing positive feedback is generated. For example, feedback with a high positive sentiment score is displayed preferentially. In addition, sentiment analysis is used to build an automatic generation system for emphasizing positive feedback on the pointed out points. For example, feedback with a high positive sentiment score is highlighted. In this way, the quality of the material is improved by emphasizing positive feedback.

[0061] The Point of Issue Comprehension Unit prioritizes the points raised based on the supervisor's past evaluation trends, allowing the more important points to be corrected first. The Point of Issue Comprehension Unit, for example, uses generation AI to analyze the supervisor's past evaluation trends and prioritize the points raised. It generates a list for correcting the more important points first. It also develops an algorithm to prioritize the points raised based on the supervisor's past evaluation trends. For example, it identifies the more important points based on past feedback data. It also builds a system for prioritizing the points raised, reflecting the supervisor's past evaluation trends. For example, it automatically displays the more important points at the top of the list. This allows the more important points to be corrected first, improving the quality of the document.

[0062] The point-of-remarks comprehensive unit customizes the points of criticism to suit the individual preferences of the supervisor, enabling more individualized responses. The point-of-remarks comprehensive unit, for example, uses generation AI to analyze the individual preferences and style of the supervisor and customizes the points of criticism. For example, it reflects the expressions and formats preferred by the supervisor. It also builds a system that customizes the points of criticism based on the individual preferences and style of the supervisor. For example, it customizes based on the supervisor's past feedback data. It also generates templates for customizing the points of criticism to reflect the individual preferences and style of the supervisor. For example, it automatically applies the wording and layout preferred by the supervisor. This makes it possible to create more effective materials by customizing them to suit the individual preferences and style of the supervisor.

[0063] The pointed out points comprehensive unit can compare the pointed out points with feedback data from different industries or fields and extract common improvement points. The pointed out points comprehensive unit, for example, uses generative AI to collect feedback data from different industries and fields and compare it with the pointed out points. It extracts common improvement points and reflects them in the materials. It also develops an algorithm that analyzes feedback data from different industries and fields and identifies common points with the pointed out points. For example, it lists common improvement points. It also builds a system that compares the pointed out points with feedback data from different industries and fields and extracts common improvement points. For example, it automatically highlights common improvement points. In this way, by comparing with feedback data from different industries and fields, common improvement points can be extracted and the quality of the materials can be improved.

[0064] The pointed out points comprehensive unit can present the pointed out points in a multimodal format including visual or audio data to deepen understanding. The pointed out points comprehensive unit, for example, uses generative AI to build a system that presents the pointed out points in a multimodal format including visual and audio data. For example, it adds graphs and audio commentary. It also generates templates for presenting the pointed out points in a multimodal format. For example, it creates presentation materials that combine visual data and audio data. It also develops algorithms that present the pointed out points in a multimodal format using visual and audio data. For example, it automatically generates graphs and charts that are visually easy to understand. This allows the use of visual and audio data to deepen understanding of the pointed out points.

[0065] The pointed-out point comprehensive unit can use the emotion estimation function to collect the user's emotional reactions to the pointed-out points and make suggestions to elicit a positive reaction. The pointed-out point comprehensive unit, for example, uses the emotion estimation function to build a system that collects the user's emotional reactions to the pointed-out points in real time. For example, it analyzes the user's facial expressions and voice and calculates an emotion score. It also develops an algorithm that makes suggestions to elicit a positive reaction based on the user's emotional reaction data. For example, it prioritizes displaying feedback with a high positive emotion score. It also builds a system that uses the emotion estimation data to collect the user's emotional reactions to the pointed-out points and makes suggestions to elicit a positive reaction. For example, it automatically generates feedback that emphasizes positive emotions. In this way, the quality of the material is improved by collecting the user's emotional reactions and making suggestions to elicit a positive reaction.

[0066] The boss information reflection unit can estimate the boss's emotional state and provide information based on that emotion. The boss information reflection unit, for example, uses generative AI to build a system that estimates the boss's emotional state in real time. For example, it analyzes the boss's facial expressions and voice and calculates an emotion score. It also develops an algorithm that provides information tailored to the boss's emotional state. For example, it provides detailed information when the boss is relaxed and provides concise information when the boss is stressed. It also builds a system that provides information tailored to the boss's emotional state based on the emotion estimation data. For example, it adjusts the way information is presented depending on the boss's emotion score. This allows the boss to understand the boss better by providing information tailored to their emotional state.

[0067] The supervisor information reflection unit can develop an algorithm for tracking the evolution of a supervisor's thoughts over time and reflecting the latest thoughts. The supervisor information reflection unit, for example, uses generative AI to build a system for tracking the evolution of a supervisor's thoughts over time. For example, it organizes the supervisor's comments and notes in chronological order and visualizes the changes. It also develops an algorithm for reflecting the supervisor's latest thoughts. For example, it identifies the latest thoughts based on the supervisor's past comment data and reflects them in documents. It also builds a system for tracking the evolution of a supervisor's thoughts over time and reflecting the latest thoughts. For example, it analyzes the supervisor's comment history and automatically reflects the latest thoughts in documents. In this way, the quality of documents is improved by reflecting the supervisor's latest thoughts.

[0068] The supervisor information reflection unit compares supervisor information with information on supervisors from different cultures or regions to gain insights from a global perspective. The supervisor information reflection unit, for example, uses generative AI to build a system that compares supervisor information with information on supervisors from different cultures or regions. For example, to gain insights from a global perspective, it collects speech data from supervisors from different cultures. It also develops an algorithm that analyzes information on supervisors from different cultures or regions and compares it with the supervisor information. For example, it identifies differences between cultures or regions and reflects them in documents. It also builds a system that compares supervisor information with information on supervisors from different cultures or regions to gain insights from a global perspective. For example, it gains insights based on speech data from supervisors from different cultures. This allows it to gain insights from a global perspective and improve the quality of documents.

[0069] The supervisor information reflection unit can convert the supervisor's information into visual notes or mind maps to make it easier to understand visually. The supervisor information reflection unit, for example, uses generation AI to build a system that converts the supervisor's information into visual notes or mind maps. For example, it visually organizes the supervisor's comments and notes. It also develops an algorithm that automatically generates visual notes and mind maps to make the supervisor's information easier to understand visually. For example, it shows important points with diagrams or icons. It also builds a system that converts the supervisor's information into visual notes or mind maps to make it easier to understand visually. For example, it creates visual materials based on the supervisor's comment data. This makes the supervisor's information easier to understand visually, improving the quality of the materials.

[0070] The boss information reflection unit can use the emotion estimation function to collect the user's emotional reactions to the boss's information and optimize the information presentation method based on that. The boss information reflection unit, for example, uses the emotion estimation function to build a system that collects the user's emotional reactions to the boss's information in real time. For example, it analyzes the user's facial expressions and voice and calculates an emotion score. It also develops an algorithm that optimizes the boss's information presentation method based on the user's emotional reaction data. For example, it prioritizes the adoption of an information presentation method with a high positive emotion score. It also builds a system that uses the emotion estimation data to collect the user's emotional reactions to the boss's information and optimizes the information presentation method based on that. For example, it adjusts the information presentation method according to the user's emotion score. In this way, the quality of materials is improved by collecting the user's emotional reactions and optimizing the information presentation method based on that.

[0071] The Company Situation Reflection Department can perform sentiment analysis on the company's situation and emphasize positive elements. The Company Situation Reflection Department, for example, uses generative AI to build a system that performs sentiment analysis on the company's situation and strategy. For example, it analyzes internal data and reports and calculates sentiment scores. It also develops an algorithm that performs sentiment analysis on the company's situation and strategy and emphasizes positive elements. For example, it highlights elements with high positive sentiment scores. It also uses sentiment analysis to build an automatic generation system to emphasize positive elements on the company's situation and strategy. For example, it prioritizes presenting information with high positive sentiment scores. This improves the quality of materials by emphasizing positive elements.

[0072] The Company Situation Reflection Department can compare the company's situation or strategy with past data and extract trends or patterns. The Company Situation Reflection Department, for example, uses generative AI to build a system that compares the company's situation and strategy with past data. For example, it analyzes sales data and market trends over time to extract trends. It also develops algorithms that compare past data with current data and extract trends and patterns. For example, it identifies increases or decreases in sales and fluctuations in market share. It also builds a system that compares the company's situation and strategy with past data and extracts trends and patterns. For example, it identifies trends based on past successes and failures. By comparing with past data, it can extract trends and patterns and improve the quality of the materials.

[0073] The Company Situation Reflection Department can simulate the company's situation or strategy based on different scenarios and propose the optimal strategy. The Company Situation Reflection Department, for example, uses generative AI to build a system that simulates the company's situation and strategy based on different scenarios. For example, it sets multiple scenarios and compares the results of each. It also develops an algorithm that simulates the company's situation and strategy based on different scenarios and proposes the optimal strategy. For example, it sets a risk scenario and a growth scenario and identifies the optimal strategy. It also builds a system that simulates the company's situation and strategy based on different scenarios and proposes the optimal strategy. For example, it visualizes the results of each scenario and selects the optimal strategy. In this way, it can propose the optimal strategy by simulating based on different scenarios and improve the quality of the materials.

[0074] The Company Situation Reflection Department can compare the company's situation or strategy with data from different industries or markets to gain new insights. The Company Situation Reflection Department, for example, uses generative AI to build a system that compares the company's situation and strategy with data from different industries and markets. For example, it collects and compares sales data and market trends from different industries. It also develops algorithms that analyze data from different industries and markets and compare it with the company's situation and strategy. For example, it gains insights based on success stories and failures from different industries. It also builds a system that compares the company's situation and strategy with data from different industries and markets to gain new insights. For example, it adjusts strategies based on trends in different markets. In this way, by comparing with data from different industries and markets, new insights can be gained and the quality of the materials can be improved.

[0075] The Company Situation Reflection Department can convert the company's situation or strategy into visuals or infographics to make it easier to understand visually. The Company Situation Reflection Department, for example, uses generative AI to build a system that converts the company's situation or strategy into visuals or infographics. For example, sales data and market trends are displayed in graphs and charts. The department also develops algorithms that automatically generate visuals and infographics to make the company's situation and strategy easier to understand visually. For example, important data is displayed using diagrams and icons. The department also builds a system that converts the company's situation and strategy into visuals or infographics to make them easier to understand visually. For example, visual materials are created based on data. In this way, the company's situation and strategy can be visually easier to understand by using visuals and infographics.

[0076] The company situation reflection unit can use the emotion estimation function to collect users' emotional reactions to the company's situation or strategy, and optimize the strategy presentation method based on that. The company situation reflection unit, for example, uses the emotion estimation function to build a system that collects users' emotional reactions to the company's situation or strategy in real time. For example, it analyzes the user's facial expressions and voice and calculates an emotion score. It also develops an algorithm that optimizes the company's situation and strategy presentation method based on the user's emotional reaction data. For example, it prioritizes the adoption of an information presentation method with a high positive emotion score. It also builds a system that uses the emotion estimation data to collect users' emotional reactions to the company's situation and strategy, and optimizes the strategy presentation method based on that. For example, it adjusts the information presentation method according to the user's emotion score. In this way, the quality of materials is improved by collecting users' emotional reactions and optimizing the strategy presentation method based on that.

[0077] The presentation material composition unit can create materials that will attract the interest of the boss's boss by analyzing past presentation materials from the boss's boss and emphasizing specific keywords or phrases. The presentation material composition unit, for example, uses a generation AI to analyze past presentation materials from the boss's boss and build a system that extracts specific keywords and phrases. For example, it highlights words frequently used by the boss's boss. It also develops an algorithm that emphasizes specific keywords and phrases to attract the interest of the boss's boss. For example, it identifies important keywords based on past speech data from the boss's boss. It also builds a system that analyzes past presentation materials from the boss's boss and emphasizes specific keywords and phrases to automatically generate materials that will attract the interest of the boss's boss. For example, it highlights topics that will interest the boss's boss. This improves the quality of the materials by creating materials that will attract the interest of the boss's boss.

[0078] The presentation material composition unit can develop an algorithm for tracking the evolution of the boss's boss's thoughts over time and reflecting the latest thoughts. The presentation material composition unit, for example, uses generative AI to build a system for tracking the evolution of the boss's boss's thoughts over time. For example, it organizes the boss's boss's comments and notes in chronological order and visualizes the changes. It also develops an algorithm for reflecting the boss's boss's latest thoughts. For example, it identifies the latest thoughts based on the boss's boss's past comment data and reflects them in the materials. It also builds a system for tracking the evolution of the boss's boss's thoughts over time and reflecting the latest thoughts. For example, it analyzes the comment history of the boss's boss and automatically reflects the latest thoughts in the materials. In this way, the quality of the materials is improved by reflecting the boss's boss's latest thoughts.

[0079] The presentation material composition unit compares information about the boss's boss with information about the boss's boss from a different culture or region to gain insights from a global perspective. The presentation material composition unit, for example, uses generative AI to build a system that compares information about the boss's boss with information about the boss's boss from a different culture or region. For example, to gain insights from a global perspective, the unit collects speech data from the boss's boss from a different culture. The unit also develops an algorithm that analyzes the information about the boss's boss from a different culture or region and compares it with information about the boss's boss. For example, the unit identifies differences between cultures and regions and reflects them in the materials. The unit also builds a system that compares information about the boss's boss with information about the boss's boss from a different culture or region to gain insights from a global perspective. For example, insights are gained based on speech data from the boss's boss from a different culture. This allows insights from a global perspective to be gained, improving the quality of the materials.

[0080] The presentation material composition unit can convert the information about the boss's boss into visual notes or mind maps to make it easier to understand visually. The presentation material composition unit, for example, uses generation AI to build a system that converts the information about the boss's boss into visual notes or mind maps. For example, it visually organizes the remarks and notes of the boss's boss. It also develops an algorithm that automatically generates visual notes and mind maps to make the information about the boss's boss easier to understand visually. For example, it indicates important points with diagrams and icons. It also builds a system that converts the information about the boss's boss into visual notes or mind maps to make it easier to understand visually. For example, it creates visual materials based on the remarks data of the boss's boss. This makes the information about the boss's boss easier to understand visually, improving the quality of the materials.

[0081] The presentation material composition unit can use the emotion estimation function to collect users' emotional reactions to information about their boss's boss and optimize the information presentation method based on that. The presentation material composition unit, for example, uses the emotion estimation function to build a system that collects users' emotional reactions to information about their boss's boss in real time. For example, the system analyzes the user's facial expressions and voice and calculates an emotion score. The presentation material composition unit also develops an algorithm that optimizes the presentation method for information about their boss's boss based on the user's emotional reaction data. For example, the system prioritizes the adoption of an information presentation method with a high positive emotion score. The presentation material composition unit also uses the emotion estimation data to collect users' emotional reactions to information about their boss's boss and builds a system that optimizes the information presentation method based on that. For example, the system adjusts the information presentation method according to the user's emotion score. In this way, the system improves the quality of the presentation materials by collecting users' emotional reactions and optimizing the information presentation method based on that.

[0082] The document correction department can perform sentiment analysis on document corrections and emphasize positive feedback. The document correction department, for example, uses generative AI to build a system that performs sentiment analysis on document corrections. For example, it calculates a sentiment score for the content of the corrections and emphasizes positive feedback. It also performs sentiment analysis on document corrections and develops an algorithm that emphasizes positive feedback. For example, it preferentially displays corrections with a high positive sentiment score. It also uses sentiment analysis to build an automatic generation system for emphasizing positive feedback on document corrections. For example, it highlights feedback with a high positive sentiment score. In this way, emphasizing positive feedback improves the quality of the document.

[0083] The document revision department can track the revision history of documents and extract the most effective revision patterns. The document revision department, for example, uses generative AI to build a system that tracks the revision history of documents. For example, it records the content of revisions and the number of revisions and extracts effective revision patterns. It also analyzes the revision history of documents and develops an algorithm that extracts the most effective revision patterns. For example, it identifies effective revision patterns based on past revision data. It also builds a system that tracks the revision history of documents and extracts the most effective revision patterns. For example, it visualizes the revision history and highlights effective revision patterns. In this way, it can track the revision history, extract the most effective revision patterns, and improve the quality of documents.

[0084] The document correction unit customizes document corrections to suit the individual preferences of the user, thereby further strengthening the individual response. The document correction unit, for example, uses a generative AI to build a system that customizes document corrections to suit the individual preferences and style of the user. For example, it reflects the user's preferred expressions and formats. It also develops an algorithm that customizes document corrections based on the user's individual preferences and style. For example, it customizes based on the user's past correction data. It also generates templates for customizing document corrections to suit the user's individual preferences and style. For example, it automatically applies the user's preferred wording and layout. This allows more effective documents to be created by customizing the documents to suit the user's individual preferences and style.

[0085] The document correction department can compare the document corrections with feedback data from different industries or fields and extract the common areas for improvement. The document correction department, for example, uses generative AI to collect feedback data from different industries or fields and compare it with the document corrections. It extracts common areas for improvement and reflects them in the document. It also analyzes feedback data from different industries and fields and develops an algorithm to identify commonalities with the document corrections. For example, it lists common areas for improvement. It also builds a system that compares the document corrections with feedback data from different industries and fields and extracts common areas for improvement. For example, it automatically highlights common areas for improvement. In this way, by comparing with feedback data from different industries and fields, common areas for improvement can be extracted and the quality of the document can be improved.

[0086] The document correction unit can present the document corrections in the multimodal format including the visual or audio data to deepen the understanding. The document correction unit, for example, uses a generative AI to build a system that presents the document corrections in a multimodal format including visual and audio data. For example, graphs and audio commentary are added. Also, a template is generated for presenting the document corrections in a multimodal format. For example, a presentation material that combines visual data and audio data is created. Also, an algorithm is developed to present the document corrections in a multimodal format using visual and audio data. For example, graphs and charts that are easy to understand visually are automatically generated. This allows the use of visual and audio data to deepen understanding of the document corrections.

[0087] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0088] The materials quality improvement system can further include a learning style adaptation unit that analyzes the user's learning history and creates materials tailored to each individual's learning style. For example, the system can identify the user's learning style by analyzing what materials the user has created in the past and the feedback they have received. It can also develop an algorithm that customizes the structure and content of materials based on the user's learning style. For example, it can make extensive use of graphs and charts for visual learners and add audio commentary for auditory learners. The learning style adaptation unit can also generate templates tailored to the user's learning style, supporting efficient material creation. This can improve the quality of materials by creating materials optimized for the user's learning style.

[0089] The document quality improvement system may further include an emotion adaptation unit that estimates the user's emotional state and adjusts the tone and style of the document based on the estimated emotion. For example, if the user is feeling stressed, concise and clear information is provided, and if the user is relaxed, detailed information is provided. The emotion adaptation unit may also develop an algorithm that adjusts the color and font of the document based on the user's emotional state. For example, bright colors may be used to elicit positive emotions, and calm colors may be used to alleviate negative emotions. The emotion adaptation unit may also generate templates that match the user's emotional state and assist in document creation. This allows the quality of the document to be improved by creating documents optimized for the user's emotional state.

[0090] The document quality improvement system can also include a cultural adaptation section that collects feedback data from different cultures and regions and gains insights from a global perspective. For example, it can analyze feedback data from superiors and colleagues from different cultures to extract common areas for improvement and culturally specific points. The cultural adaptation section can also develop algorithms that adjust the content and structure of documents based on feedback data from different cultures and regions. For example, it can reflect culturally specific expressions and formats. The cultural adaptation section can also generate templates tailored to different cultures and regions, supporting document creation from a global perspective. This can improve the quality of documents by creating documents optimized for different cultures and regions.

[0091] The document quality improvement system can further include a success story analysis unit that analyzes the user's past success stories and failure stories and proposes the optimal method for creating documents. For example, it analyzes documents created by the user in the past and their results to identify the factors that led to success and failure. The success story analysis unit also develops an algorithm that optimizes the structure and content of documents based on past success stories. For example, it uses the structure and expression of successful documents as a reference. The success story analysis unit also generates templates based on the user's past success stories and failure stories to support document creation. This makes it possible to improve the quality of documents by utilizing past success stories and failure stories.

[0092] The document quality improvement system may further include an emotional feedback unit that estimates the user's emotional state and adjusts the content of the feedback based on the estimated emotion. For example, detailed feedback is provided when the user has positive emotions, and brief feedback is provided when the user has negative emotions. The emotional feedback unit also develops an algorithm that adjusts the tone and style of the feedback based on the user's emotional state. For example, encouraging words are used to elicit positive emotions, and kind words are used to alleviate negative emotions. The emotional feedback unit also generates feedback templates tailored to the user's emotional state to assist in document creation. This allows the quality of the document to be improved by providing feedback optimized for the user's emotional state.

[0093] The document quality improvement system can further include an environment adaptation unit that analyzes the user's work environment and suggests the optimal work environment. For example, it can analyze the volume, lighting, and temperature of the user's work environment to identify the optimal environmental conditions. The environment adaptation unit can also develop an algorithm that makes suggestions to improve the efficiency of document creation based on the user's work environment. For example, it can recommend working in a quiet environment and set appropriate lighting and temperature. The environment adaptation unit can also generate templates tailored to the user's work environment to support efficient document creation. This can improve the quality of documents by providing the optimal work environment.

[0094] The document quality improvement system may further include an emotion revision suggestion unit that estimates the user's emotional state and makes document revision suggestions based on the estimated emotion. For example, if the user is feeling stressed, concise and clear revision suggestions are made, and if the user is relaxed, detailed revision suggestions are made. The emotion revision suggestion unit also develops an algorithm that adjusts the tone and style of the revision suggestions based on the user's emotional state. For example, encouraging words may be used to elicit positive emotions, and kind words may be used to alleviate negative emotions. The emotion revision suggestion unit also generates revision suggestion templates tailored to the user's emotional state to assist in document creation. This allows the quality of the document to be improved by providing revision suggestions optimized for the user's emotional state.

[0095] The document quality improvement system can further include a work schedule optimization unit that analyzes the user's work patterns and proposes an optimal work schedule. For example, it analyzes the user's past work history and identifies efficient work times and break times. The work schedule optimization unit also develops an algorithm that proposes an optimal work schedule based on the user's work patterns. For example, it places important work during times when concentration is highest, with appropriate breaks between each. The work schedule optimization unit also generates a schedule template that matches the user's work patterns, supporting efficient document creation. This allows the provision of an optimal work schedule to improve the quality of documents.

[0096] The document quality improvement system can further include an emotion evaluation unit that estimates the user's emotional state and evaluates the document based on the estimated emotion. For example, if the user has positive emotions, a detailed evaluation is made, and if the user has negative emotions, a brief evaluation is made. The emotion evaluation unit also develops an algorithm that adjusts the tone and style of the evaluation based on the user's emotional state. For example, encouraging words are used to elicit positive emotions, and kind words are used to alleviate negative emotions. The emotion evaluation unit also generates an evaluation template tailored to the user's emotional state to assist in document creation. This allows the quality of the document to be improved by providing an evaluation optimized for the user's emotional state.

[0097] The document quality improvement system can further include a history analysis unit that analyzes the user's past document creation history and suggests the optimal document creation method. For example, it analyzes documents created by the user in the past and the results to identify effective document creation methods. The history analysis unit also develops an algorithm that optimizes the structure and content of documents based on the user's past document creation history. For example, it refers to the structure and expression of successful documents. The history analysis unit also generates templates based on the user's past document creation history to assist in document creation. This makes it possible to improve the quality of documents by utilizing the user's past document creation history.

[0098] The processing flow of the second embodiment will be briefly explained below.

[0099] Step 1: The point-reporting unit covers all the points that have been pointed out. For example, the generation AI analyzes past meeting records and feedback data to list the points that have been pointed out. The generation AI can also perform sentiment analysis of the points that have been pointed out and emphasize positive feedback. Furthermore, the generation AI can prioritize the points that have been pointed out based on the supervisor's past evaluation trends and correct the most important points first. Step 2: The supervisor information reflection unit reflects the supervisor's information and thoughts. For example, the generation AI analyzes the supervisor's past statements, notes, and emails, and reflects the information the supervisor has grasped and the direction of their thinking in the document. The generation AI can also estimate the supervisor's emotional state and provide information tailored to that emotion. Furthermore, the generation AI can analyze the supervisor's past statements and notes, and create documents that will attract the supervisor's attention by emphasizing specific keywords and phrases. Step 3: The company situation reflection unit reflects the company's situation and strategy in real time. For example, the generation AI analyzes the latest internal data and reports and reflects the company's situation and strategy in the materials. The generation AI can also perform sentiment analysis on the company's situation and strategy and emphasize positive aspects. Furthermore, the generation AI can compare the company's situation and strategy with past data to extract trends and patterns. Step 4: The presentation material composition unit determines the composition of the materials from the perspective of presentation materials for the boss's boss. For example, the generation AI analyzes the boss's past presentation materials and statements to determine in advance the composition of materials that will be easy to speak from the boss's perspective. The generation AI can also estimate the emotional state of the boss's boss and create presentation materials that match those emotions. Furthermore, the generation AI can analyze the boss's boss's past presentation materials and emphasize specific keywords and phrases to create materials that will attract the interest of the boss's boss.

[0100] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0101] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0102] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0103] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0104] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0105] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0106] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0107] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0108] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0109] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0110] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0111] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0112] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0113] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0114] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0115] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0116] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0117] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

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

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

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

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

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

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

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

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

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

[0127] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

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

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

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

[0131] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

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

[0133] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0134] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0135] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0136] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0137] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0138] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0139] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0140] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0141] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0142] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0143] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0144] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0145] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0146] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0147] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0148] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0149] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0150] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0151] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0152] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0153] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0154] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0155] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0156] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0157] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0158] 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.

[0159] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0160] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0161] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0162] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0163] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0164] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0165] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0166] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0167] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a point-finding unit that covers all the points that are pointed out; a supervisor information reflecting unit that reflects information about a supervisor; A company status reflection department that reflects the company's status in real time; A presentation materials composition department will be in charge of structuring materials from the perspective of presentation materials for the boss's boss. A system characterized by:

2. The pointed out point comprehensive unit Perform sentiment analysis on points raised and highlight positive feedback 2. The system of claim 1.

3. The pointed out point comprehensive unit Compare the above findings with feedback data from different industries or fields to identify common areas for improvement.

2. The system of claim 1.

4. The supervisor information reflecting unit Estimate the boss' emotional state and provide information based on that emotion 2. The system of claim 1.

5. The company status reflection unit Conduct a sentiment analysis of the company's situation and highlight the positive aspects 2. The system of claim 1.

6. The presentation material composition unit Estimate the emotional state of your boss's boss and create a presentation based on that emotion.

2. The system of claim 1.

7. The document correction department Conduct sentiment analysis on document revisions and highlight positive feedback 2. The system of claim 1.

8. The pointed out point comprehensive unit Collect users' emotional responses to the points mentioned above and make suggestions to elicit positive responses.

2. The system of claim 1.

Images