system

Abstract

The system according to this embodiment aims to digitize the know-how of craftsmen and technicians, enabling the reproduction of techniques and traditions even without successors. [Solution] The system according to the embodiment comprises a data collection unit, an analysis unit, a storage unit, a memory unit, a classification unit, and an output unit. The data collection unit digitizes the know-how of craftsmen and engineers. The analysis unit analyzes the data collected by the data collection unit. The storage unit stores the data analyzed by the analysis unit. The memory unit stores the data stored by the storage unit. The classification unit classifies the data stored by the memory unit. The output unit provides output based on the data classified by the classification unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, the know-how of craftsmen and technicians is not properly digitized, and there is a risk that technology and traditions will be lost due to a shortage of successors.

[0005] The system according to the embodiment aims to digitize the know-how of craftsmen and technicians so that technology and traditions can be reproduced even without successors.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a data collection unit, an analysis unit, a storage unit, a memory unit, a classification unit, and an output unit. The data collection unit digitizes the know-how of craftsmen and engineers. The analysis unit analyzes the data collected by the data collection unit. The storage unit stores the data analyzed by the analysis unit. The memory unit stores the data stored by the storage unit. The classification unit classifies the data stored by the memory unit. The output unit provides output based on the data classified by the classification unit. [Effects of the Invention]

[0007] The system according to this embodiment can digitize the know-how of craftsmen and technicians, making it possible to reproduce techniques and traditions even if there are no successors. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The AI ​​system according to an embodiment of the present invention is a system designed to address the crisis of traditional techniques and know-how disappearing due to a shortage of successors resulting from the declining birthrate and aging population. This system digitizes the wisdom and know-how of craftsmen and technicians, and the AI ​​analyzes, stores, remembers, and classifies it, allowing for output and reproduction when needed. For example, when digitizing the wisdom and know-how of craftsmen and technicians, various forms of data are collected, such as linguistic data and image data. This includes, for example, the amount of lacquer applied, small ingenious techniques used in making musical instruments, and unique techniques used in architecture. Next, the AI ​​analyzes, stores, remembers, and classifies the collected data. The AI ​​analyzes the data, extracts important points, and classifies them efficiently. This includes, for example, unique language used in customer service, know-how for handling complaints, and how to make old techniques and old models of machinery. Furthermore, output can be obtained from the AI ​​when needed and reproduced. For example, to reproduce old techniques, the AI ​​provides specific procedures based on the analyzed data. This makes it possible to reproduce traditional techniques and know-how even without successors. This system has strategic significance because it ensures that important technologies and traditions for a nation are passed down and can be quickly reproduced when needed, even without successors. Furthermore, for companies, it allows them to accumulate societal know-how and fulfill their role as social infrastructure. This enables AI systems to efficiently digitize, analyze, store, remember, classify, and output the know-how of craftsmen and engineers.

[0029] The AI ​​system according to this embodiment comprises a data collection unit, an analysis unit, a storage unit, a memory unit, a classification unit, and an output unit. The data collection unit digitizes the know-how of craftsmen and engineers. The data collection unit collects, for example, language data and image data. For example, the data collection unit records what a craftsman says and converts it into text data. The data collection unit can also videotape the craftsman's work and save it as image data. Furthermore, the data collection unit can scan drawings and blueprints created by craftsmen and convert them into digital data. The analysis unit analyzes the collected data. For example, the analysis unit analyzes the collected data and extracts important points. For example, the analysis unit extracts frequently occurring keywords from text data. Furthermore, the analysis unit can detect specific patterns from image data. Furthermore, the analysis unit can extract motion characteristics from video data. The storage unit stores the analyzed data. For example, the storage unit saves the analyzed data to a database. For example, the storage unit saves text data to a database. Furthermore, the storage unit can save image data to cloud storage. Furthermore, the storage unit can also perform backups for long-term storage of video data. The memory unit stores the stored data. The memory unit, for example, performs backups for long-term storage of the stored data. For example, the memory unit can perform data redundancy to prevent data loss. The memory unit can also encrypt the data to ensure security. Furthermore, the memory unit can set access permissions for the data to prevent unauthorized use. The classification unit classifies the stored data. The classification unit categorizes the stored data. For example, the classification unit classifies text data into technical categories and work procedure categories. The classification unit can also classify image data into product categories and parts categories. Furthermore, the classification unit can also classify video data into work process categories and motion pattern categories. The output unit provides specific procedures based on the classified data. For example, the output unit generates work manuals based on the classified data. For example, the output unit creates work procedure documents based on data classified into technical categories.Furthermore, the output unit can create operation guides based on data classified into product categories. In addition, the output unit can create procedure manuals based on data classified into work process categories. As a result, the AI ​​system according to this embodiment can efficiently digitize, analyze, store, remember, classify, and output the know-how of craftsmen and technicians.

[0030] The data collection unit digitizes the know-how of craftsmen and technicians. For example, it collects linguistic and image data. Specifically, it records what craftsmen say and converts it into text data using speech recognition technology. This speech recognition technology utilizes natural language processing (NLP) to accurately recognize the craftsmen's specialized terminology and unique expressions. The data collection unit also films craftsmen's work with high-resolution video cameras and saves the footage as image data. The video data is analyzed frame by frame to extract important actions and procedures. Furthermore, the data collection unit scans drawings and blueprints created by craftsmen with a high-precision scanner and converts them into digital data. This digital data is used for later analysis and classification. The data collection unit centrally manages and collects this diverse data in real time. For example, when a craftsman develops a new technology, data can be collected on the spot and immediately reflected in the system. This allows the data collection unit to efficiently and accurately digitize the know-how of craftsmen and technicians, enriching the overall knowledge base of the system.

[0031] The analysis unit analyzes the collected data. For example, the analysis unit analyzes the collected data and extracts important points. Specifically, it uses natural language processing (NLP) techniques to extract frequently occurring keywords from text data. NLP techniques can understand the context of text data and identify important keywords and phrases. It also uses image recognition techniques to detect specific patterns from image data. Image recognition techniques utilize deep learning to automatically extract features within images and detect specific patterns and anomalies. Furthermore, it uses motion analysis algorithms to extract motion features from video data. Motion analysis algorithms can analyze movement between video frames and identify specific actions and procedures. The analysis unit combines these techniques to analyze the collected data from multiple angles and extract important information. For example, it can analyze the work procedures of craftsmen and identify efficient work methods. This allows the analysis unit to analyze the collected data quickly and accurately, strengthening the knowledge base of the entire system.

[0032] The storage unit stores the analyzed data. For example, it stores the analyzed data in a database. Specifically, it stores text data in a relational database, enabling efficient searching and access. It also stores image data in cloud storage, allowing for efficient management of large amounts of data. Furthermore, it uses a dedicated video storage system for long-term storage of video data and performs backups. The storage unit centrally manages this data and makes it quickly accessible as needed. For example, when searching for data on a specific technology, the storage unit can quickly provide the relevant data. In this way, the storage unit can efficiently store the analyzed data and enhance data management throughout the entire system.

[0033] The storage unit stores accumulated data. For example, the storage unit performs backups for long-term storage of accumulated data. Specifically, it prevents data loss by implementing data redundancy and storing data on multiple storage devices. Furthermore, the storage unit ensures security by encrypting data. Encryption technology protects data confidentiality and safeguards data from unauthorized access. In addition, the storage unit sets data access permissions to prevent misuse of data. Using an access rights management system, access to data can be granted only to specific users or groups. This allows the storage unit to ensure data security and confidentiality, improving the overall reliability of the system.

[0034] The classification unit categorizes stored data. For example, it categorizes stored data. Specifically, it uses machine learning algorithms to classify text data into technical categories and work procedure categories. Machine learning algorithms can learn the characteristics of the data and automatically categorize it. It also uses image classification algorithms to classify image data into product categories and component categories. Image classification algorithms can analyze the characteristics of images and classify them into appropriate categories. Furthermore, it uses motion analysis algorithms to classify video data into work process categories and motion pattern categories. Motion analysis algorithms can analyze the motion of video data and classify it into appropriate categories. As a result, the classification unit can efficiently classify stored data and enhance data management throughout the system.

[0035] The output unit provides specific procedures based on classified data. For example, the output unit generates work manuals based on classified data. Specifically, it creates detailed work procedure manuals based on data classified into technical categories. These manuals are provided in a visually easy-to-understand format by combining text and image data. It also creates operation guides based on data classified into product categories. These operation guides explain product usage and maintenance procedures in detail, enabling users to operate the products accurately. Furthermore, it creates procedure manuals based on data classified into work process categories. These manuals can visually demonstrate specific work procedures by combining video data and motion analysis data. In this way, the output unit provides specific procedures based on classified data, supporting users in performing tasks efficiently and accurately.

[0036] The data collection unit collects language data and image data. For example, the data collection unit records what a craftsman says and converts it into text data. For example, the data collection unit records a craftsman's conversation and converts it into text data using speech recognition technology. The data collection unit can also videotape a craftsman's work and save it as image data. For example, the data collection unit films a craftsman's work with a high-resolution camera and saves it as image data. Furthermore, the data collection unit can scan drawings and blueprints created by craftsmen and convert them into digital data. For example, the data collection unit scans a handwritten drawing created by a craftsman and converts it into digital data. In this way, by collecting language data and image data, the know-how of craftsmen and technicians can be digitized in various formats. Some or all of the above processes in the data collection unit may be performed using AI, for example, or not. For example, the data collection unit can have AI perform the process of recording a craftsman's conversation and converting it into text data using speech recognition technology.

[0037] The analysis unit analyzes the collected data and extracts important points. For example, the analysis unit can extract frequently occurring keywords from text data. For example, the analysis unit can analyze text data using natural language processing technology and extract frequently occurring keywords. The analysis unit can also detect specific patterns from image data. For example, the analysis unit can analyze image data using image recognition technology and detect specific patterns. Furthermore, the analysis unit can extract motion features from video data. For example, the analysis unit can analyze video data using video analysis technology and extract motion features. This improves the accuracy of data analysis by extracting important points. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can have AI perform the process of analyzing text data using natural language processing technology and extracting frequently occurring keywords.

[0038] The storage unit stores the analyzed data. For example, the storage unit saves the analyzed data to a database. For example, the storage unit saves text data to a database. For example, the storage unit saves text data to a relational database. The storage unit can also save image data to cloud storage. For example, the storage unit uploads and saves image data to a cloud storage service. Furthermore, the storage unit can perform backups for long-term storage of video data. For example, the storage unit backs up and saves video data to external storage. This makes data storage and management more efficient by storing the analyzed data. Some or all of the above processes in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can have AI perform the process of saving text data to a relational database.

[0039] The storage unit stores the accumulated data. The storage unit can, for example, perform backups for long-term storage of the accumulated data. For example, the storage unit can perform data redundancy to prevent data loss. For example, the storage unit can distribute and store data across multiple storage devices. The storage unit can also encrypt the data to ensure security. For example, the storage unit can encrypt and store data to prevent unauthorized access. Furthermore, the storage unit can set access permissions for data to prevent unauthorized use of data. For example, the storage unit can set access permissions for data so that only specific users can access it. This makes long-term storage of data possible by storing the accumulated data. Some or all of the above processes in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can have AI perform the process of performing data redundancy.

[0040] The classification unit classifies the stored data. For example, the classification unit categorizes the stored data. For example, the classification unit classifies text data into technical categories or work procedure categories. For example, the classification unit analyzes text data using natural language processing technology and classifies it into technical categories or work procedure categories. The classification unit can also classify image data into product categories or part categories. For example, the classification unit analyzes image data using image recognition technology and classifies it into product categories or part categories. Furthermore, the classification unit can also classify video data into work process categories or motion pattern categories. For example, the classification unit analyzes video data using video analysis technology and classifies it into work process categories or motion pattern categories. By classifying the stored data in this way, data retrieval and utilization become easier. Some or all of the above processing in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can have AI perform the process of analyzing text data using natural language processing technology and classifying it into technical categories or work procedure categories.

[0041] The output unit provides specific procedures based on the classified data. For example, the output unit generates work manuals based on the classified data. For example, the output unit creates work procedure manuals based on data classified into technical categories. For example, the output unit creates work procedure manuals based on data classified into technical categories using natural language generation technology. The output unit can also create operation guides based on data classified into product categories. For example, the output unit creates operation guides based on data classified into product categories using image generation technology. Furthermore, the output unit can also create procedure manuals based on data classified into work process categories. For example, the output unit creates procedure manuals based on data classified into work process categories using video generation technology. This makes it possible to reproduce the know-how of craftsmen and technicians by providing specific procedures. Some or all of the above-described processes in the output unit may be performed using AI, for example, or without AI. For example, the output unit can have AI perform the process of creating work procedure manuals based on data classified into technical categories using natural language generation technology.

[0042] The data collection unit analyzes the craftsman's past work history and selects the optimal data collection method. For example, the data collection unit analyzes videos of past work performed by the craftsman, extracts key points, and creates interview questions. For example, the data collection unit uses video analysis technology to analyze past work videos and extract key points. The data collection unit also identifies particularly important techniques and know-how from the craftsman's past work history and focuses data collection on those. For example, the data collection unit uses text analysis technology to analyze past work history and identify important techniques and know-how. Furthermore, the data collection unit determines the optimal timing and method of data collection based on the craftsman's past work history. For example, the data collection unit uses machine learning algorithms to analyze past work history and determine the optimal timing and method of data collection. This allows for the selection of the optimal data collection method by analyzing past work history. Some or all of the above processes in the data collection unit may be performed using AI, for example, or not. For example, the data collection unit can have AI perform the process of analyzing past work videos using video analysis technology and extracting key points.

[0043] The data collection unit filters data based on the craftsman's current work status and areas of interest during data collection. For example, the data collection unit prioritizes collecting data related to the work the craftsman is currently performing. For example, the data collection unit monitors the craftsman's current work in real time and prioritizes collecting relevant data. The data collection unit also focuses on collecting data on technologies and know-how that the craftsman is particularly interested in. For example, the data collection unit understands the craftsman's areas of interest through questionnaires and interviews and prioritizes collecting relevant data. Furthermore, the data collection unit considers the craftsman's current work status and filters the data to collect it efficiently. For example, the data collection unit monitors the craftsman's work progress and collects data at the appropriate time. This allows for efficient data collection by filtering the data based on the current work status and areas of interest. Some or all of the above processing in the data collection unit may be performed using AI, or not. For example, the data collection unit can have AI perform the process of monitoring the craftsman's current work in real time and prioritizing the collection of relevant data.

[0044] The data collection unit prioritizes collecting highly relevant data, taking into account the geographical location information of the craftsman. For example, the data collection unit prioritizes collecting data related to the work the craftsman is performing in a specific area. For example, the data collection unit obtains the craftsman's geographical location information from GPS data and prioritizes collecting relevant data. The data collection unit also prioritizes collecting data on work performed by the craftsman while traveling. For example, the data collection unit analyzes the craftsman's travel history and prioritizes collecting data on work performed while traveling. Furthermore, if the craftsman is interested in working in a specific area, the data collection unit prioritizes collecting data related to that area. For example, the data collection unit identifies the craftsman's areas of interest through questionnaires or interviews and prioritizes collecting relevant data. This allows for the priority collection of highly relevant data by considering geographical location information. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can have AI perform the process of obtaining the craftsman's geographical location information from GPS data and prioritizing the collection of relevant data.

[0045] The data collection unit analyzes the social media activities of artisans and collects relevant data during data collection. For example, the data collection unit collects photos and videos of the work that artisans share on social media. For example, the data collection unit uses social media analysis technology to analyze the content of artisans' posts and collects relevant photos and videos. The data collection unit also collects data related to the techniques and know-how that artisans mention on social media. For example, the data collection unit uses text analysis technology to analyze the content of artisans' posts and collects relevant techniques and know-how. Furthermore, the data collection unit collects data on other artisans and technicians that artisans follow on social media. For example, the data collection unit uses social network analysis technology to analyze the artisan's follow network and collects relevant data. This allows for the efficient collection of relevant data by analyzing social media activities. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can have AI perform the process of analyzing the content of artisans' posts using social media analysis technology and collecting relevant photos and videos.

[0046] The analysis unit adjusts the level of detail of the analysis based on the importance of the data. For example, the analysis unit performs a detailed analysis on important data. For example, the analysis unit evaluates the importance of the data and performs a detailed analysis on important data. The analysis unit also performs a concise analysis on less important data. For example, the analysis unit evaluates the importance of the data and performs a concise analysis on less important data. Furthermore, the analysis unit determines the priority of the analysis according to the importance of the data. For example, the analysis unit evaluates the importance of the data and prioritizes the analysis of important data. This allows for efficient analysis by adjusting the level of detail of the analysis based on the importance of the data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can have AI perform the process of evaluating the importance of the data and performing a detailed analysis on important data.

[0047] The analysis unit applies different analysis algorithms depending on the data category during analysis. For example, the analysis unit applies a natural language processing algorithm to language data. For example, the analysis unit analyzes language data using natural language processing technology. The analysis unit also applies an image analysis algorithm to image data. For example, the analysis unit analyzes image data using image recognition technology. Furthermore, the analysis unit applies a video analysis algorithm to video data. For example, the analysis unit analyzes video data using video analysis technology. By applying different analysis algorithms depending on the data category, the accuracy of the analysis is improved. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can have AI perform the process of analyzing language data using natural language processing technology.

[0048] The analysis unit determines the priority of analysis based on the data collection timing during analysis. For example, the analysis unit prioritizes the analysis of recently collected data. For example, the analysis unit evaluates the data collection timing and prioritizes the analysis of recently collected data. The analysis unit also prioritizes the analysis of data collected at important times. For example, the analysis unit evaluates the data collection timing and prioritizes the analysis of data collected at important times. Furthermore, the analysis unit determines the order of analysis based on the data collection timing. For example, the analysis unit evaluates the data collection timing and determines the order of analysis. This enables efficient analysis by determining the priority of analysis based on the data collection timing. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can have AI perform the process of evaluating the data collection timing and prioritizing the analysis of recently collected data.

[0049] The analysis unit adjusts the order of analysis based on the relevance of the data during analysis. For example, the analysis unit prioritizes analyzing highly relevant data. For example, the analysis unit evaluates the relevance of the data and prioritizes analyzing highly relevant data. The analysis unit also postpones analyzing less relevant data. For example, the analysis unit evaluates the relevance of the data and postpones analyzing less relevant data. Furthermore, the analysis unit determines the order of analysis based on the relevance of the data. For example, the analysis unit evaluates the relevance of the data and determines the order of analysis. This allows for efficient analysis by adjusting the order of analysis based on the relevance of the data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can have AI perform the process of evaluating the relevance of the data and prioritizing the analysis of highly relevant data.

[0050] The storage unit optimizes the storage algorithm by referring to past stored data during storage. For example, the storage unit analyzes past stored data and selects the optimal storage algorithm. The storage unit also learns efficient storage methods from past stored data. For example, the storage unit uses machine learning algorithms to analyze past stored data and learn efficient storage methods. Furthermore, the storage unit improves the storage algorithm based on past stored data. For example, the storage unit analyzes past stored data and improves the storage algorithm. This allows the storage algorithm to be optimized by referring to past stored data. Some or all of the above processes in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can have AI perform the process of analyzing past stored data and selecting the optimal storage algorithm.

[0051] The storage unit improves the accuracy of storage by considering the interrelationships of the data during storage. For example, the storage unit analyzes the interrelationships of the data and stores related data together. For example, the storage unit analyzes the interrelationships of the data and stores related data together. The storage unit also selects an efficient storage method by considering the interrelationships of the data. For example, the storage unit analyzes the interrelationships of the data and selects an efficient storage method. Furthermore, the storage unit improves the accuracy of storage based on the interrelationships of the data. For example, the storage unit analyzes the interrelationships of the data and improves the accuracy of storage. As a result, the accuracy of storage is improved by considering the interrelationships of the data. Some or all of the above processing in the storage unit may be performed using AI, for example, or without using AI. For example, the storage unit can have AI perform the process of analyzing the interrelationships of the data and storing related data together.

[0052] The storage unit weights the stored data based on when the data was collected. For example, the storage unit assigns a higher weight to recently collected data. For example, the storage unit evaluates when the data was collected and assigns a higher weight to recently collected data. The storage unit also assigns a higher weight to data collected during important periods. For example, the storage unit evaluates when the data was collected and assigns a higher weight to data collected during important periods. Furthermore, the storage unit weights the stored data based on when the data was collected. For example, the storage unit evaluates when the data was collected and weights the stored data. This allows for the priority storage of important data by weighting the stored data based on when it was collected. Some or all of the above processing in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can have AI perform the process of evaluating when the data was collected and assigning a higher weight to recently collected data for storage.

[0053] The storage unit improves the accuracy of data storage by referring to relevant literature during storage. For example, the storage unit improves the accuracy of data storage by referring to relevant literature. For example, the storage unit improves the accuracy of data storage by analyzing relevant literature. The storage unit also selects an efficient storage method based on the relevant literature. For example, the storage unit analyzes relevant literature and selects an efficient storage method. Furthermore, the storage unit improves the storage algorithm by referring to relevant literature. For example, the storage unit analyzes relevant literature and improves the storage algorithm. As a result, the accuracy of data storage is improved by referring to relevant literature. Some or all of the above processes in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can have AI perform the process of analyzing relevant literature and improving the accuracy of data storage.

[0054] The memory unit optimizes the memory algorithm by referring to past memory data during memory storage. For example, the memory unit analyzes past memory data and selects the optimal memory algorithm. The memory unit also learns efficient memory methods from past memory data. For example, the memory unit uses machine learning algorithms to analyze past memory data and learn efficient memory methods. Furthermore, the memory unit improves the memory algorithm based on past memory data. For example, the memory unit analyzes past memory data and improves the memory algorithm. This allows the memory algorithm to be optimized by referring to past memory data. Some or all of the above processes in the memory unit may be performed using AI, for example, or without AI. For example, the memory unit can have AI perform the process of analyzing past memory data and selecting the optimal memory algorithm.

[0055] The memory unit improves the accuracy of memory by considering the interrelationships of data during storage. For example, the memory unit analyzes the interrelationships of data and stores related data together. For example, the memory unit analyzes the interrelationships of data and stores related data together. The memory unit also selects an efficient storage method by considering the interrelationships of data. For example, the memory unit analyzes the interrelationships of data and selects an efficient storage method. Furthermore, the memory unit improves the accuracy of memory based on the interrelationships of data. For example, the memory unit analyzes the interrelationships of data and improves the accuracy of memory. Thus, the accuracy of memory is improved by considering the interrelationships of data. Some or all of the above processing in the memory unit may be performed using AI, for example, or without AI. For example, the memory unit can have AI perform the process of analyzing the interrelationships of data and storing related data together.

[0056] The memory unit weights the stored data based on when the data was collected. For example, the memory unit assigns a higher weight to recently collected data. For example, the memory unit evaluates when the data was collected and assigns a higher weight to recently collected data. The memory unit also assigns a higher weight to data collected at important times. For example, the memory unit evaluates when the data was collected and assigns a higher weight to data collected at important times. Furthermore, the memory unit weights the stored data based on when the data was collected. For example, the memory unit evaluates when the data was collected and weights the stored data. This allows important data to be stored preferentially by weighting the stored data based on when it was collected. Some or all of the above processing in the memory unit may be performed using AI, for example, or without AI. For example, the memory unit can have AI perform the process of evaluating when the data was collected and assigning a higher weight to recently collected data.

[0057] The memory unit improves the accuracy of memory by referring to relevant literature on the data during storage. For example, the memory unit improves the accuracy of memory by referring to relevant literature on the data. For example, the memory unit improves the accuracy of memory by analyzing relevant literature. The memory unit also selects an efficient storage method based on the relevant literature. For example, the memory unit analyzes relevant literature and selects an efficient storage method. Furthermore, the memory unit improves the storage algorithm by referring to relevant literature. For example, the memory unit analyzes relevant literature and improves the storage algorithm. As a result, the accuracy of memory is improved by referring to relevant literature on the data. Some or all of the above processing in the memory unit may be performed using AI, for example, or without AI. For example, the memory unit can have AI perform the process of analyzing relevant literature and improving the accuracy of memory.

[0058] The classification unit improves the accuracy of classification by considering the interrelationships of the data during classification. For example, the classification unit analyzes the interrelationships of the data and classifies related data together. For example, the classification unit analyzes the interrelationships of the data and classifies related data together. The classification unit also selects an efficient classification method by considering the interrelationships of the data. For example, the classification unit analyzes the interrelationships of the data and selects an efficient classification method. Furthermore, the classification unit improves the accuracy of classification based on the interrelationships of the data. For example, the classification unit analyzes the interrelationships of the data and improves the accuracy of classification. As a result, the accuracy of classification is improved by considering the interrelationships of the data. Some or all of the above processes in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can have AI perform the process of analyzing the interrelationships of the data and classifying related data together.

[0059] The classification unit considers the attribute information of the data submitter when classifying data. For example, if the data submitter is a craftsman, the classification unit classifies the data based on their skills and know-how. For example, the classification unit analyzes the submitter's attribute information and classifies the data based on the craftsman's skills and know-how. Also, if the data submitter is an engineer, the classification unit classifies the data based on their field of expertise. For example, the classification unit analyzes the submitter's attribute information and classifies the data based on the engineer's field of expertise. Furthermore, the classification unit selects the optimal classification method based on the attribute information of the data submitter. For example, the classification unit analyzes the submitter's attribute information and selects the optimal classification method. This makes it possible to perform more appropriate classification by considering the attribute information of the data submitter. Some or all of the above processing in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can have AI perform the process of analyzing the submitter's attribute information and classifying the data based on the craftsman's skills and know-how.

[0060] The classification unit considers the geographical distribution of the data when classifying it. For example, the classification unit analyzes the geographical distribution of the data and classifies it by region. For example, the classification unit analyzes the geographical distribution and classifies it by region. The classification unit also classifies related data together based on the geographical distribution. For example, the classification unit analyzes the geographical distribution and classifies related data together. Furthermore, the classification unit selects an efficient classification method considering the geographical distribution. For example, the classification unit analyzes the geographical distribution and selects an efficient classification method. This makes it possible to classify data appropriately by region by considering its geographical distribution. Some or all of the above processes in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can have AI perform the process of analyzing the geographical distribution and classifying it by region.

[0061] The classification unit improves the accuracy of classification by referring to relevant literature for the data during the classification process. For example, the classification unit improves the accuracy of classification by referring to relevant literature for the data. For example, the classification unit improves the accuracy of classification by analyzing relevant literature. The classification unit also selects an efficient classification method based on the relevant literature. For example, the classification unit analyzes relevant literature and selects an efficient classification method. Furthermore, the classification unit improves the classification algorithm by referring to relevant literature. For example, the classification unit analyzes relevant literature and improves the classification algorithm. As a result, the accuracy of classification is improved by referring to relevant literature for the data. Some or all of the above processes in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can have AI perform the process of analyzing relevant literature and improving the accuracy of classification.

[0062] The output unit adjusts the level of detail of the output based on the importance of the data. For example, the output unit provides detailed output for important data. For example, the output unit evaluates the importance of the data and provides detailed output for important data. The output unit also provides concise output for less important data. For example, the output unit evaluates the importance of the data and provides concise output for less important data. Furthermore, the output unit determines the priority of the output according to the importance of the data. For example, the output unit evaluates the importance of the data and prioritizes outputting important data. This allows for efficient information provision by adjusting the level of detail of the output based on the importance of the data. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can have AI perform the process of evaluating the importance of the data and providing detailed output for important data.

[0063] The output unit applies different output algorithms depending on the data category during output. For example, the output unit applies a natural language generation algorithm to language data. For example, the output unit outputs language data using natural language generation technology. The output unit also applies an image generation algorithm to image data. For example, the output unit outputs image data using image generation technology. Furthermore, the output unit applies a video generation algorithm to video data. For example, the output unit outputs video data using video generation technology. By applying different output algorithms depending on the data category, the accuracy of information provision is improved. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can have AI perform the process of outputting language data using natural language generation technology.

[0064] The output unit adjusts the order of outputs based on the data collection timing. For example, the output unit prioritizes outputting recently collected data. For example, the output unit evaluates the data collection timing and prioritizes outputting recently collected data. The output unit also prioritizes outputting data collected during important periods. For example, the output unit evaluates the data collection timing and prioritizes outputting data collected during important periods. Furthermore, the output unit determines the order of outputs based on the data collection timing. For example, the output unit evaluates the data collection timing and determines the order of outputs. This allows for the priority provision of the latest information by adjusting the order of outputs based on the data collection timing. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can have AI perform the process of evaluating the data collection timing and prioritizing the output of recently collected data.

[0065] The output unit adjusts the order of outputs based on the relevance of the data during output. For example, the output unit prioritizes outputting highly relevant data. For example, the output unit evaluates the relevance of the data and prioritizes outputting highly relevant data. The output unit also postpones outputting less relevant data. For example, the output unit evaluates the relevance of the data and postpones outputting less relevant data. Furthermore, the output unit determines the order of outputs based on the relevance of the data. For example, the output unit evaluates the relevance of the data and determines the order of outputs. This allows for the priority provision of highly relevant information by adjusting the order of outputs based on the relevance of the data. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can have AI perform the process of evaluating the relevance of the data and prioritizing the output of highly relevant data.

[0066] The output unit improves the accuracy of the output based on user feedback during output. For example, the output unit analyzes user feedback to improve the accuracy of the output. For example, the output unit analyzes user feedback to improve the accuracy of the output. The output unit also selects an efficient output method based on user feedback. For example, the output unit analyzes user feedback to select an efficient output method. Furthermore, the output unit improves the output algorithm by referring to user feedback. For example, the output unit analyzes user feedback to improve the output algorithm. This improves the accuracy of the output based on user feedback, enabling the provision of more appropriate information. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can have AI perform the process of analyzing user feedback and improving the accuracy of the output.

[0067] The output unit selects the optimal display method when outputting, taking into account the user's device information. For example, if the user is using a smartphone, the output unit provides a display method that matches the screen size. For example, the output unit analyzes the user's device information and provides a display method optimized for the smartphone screen size. Also, if the user is using a tablet, the output unit provides a display method optimized for the larger screen. For example, the output unit analyzes the user's device information and provides a display method optimized for the tablet screen size. Furthermore, if the user is using a smartwatch, the output unit provides a concise and highly visible display method. For example, the output unit analyzes the user's device information and provides a display method optimized for the smartwatch screen size. In this way, the optimal display method can be provided by taking the user's device information into consideration. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can have AI perform the process of analyzing the user's device information and providing a display method optimized for the smartphone screen size.

[0068] The output unit provides multilingual output according to the user's language settings when outputting. For example, the output unit automatically sets the output language based on the language settings of the user's device. For example, the output unit analyzes the user's device information and automatically sets the output language based on the language settings. The output unit also provides a language switching function when the user uses multiple languages. For example, the output unit analyzes the user's language settings and provides output that supports multiple languages. Furthermore, if the user selects a specific language, the output unit provides output in that language. For example, the output unit analyzes the user's language settings and provides output in the selected language. This makes it possible to provide information that is easy for the user to understand by providing multilingual output according to the user's language settings. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can have AI perform the process of analyzing the user's device information and automatically setting the output language based on the language settings.

[0069] The output unit selects the optimal display method when outputting, taking into account the user's health condition. For example, if the user is tired, the output unit provides a simple and highly visible display method. For example, the output unit analyzes the user's health condition and provides a simple and highly visible display method when the user is tired. Furthermore, if the user is healthy, the output unit provides a display method that includes detailed information. For example, the output unit analyzes the user's health condition and provides a display method that includes detailed information when the user is healthy. In addition, if the user is unwell, the output unit provides a less burdensome display method. For example, the output unit analyzes the user's health condition and provides a less burdensome display method when the user is unwell. In this way, a less burdensome display method can be provided by taking the user's health condition into consideration. Some or all of the above processing in the output unit may be performed using AI, for example, or without using AI. For example, the output unit can have AI perform the process of analyzing the user's health condition and providing a simple and highly visible display method when the user is tired.

[0070] The output unit selects the optimal display method when outputting, taking into account the user's past usage history. For example, the output unit prioritizes providing display methods that the user has previously preferred. For example, the output unit analyzes the user's past usage history and prioritizes providing preferred display methods. The output unit also learns and provides the optimal display method from the user's past usage history. For example, the output unit uses a machine learning algorithm to analyze the user's past usage history, learns and provides the optimal display method. Furthermore, the output unit provides a customized display method based on the user's past usage history. For example, the output unit analyzes the user's past usage history and provides a customized display method. This allows for the provision of a customized display method by considering the user's past usage history. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can have AI perform the process of analyzing the user's past usage history and prioritizing the provision of preferred display methods.

[0071] The output unit selects the optimal display method when outputting, taking into account the user's current environmental information. For example, if the user is outdoors, the output unit provides a display method that is highly visible even in bright environments. For example, the output unit analyzes the user's current environmental information and provides a display method that is highly visible even in bright environments when the user is outdoors. Furthermore, if the user is indoors, the output unit provides a display method that includes detailed information. For example, the output unit analyzes the user's current environmental information and provides a display method that includes detailed information when the user is indoors. In addition, the output unit selects the optimal display method based on the user's current environmental information. For example, the output unit analyzes the user's current environmental information and selects the optimal display method. This allows the system to provide the optimal display method by taking into account the user's current environmental information. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can have AI perform the process of analyzing the user's current environmental information and providing a display method that is highly visible even in bright environments when the user is outdoors.

[0072] The output unit selects the optimal display method when outputting, taking into account the battery level of the user's device. For example, if the battery level of the user's device is low, the output unit provides a simple and power-saving display method. For example, the output unit analyzes the user's device information and provides a simple and power-saving display method when the battery level is low. Furthermore, if the battery level of the user's device is sufficient, the output unit provides a display method that includes detailed information. For example, the output unit analyzes the user's device information and provides a display method that includes detailed information when the battery level is sufficient. In addition, the output unit selects the optimal display method based on the battery level of the user's device. For example, the output unit analyzes the user's device information and selects the optimal display method. This allows for the provision of a power-saving display method by considering the battery level of the user's device. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can have AI perform the process of analyzing the user's device information and providing a simple and power-saving display method when the battery level is low.

[0073] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0074] The analysis unit can also determine the priority of analysis based on the data collection period when analyzing collected data and extracting important points. For example, it can prioritize the analysis of recently collected data. The analysis unit evaluates the data collection period and prioritizes the analysis of recently collected data. It can also prioritize the analysis of data collected at important periods. The analysis unit evaluates the data collection period and prioritizes the analysis of data collected at important periods. Furthermore, it can also determine the order of analysis based on the data collection period. The analysis unit evaluates the data collection period and determines the order of analysis. This enables efficient analysis by determining the priority of analysis based on the data collection period.

[0075] The storage unit can improve the accuracy of data storage by considering the interrelationships between analyzed data. For example, it can analyze the interrelationships between data and store related data together. The storage unit analyzes the interrelationships between data and stores related data together. It can also select an efficient storage method by considering the interrelationships between data. The storage unit analyzes the interrelationships between data and selects an efficient storage method. Furthermore, it can improve the accuracy of storage based on the interrelationships between data. The storage unit analyzes the interrelationships between data and improves the accuracy of storage. As a result, the accuracy of storage is improved by considering the interrelationships between data.

[0076] The classification unit can also classify stored data by considering the attribute information of the data submitter. For example, if the data submitter is a craftsman, the data can be classified based on their skills and know-how. The classification unit analyzes the submitter's attribute information and classifies the data based on the craftsman's skills and know-how. Similarly, if the data submitter is an engineer, the data can be classified based on their area of ​​expertise. The classification unit analyzes the submitter's attribute information and classifies the data based on the engineer's area of ​​expertise. Furthermore, the classification unit can select the optimal classification method based on the data submitter's attribute information. The classification unit analyzes the submitter's attribute information and selects the optimal classification method. This allows for more appropriate classification by considering the attribute information of the data submitter.

[0077] The data collection department can also analyze a craftsman's past work history and select the optimal data collection method. For example, it can analyze videos of a craftsman's past work, extract key points, and create interview questions. The data collection department uses video analysis technology to analyze past work videos and extract key points. It can also identify particularly important techniques and know-how from a craftsman's past work history and focus data collection on those. The data collection department uses text analysis technology to analyze past work history and identify important techniques and know-how. Furthermore, it can determine the optimal timing and method of data collection based on a craftsman's past work history. The data collection department uses machine learning algorithms to analyze past work history and determine the optimal timing and method of data collection. This allows for the selection of the optimal data collection method by analyzing past work history.

[0078] The storage unit can optimize its storage algorithm by referencing past stored data when storing accumulated data. For example, it can analyze past stored data and select the optimal storage algorithm. The storage unit analyzes past stored data and selects the optimal storage algorithm. It can also learn efficient storage methods from past stored data. The storage unit uses machine learning algorithms to analyze past stored data and learn efficient storage methods. Furthermore, it can improve the storage algorithm based on past stored data. The storage unit analyzes past stored data and improves the storage algorithm. In this way, the storage algorithm can be optimized by referring to past stored data.

[0079] The output unit can improve the accuracy of its output based on user feedback when providing specific procedures based on classified data. For example, it can analyze user feedback to improve the accuracy of the output. The output unit analyzes user feedback and improves the accuracy of the output. It can also select an efficient output method based on user feedback. The output unit analyzes user feedback and selects an efficient output method. Furthermore, it can improve the output algorithm by referring to user feedback. The output unit analyzes user feedback and improves the output algorithm. As a result, by improving the accuracy of the output based on user feedback, it becomes possible to provide more appropriate information.

[0080] The following briefly describes the processing flow for example form 1.

[0081] Step 1: The data collection unit digitizes the know-how of craftsmen and technicians. For example, it collects language data and image data, and records what craftsmen say and converts it into text data. It can also videotape craftsmen at work and save it as image data. Furthermore, it can scan drawings and blueprints created by craftsmen and convert them into digital data. Step 2: The analysis unit analyzes the collected data. For example, it can analyze the collected data to extract important points and extract frequently occurring keywords from text data. It can also detect specific patterns from image data and extract motion characteristics from video data. Step 3: The storage unit stores the analyzed data. For example, it can save the analyzed data to a database and save text data to a database. It can also save image data to cloud storage and perform backups for long-term storage of video data. Step 4: The memory unit stores the accumulated data. For example, it performs backups for long-term storage of accumulated data and implements data redundancy to prevent data loss. It can also encrypt data to ensure security. Furthermore, it can set data access permissions to prevent unauthorized use of data. Step 5: The classification unit categorizes the stored data. For example, it categorizes stored data, classifying text data into technical categories or work procedure categories. It can also classify image data into product categories or parts categories, and video data into work process categories or motion pattern categories. Step 6: The output section provides specific procedures based on the classified data. For example, it can generate work manuals based on classified data and create work procedure documents based on data classified into technical categories. It can also create operation guides based on data classified into product categories and procedure documents based on data classified into work process categories.

[0082] (Example of form 2) The AI ​​system according to an embodiment of the present invention is a system designed to address the crisis of traditional techniques and know-how disappearing due to a shortage of successors resulting from the declining birthrate and aging population. This system digitizes the wisdom and know-how of craftsmen and technicians, and the AI ​​analyzes, stores, remembers, and classifies it, allowing for output and reproduction when needed. For example, when digitizing the wisdom and know-how of craftsmen and technicians, various forms of data are collected, such as linguistic data and image data. This includes, for example, the amount of lacquer applied, small ingenious techniques used in making musical instruments, and unique techniques used in architecture. Next, the AI ​​analyzes, stores, remembers, and classifies the collected data. The AI ​​analyzes the data, extracts important points, and classifies them efficiently. This includes, for example, unique language used in customer service, know-how for handling complaints, and how to make old techniques and old models of machinery. Furthermore, output can be obtained from the AI ​​when needed and reproduced. For example, to reproduce old techniques, the AI ​​provides specific procedures based on the analyzed data. This makes it possible to reproduce traditional techniques and know-how even without successors. This system has strategic significance because it ensures that important technologies and traditions for a nation are passed down and can be quickly reproduced when needed, even without successors. Furthermore, for companies, it allows them to accumulate societal know-how and fulfill their role as social infrastructure. This enables AI systems to efficiently digitize, analyze, store, remember, classify, and output the know-how of craftsmen and engineers.

[0083] The AI ​​system according to this embodiment comprises a data collection unit, an analysis unit, a storage unit, a memory unit, a classification unit, and an output unit. The data collection unit digitizes the know-how of craftsmen and engineers. The data collection unit collects, for example, language data and image data. For example, the data collection unit records what a craftsman says and converts it into text data. The data collection unit can also videotape the craftsman's work and save it as image data. Furthermore, the data collection unit can scan drawings and blueprints created by craftsmen and convert them into digital data. The analysis unit analyzes the collected data. For example, the analysis unit analyzes the collected data and extracts important points. For example, the analysis unit extracts frequently occurring keywords from text data. Furthermore, the analysis unit can detect specific patterns from image data. Furthermore, the analysis unit can extract motion characteristics from video data. The storage unit stores the analyzed data. For example, the storage unit saves the analyzed data to a database. For example, the storage unit saves text data to a database. Furthermore, the storage unit can save image data to cloud storage. Furthermore, the storage unit can also perform backups for long-term storage of video data. The memory unit stores the stored data. The memory unit, for example, performs backups for long-term storage of the stored data. For example, the memory unit can perform data redundancy to prevent data loss. The memory unit can also encrypt the data to ensure security. Furthermore, the memory unit can set access permissions for the data to prevent unauthorized use. The classification unit classifies the stored data. The classification unit categorizes the stored data. For example, the classification unit classifies text data into technical categories and work procedure categories. The classification unit can also classify image data into product categories and parts categories. Furthermore, the classification unit can also classify video data into work process categories and motion pattern categories. The output unit provides specific procedures based on the classified data. For example, the output unit generates work manuals based on the classified data. For example, the output unit creates work procedure documents based on data classified into technical categories.Furthermore, the output unit can create operation guides based on data classified into product categories. In addition, the output unit can create procedure manuals based on data classified into work process categories. As a result, the AI ​​system according to this embodiment can efficiently digitize, analyze, store, remember, classify, and output the know-how of craftsmen and technicians.

[0084] The data collection unit digitizes the know-how of craftsmen and technicians. For example, it collects linguistic and image data. Specifically, it records what craftsmen say and converts it into text data using speech recognition technology. This speech recognition technology utilizes natural language processing (NLP) to accurately recognize the craftsmen's specialized terminology and unique expressions. The data collection unit also films craftsmen's work with high-resolution video cameras and saves the footage as image data. The video data is analyzed frame by frame to extract important actions and procedures. Furthermore, the data collection unit scans drawings and blueprints created by craftsmen with a high-precision scanner and converts them into digital data. This digital data is used for later analysis and classification. The data collection unit centrally manages and collects this diverse data in real time. For example, when a craftsman develops a new technology, data can be collected on the spot and immediately reflected in the system. This allows the data collection unit to efficiently and accurately digitize the know-how of craftsmen and technicians, enriching the overall knowledge base of the system.

[0085] The analysis unit analyzes the collected data. For example, the analysis unit analyzes the collected data and extracts important points. Specifically, it uses natural language processing (NLP) techniques to extract frequently occurring keywords from text data. NLP techniques can understand the context of text data and identify important keywords and phrases. It also uses image recognition techniques to detect specific patterns from image data. Image recognition techniques utilize deep learning to automatically extract features within images and detect specific patterns and anomalies. Furthermore, it uses motion analysis algorithms to extract motion features from video data. Motion analysis algorithms can analyze movement between video frames and identify specific actions and procedures. The analysis unit combines these techniques to analyze the collected data from multiple angles and extract important information. For example, it can analyze the work procedures of craftsmen and identify efficient work methods. This allows the analysis unit to analyze the collected data quickly and accurately, strengthening the knowledge base of the entire system.

[0086] The storage unit stores the analyzed data. For example, it stores the analyzed data in a database. Specifically, it stores text data in a relational database, enabling efficient searching and access. It also stores image data in cloud storage, allowing for efficient management of large amounts of data. Furthermore, it uses a dedicated video storage system for long-term storage of video data and performs backups. The storage unit centrally manages this data and makes it quickly accessible as needed. For example, when searching for data on a specific technology, the storage unit can quickly provide the relevant data. In this way, the storage unit can efficiently store the analyzed data and enhance data management throughout the entire system.

[0087] The storage unit stores accumulated data. For example, the storage unit performs backups for long-term storage of accumulated data. Specifically, it prevents data loss by implementing data redundancy and storing data on multiple storage devices. Furthermore, the storage unit ensures security by encrypting data. Encryption technology protects data confidentiality and safeguards data from unauthorized access. In addition, the storage unit sets data access permissions to prevent misuse of data. Using an access rights management system, access to data can be granted only to specific users or groups. This allows the storage unit to ensure data security and confidentiality, improving the overall reliability of the system.

[0088] The classification unit categorizes stored data. For example, it categorizes stored data. Specifically, it uses machine learning algorithms to classify text data into technical categories and work procedure categories. Machine learning algorithms can learn the characteristics of the data and automatically categorize it. It also uses image classification algorithms to classify image data into product categories and component categories. Image classification algorithms can analyze the characteristics of images and classify them into appropriate categories. Furthermore, it uses motion analysis algorithms to classify video data into work process categories and motion pattern categories. Motion analysis algorithms can analyze the motion of video data and classify it into appropriate categories. As a result, the classification unit can efficiently classify stored data and enhance data management throughout the system.

[0089] The output unit provides specific procedures based on classified data. For example, the output unit generates work manuals based on classified data. Specifically, it creates detailed work procedure manuals based on data classified into technical categories. These manuals are provided in a visually easy-to-understand format by combining text and image data. It also creates operation guides based on data classified into product categories. These operation guides explain product usage and maintenance procedures in detail, enabling users to operate the products accurately. Furthermore, it creates procedure manuals based on data classified into work process categories. These manuals can visually demonstrate specific work procedures by combining video data and motion analysis data. In this way, the output unit provides specific procedures based on classified data, supporting users in performing tasks efficiently and accurately.

[0090] The data collection unit collects language data and image data. For example, the data collection unit records what a craftsman says and converts it into text data. For example, the data collection unit records a craftsman's conversation and converts it into text data using speech recognition technology. The data collection unit can also videotape a craftsman's work and save it as image data. For example, the data collection unit films a craftsman's work with a high-resolution camera and saves it as image data. Furthermore, the data collection unit can scan drawings and blueprints created by craftsmen and convert them into digital data. For example, the data collection unit scans a handwritten drawing created by a craftsman and converts it into digital data. In this way, by collecting language data and image data, the know-how of craftsmen and technicians can be digitized in various formats. Some or all of the above processes in the data collection unit may be performed using AI, for example, or not. For example, the data collection unit can have AI perform the process of recording a craftsman's conversation and converting it into text data using speech recognition technology.

[0091] The analysis unit analyzes the collected data and extracts important points. For example, the analysis unit can extract frequently occurring keywords from text data. For example, the analysis unit can analyze text data using natural language processing technology and extract frequently occurring keywords. The analysis unit can also detect specific patterns from image data. For example, the analysis unit can analyze image data using image recognition technology and detect specific patterns. Furthermore, the analysis unit can extract motion features from video data. For example, the analysis unit can analyze video data using video analysis technology and extract motion features. This improves the accuracy of data analysis by extracting important points. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can have AI perform the process of analyzing text data using natural language processing technology and extracting frequently occurring keywords.

[0092] The storage unit stores the analyzed data. For example, the storage unit saves the analyzed data to a database. For example, the storage unit saves text data to a database. For example, the storage unit saves text data to a relational database. The storage unit can also save image data to cloud storage. For example, the storage unit uploads and saves image data to a cloud storage service. Furthermore, the storage unit can perform backups for long-term storage of video data. For example, the storage unit backs up and saves video data to external storage. This makes data storage and management more efficient by storing the analyzed data. Some or all of the above processes in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can have AI perform the process of saving text data to a relational database.

[0093] The storage unit stores the accumulated data. The storage unit can, for example, perform backups for long-term storage of the accumulated data. For example, the storage unit can perform data redundancy to prevent data loss. For example, the storage unit can distribute and store data across multiple storage devices. The storage unit can also encrypt the data to ensure security. For example, the storage unit can encrypt and store data to prevent unauthorized access. Furthermore, the storage unit can set access permissions for data to prevent unauthorized use of data. For example, the storage unit can set access permissions for data so that only specific users can access it. This makes long-term storage of data possible by storing the accumulated data. Some or all of the above processes in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can have AI perform the process of performing data redundancy.

[0094] The classification unit classifies the stored data. For example, the classification unit categorizes the stored data. For example, the classification unit classifies text data into technical categories or work procedure categories. For example, the classification unit analyzes text data using natural language processing technology and classifies it into technical categories or work procedure categories. The classification unit can also classify image data into product categories or part categories. For example, the classification unit analyzes image data using image recognition technology and classifies it into product categories or part categories. Furthermore, the classification unit can also classify video data into work process categories or motion pattern categories. For example, the classification unit analyzes video data using video analysis technology and classifies it into work process categories or motion pattern categories. By classifying the stored data in this way, data retrieval and utilization become easier. Some or all of the above processing in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can have AI perform the process of analyzing text data using natural language processing technology and classifying it into technical categories or work procedure categories.

[0095] The output unit provides specific procedures based on the classified data. For example, the output unit generates work manuals based on the classified data. For example, the output unit creates work procedure manuals based on data classified into technical categories. For example, the output unit creates work procedure manuals based on data classified into technical categories using natural language generation technology. The output unit can also create operation guides based on data classified into product categories. For example, the output unit creates operation guides based on data classified into product categories using image generation technology. Furthermore, the output unit can also create procedure manuals based on data classified into work process categories. For example, the output unit creates procedure manuals based on data classified into work process categories using video generation technology. This makes it possible to reproduce the know-how of craftsmen and technicians by providing specific procedures. Some or all of the above-described processes in the output unit may be performed using AI, for example, or without AI. For example, the output unit can have AI perform the process of creating work procedure manuals based on data classified into technical categories using natural language generation technology.

[0096] The data collection unit estimates the emotions of the craftsman and adjusts the timing of data collection based on the estimated emotions. For example, the data collection unit conducts detailed interviews when the craftsman is relaxed to extract deep knowledge. For example, the data collection unit captures the craftsman's facial expressions with a camera and uses an emotion estimation algorithm to determine if they are relaxed. The data collection unit also records video of the craftsman's work when they are concentrating to capture natural movements. For example, the data collection unit records the craftsman's voice and uses voice analysis technology to determine if they are concentrating. Furthermore, when the craftsman is tired, the data collection unit conducts short interviews to reduce their burden. For example, the data collection unit collects the craftsman's biometric data (heart rate and skin electrical activity) with sensors and uses an emotion estimation algorithm to determine if they are tired. This allows for the collection of more appropriate data by adjusting the timing of data collection according to the craftsman's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can have AI perform the process of taking a picture of a craftsman's facial expression with a camera and using an emotion estimation algorithm to determine whether or not the craftsman is relaxed.

[0097] The data collection unit analyzes the craftsman's past work history and selects the optimal data collection method. For example, the data collection unit analyzes videos of past work performed by the craftsman, extracts key points, and creates interview questions. For example, the data collection unit uses video analysis technology to analyze past work videos and extract key points. The data collection unit also identifies particularly important techniques and know-how from the craftsman's past work history and focuses data collection on those. For example, the data collection unit uses text analysis technology to analyze past work history and identify important techniques and know-how. Furthermore, the data collection unit determines the optimal timing and method of data collection based on the craftsman's past work history. For example, the data collection unit uses machine learning algorithms to analyze past work history and determine the optimal timing and method of data collection. This allows for the selection of the optimal data collection method by analyzing past work history. Some or all of the above processes in the data collection unit may be performed using AI, for example, or not. For example, the data collection unit can have AI perform the process of analyzing past work videos using video analysis technology and extracting key points.

[0098] The data collection unit filters data based on the craftsman's current work status and areas of interest during data collection. For example, the data collection unit prioritizes collecting data related to the work the craftsman is currently performing. For example, the data collection unit monitors the craftsman's current work in real time and prioritizes collecting relevant data. The data collection unit also focuses on collecting data on technologies and know-how that the craftsman is particularly interested in. For example, the data collection unit understands the craftsman's areas of interest through questionnaires and interviews and prioritizes collecting relevant data. Furthermore, the data collection unit considers the craftsman's current work status and filters the data to collect it efficiently. For example, the data collection unit monitors the craftsman's work progress and collects data at the appropriate time. This allows for efficient data collection by filtering the data based on the current work status and areas of interest. Some or all of the above processing in the data collection unit may be performed using AI, or not. For example, the data collection unit can have AI perform the process of monitoring the craftsman's current work in real time and prioritizing the collection of relevant data.

[0099] The data collection unit estimates the emotions of the craftsman and determines the priority of data to collect based on the estimated emotions. For example, when the craftsman is relaxed, the data collection unit prioritizes collecting detailed techniques and know-how. For example, the data collection unit captures the craftsman's facial expressions with a camera and uses an emotion estimation algorithm to determine if they are relaxed. Also, when the craftsman is concentrating, the data collection unit prioritizes video recording of important tasks. For example, the data collection unit records the craftsman's voice and uses voice analysis technology to determine if they are concentrating. Furthermore, when the craftsman is tired, the data collection unit prioritizes simple questions and short interviews. For example, the data collection unit collects the craftsman's biometric data (heart rate and skin electrical activity) with sensors and uses an emotion estimation algorithm to determine if they are tired. This allows for the priority of data collection based on the craftsman's emotions, ensuring that important data is collected preferentially. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can have AI perform the process of taking a picture of a craftsman's facial expression with a camera and using an emotion estimation algorithm to determine whether or not the craftsman is relaxed.

[0100] The data collection unit prioritizes collecting highly relevant data, taking into account the geographical location information of the craftsman. For example, the data collection unit prioritizes collecting data related to the work the craftsman is performing in a specific area. For example, the data collection unit obtains the craftsman's geographical location information from GPS data and prioritizes collecting relevant data. The data collection unit also prioritizes collecting data on work performed by the craftsman while traveling. For example, the data collection unit analyzes the craftsman's travel history and prioritizes collecting data on work performed while traveling. Furthermore, if the craftsman is interested in working in a specific area, the data collection unit prioritizes collecting data related to that area. For example, the data collection unit identifies the craftsman's areas of interest through questionnaires or interviews and prioritizes collecting relevant data. This allows for the priority collection of highly relevant data by considering geographical location information. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can have AI perform the process of obtaining the craftsman's geographical location information from GPS data and prioritizing the collection of relevant data.

[0101] The data collection unit analyzes the social media activities of artisans and collects relevant data during data collection. For example, the data collection unit collects photos and videos of the work that artisans share on social media. For example, the data collection unit uses social media analysis technology to analyze the content of artisans' posts and collects relevant photos and videos. The data collection unit also collects data related to the techniques and know-how that artisans mention on social media. For example, the data collection unit uses text analysis technology to analyze the content of artisans' posts and collects relevant techniques and know-how. Furthermore, the data collection unit collects data on other artisans and technicians that artisans follow on social media. For example, the data collection unit uses social network analysis technology to analyze the artisan's follow network and collects relevant data. This allows for the efficient collection of relevant data by analyzing social media activities. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can have AI perform the process of analyzing the content of artisans' posts using social media analysis technology and collecting relevant photos and videos.

[0102] The analysis unit estimates the emotions of the craftsman and adjusts the presentation of the analysis based on the estimated emotions. For example, if the craftsman is relaxed, the analysis unit provides detailed analysis results. For example, the analysis unit captures the craftsman's facial expression with a camera, uses an emotion estimation algorithm to determine if they are relaxed, and provides detailed analysis results. Also, if the craftsman is in a hurry, the analysis unit provides concise analysis results that get straight to the point. For example, the analysis unit records the craftsman's voice, uses voice analysis technology to determine if they are in a hurry, and provides concise analysis results. Furthermore, if the craftsman is excited, the analysis unit provides analysis results with visually stimulating effects. For example, the analysis unit collects the craftsman's biometric data (heart rate and skin electrical activity) with sensors, uses an emotion estimation algorithm to determine if they are excited, and provides analysis results with visually stimulating effects. In this way, by adjusting the presentation of the analysis according to the craftsman's emotions, more appropriate analysis results can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or not using AI. For example, the analysis unit may have the AI ​​perform the process of taking a picture of a craftsman's facial expression with a camera, using an emotion estimation algorithm to determine whether the craftsman is relaxed, and providing detailed analysis results.

[0103] The analysis unit adjusts the level of detail of the analysis based on the importance of the data. For example, the analysis unit performs a detailed analysis on important data. For example, the analysis unit evaluates the importance of the data and performs a detailed analysis on important data. The analysis unit also performs a concise analysis on less important data. For example, the analysis unit evaluates the importance of the data and performs a concise analysis on less important data. Furthermore, the analysis unit determines the priority of the analysis according to the importance of the data. For example, the analysis unit evaluates the importance of the data and prioritizes the analysis of important data. This allows for efficient analysis by adjusting the level of detail of the analysis based on the importance of the data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can have AI perform the process of evaluating the importance of the data and performing a detailed analysis on important data.

[0104] The analysis unit applies different analysis algorithms depending on the data category during analysis. For example, the analysis unit applies a natural language processing algorithm to language data. For example, the analysis unit analyzes language data using natural language processing technology. The analysis unit also applies an image analysis algorithm to image data. For example, the analysis unit analyzes image data using image recognition technology. Furthermore, the analysis unit applies a video analysis algorithm to video data. For example, the analysis unit analyzes video data using video analysis technology. By applying different analysis algorithms depending on the data category, the accuracy of the analysis is improved. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can have AI perform the process of analyzing language data using natural language processing technology.

[0105] The analysis unit estimates the emotions of the craftsman and adjusts the length of the analysis based on the estimated emotions. For example, if the craftsman is relaxed, the analysis unit performs a detailed analysis. For example, the analysis unit captures the craftsman's facial expression with a camera, uses an emotion estimation algorithm to determine if they are relaxed, and performs a detailed analysis. Also, if the craftsman is in a hurry, the analysis unit performs a concise analysis. For example, the analysis unit records the craftsman's voice, uses voice analysis technology to determine if they are in a hurry, and performs a concise analysis. Furthermore, if the craftsman is excited, the analysis unit performs a visually stimulating analysis. For example, the analysis unit collects the craftsman's biometric data (heart rate and skin electrical activity) with sensors, uses an emotion estimation algorithm to determine if they are excited, and performs a visually stimulating analysis. By adjusting the length of the analysis according to the craftsman's emotions, more appropriate analysis results can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can have AI perform processes such as taking a picture of the craftsman's facial expression with a camera, using an emotion estimation algorithm to determine whether the craftsman is relaxed, and then performing a detailed analysis.

[0106] The analysis unit determines the priority of analysis based on the data collection timing during analysis. For example, the analysis unit prioritizes the analysis of recently collected data. For example, the analysis unit evaluates the data collection timing and prioritizes the analysis of recently collected data. The analysis unit also prioritizes the analysis of data collected at important times. For example, the analysis unit evaluates the data collection timing and prioritizes the analysis of data collected at important times. Furthermore, the analysis unit determines the order of analysis based on the data collection timing. For example, the analysis unit evaluates the data collection timing and determines the order of analysis. This enables efficient analysis by determining the priority of analysis based on the data collection timing. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can have AI perform the process of evaluating the data collection timing and prioritizing the analysis of recently collected data.

[0107] The analysis unit adjusts the order of analysis based on the relevance of the data during analysis. For example, the analysis unit prioritizes analyzing highly relevant data. For example, the analysis unit evaluates the relevance of the data and prioritizes analyzing highly relevant data. The analysis unit also postpones analyzing less relevant data. For example, the analysis unit evaluates the relevance of the data and postpones analyzing less relevant data. Furthermore, the analysis unit determines the order of analysis based on the relevance of the data. For example, the analysis unit evaluates the relevance of the data and determines the order of analysis. This allows for efficient analysis by adjusting the order of analysis based on the relevance of the data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can have AI perform the process of evaluating the relevance of the data and prioritizing the analysis of highly relevant data.

[0108] The data storage unit estimates the emotions of the craftsman and selects the data to store based on the estimated emotions. For example, if the craftsman is relaxed, the storage unit stores detailed techniques and know-how. For example, the storage unit captures the craftsman's facial expressions with a camera, uses an emotion estimation algorithm to determine if they are relaxed, and stores detailed techniques and know-how. Also, if the craftsman is focused, the storage unit stores data on important tasks. For example, the storage unit records the craftsman's voice, uses voice analysis technology to determine if they are focused, and stores data on important tasks. Furthermore, if the craftsman is tired, the storage unit stores simple data. For example, the storage unit collects the craftsman's biometric data (heart rate and skin electrical activity) with sensors, uses an emotion estimation algorithm to determine if they are tired, and stores simple data. In this way, by selecting the data to store according to the craftsman's emotions, important data can be prioritized for storage. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the storage unit may be performed using AI, for example, or not using AI. For example, the storage unit can have the AI ​​perform processes such as taking a picture of a craftsman's facial expression with a camera, using an emotion estimation algorithm to determine whether they are relaxed, and storing detailed techniques and know-how.

[0109] The storage unit optimizes the storage algorithm by referring to past stored data during storage. For example, the storage unit analyzes past stored data and selects the optimal storage algorithm. The storage unit also learns efficient storage methods from past stored data. For example, the storage unit uses machine learning algorithms to analyze past stored data and learn efficient storage methods. Furthermore, the storage unit improves the storage algorithm based on past stored data. For example, the storage unit analyzes past stored data and improves the storage algorithm. This allows the storage algorithm to be optimized by referring to past stored data. Some or all of the above processes in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can have AI perform the process of analyzing past stored data and selecting the optimal storage algorithm.

[0110] The storage unit improves the accuracy of storage by considering the interrelationships of the data during storage. For example, the storage unit analyzes the interrelationships of the data and stores related data together. For example, the storage unit analyzes the interrelationships of the data and stores related data together. The storage unit also selects an efficient storage method by considering the interrelationships of the data. For example, the storage unit analyzes the interrelationships of the data and selects an efficient storage method. Furthermore, the storage unit improves the accuracy of storage based on the interrelationships of the data. For example, the storage unit analyzes the interrelationships of the data and improves the accuracy of storage. As a result, the accuracy of storage is improved by considering the interrelationships of the data. Some or all of the above processing in the storage unit may be performed using AI, for example, or without using AI. For example, the storage unit can have AI perform the process of analyzing the interrelationships of the data and storing related data together.

[0111] The data storage unit estimates the emotions of the craftsman and adjusts the storage frequency based on the estimated emotions. For example, if the craftsman is relaxed, the storage unit stores data frequently. For example, the storage unit captures the craftsman's facial expressions with a camera, uses an emotion estimation algorithm to determine if they are relaxed, and stores data frequently. Also, if the craftsman is concentrating, the storage unit stores data on important tasks frequently. For example, the storage unit records the craftsman's voice, uses voice analysis technology to determine if they are concentrating, and stores data on important tasks frequently. Furthermore, if the craftsman is tired, the storage unit reduces the storage frequency. For example, the storage unit collects the craftsman's biometric data (heart rate and skin electrical activity) with sensors, uses an emotion estimation algorithm to determine if they are tired, and reduces the storage frequency. This allows for efficient data storage by adjusting the storage frequency according to the craftsman's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can have AI perform the process of taking a picture of the craftsman's facial expression with a camera, using an emotion estimation algorithm to determine whether they are relaxed, and frequently storing the data.

[0112] The storage unit weights the stored data based on when the data was collected. For example, the storage unit assigns a higher weight to recently collected data. For example, the storage unit evaluates when the data was collected and assigns a higher weight to recently collected data. The storage unit also assigns a higher weight to data collected during important periods. For example, the storage unit evaluates when the data was collected and assigns a higher weight to data collected during important periods. Furthermore, the storage unit weights the stored data based on when the data was collected. For example, the storage unit evaluates when the data was collected and weights the stored data. This allows for the priority storage of important data by weighting the stored data based on when it was collected. Some or all of the above processing in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can have AI perform the process of evaluating when the data was collected and assigning a higher weight to recently collected data for storage.

[0113] The storage unit improves the accuracy of data storage by referring to relevant literature during storage. For example, the storage unit improves the accuracy of data storage by referring to relevant literature. For example, the storage unit improves the accuracy of data storage by analyzing relevant literature. The storage unit also selects an efficient storage method based on the relevant literature. For example, the storage unit analyzes relevant literature and selects an efficient storage method. Furthermore, the storage unit improves the storage algorithm by referring to relevant literature. For example, the storage unit analyzes relevant literature and improves the storage algorithm. As a result, the accuracy of data storage is improved by referring to relevant literature. Some or all of the above processes in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can have AI perform the process of analyzing relevant literature and improving the accuracy of data storage.

[0114] The memory unit estimates the craftsman's emotions and selects data to store based on the estimated emotions. For example, if the craftsman is relaxed, the memory unit stores detailed techniques and know-how. For instance, it might capture the craftsman's facial expressions with a camera, use an emotion estimation algorithm to determine if they are relaxed, and then store detailed techniques and know-how. Furthermore, if the craftsman is focused, the memory unit stores data on important tasks. For example, it might record the craftsman's voice, use voice analysis technology to determine if they are focused, and then store data on important tasks. Additionally, if the craftsman is tired, the memory unit stores simple data. For example, it might collect the craftsman's biometric data (heart rate and skin electrical activity) with sensors, use an emotion estimation algorithm to determine if they are tired, and then store simple data. This allows for the selection of data to store according to the craftsman's emotions, prioritizing the storage of important data. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI is, but is not limited to, text-generating AI (e.g., LLM) or multimodal generative AI. Some or all of the above-described processes in the memory unit may be performed using AI, or not using AI. For example, the memory unit can have the AI ​​perform the processes of capturing a craftsman's facial expression with a camera, determining whether they are relaxed using an emotion estimation algorithm, and storing detailed techniques and know-how.

[0115] The memory unit optimizes the memory algorithm by referring to past memory data during memory storage. For example, the memory unit analyzes past memory data and selects the optimal memory algorithm. The memory unit also learns efficient memory methods from past memory data. For example, the memory unit uses machine learning algorithms to analyze past memory data and learn efficient memory methods. Furthermore, the memory unit improves the memory algorithm based on past memory data. For example, the memory unit analyzes past memory data and improves the memory algorithm. This allows the memory algorithm to be optimized by referring to past memory data. Some or all of the above processes in the memory unit may be performed using AI, for example, or without AI. For example, the memory unit can have AI perform the process of analyzing past memory data and selecting the optimal memory algorithm.

[0116] The memory unit improves the accuracy of memory by considering the interrelationships of data during storage. For example, the memory unit analyzes the interrelationships of data and stores related data together. For example, the memory unit analyzes the interrelationships of data and stores related data together. The memory unit also selects an efficient storage method by considering the interrelationships of data. For example, the memory unit analyzes the interrelationships of data and selects an efficient storage method. Furthermore, the memory unit improves the accuracy of memory based on the interrelationships of data. For example, the memory unit analyzes the interrelationships of data and improves the accuracy of memory. Thus, the accuracy of memory is improved by considering the interrelationships of data. Some or all of the above processing in the memory unit may be performed using AI, for example, or without AI. For example, the memory unit can have AI perform the process of analyzing the interrelationships of data and storing related data together.

[0117] The memory unit estimates the craftsman's emotions and adjusts the frequency of memory based on the estimated emotions. For example, if the craftsman is relaxed, the memory unit frequently stores data. For instance, it might capture the craftsman's facial expressions with a camera, use an emotion estimation algorithm to determine if they are relaxed, and frequently store the data. Similarly, if the craftsman is focused, the memory unit frequently stores data on important tasks. For example, it might record the craftsman's voice, use voice analysis technology to determine if they are focused, and frequently store data on important tasks. Furthermore, if the craftsman is tired, the memory unit reduces the frequency of memory. For example, it might collect the craftsman's biometric data (heart rate and skin electrical activity) with sensors, use an emotion estimation algorithm to determine if they are tired, and reduce the frequency of memory. This allows for efficient data storage by adjusting the frequency of memory according to the craftsman's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the memory unit may be performed using AI, for example, or without AI. For example, the memory unit can have AI perform the process of taking a picture of the craftsman's facial expression with a camera, using an emotion estimation algorithm to determine whether they are relaxed, and frequently storing the data.

[0118] The memory unit weights the stored data based on when the data was collected. For example, the memory unit assigns a higher weight to recently collected data. For example, the memory unit evaluates when the data was collected and assigns a higher weight to recently collected data. The memory unit also assigns a higher weight to data collected at important times. For example, the memory unit evaluates when the data was collected and assigns a higher weight to data collected at important times. Furthermore, the memory unit weights the stored data based on when the data was collected. For example, the memory unit evaluates when the data was collected and weights the stored data. This allows important data to be stored preferentially by weighting the stored data based on when it was collected. Some or all of the above processing in the memory unit may be performed using AI, for example, or without AI. For example, the memory unit can have AI perform the process of evaluating when the data was collected and assigning a higher weight to recently collected data.

[0119] The memory unit improves the accuracy of memory by referring to relevant literature on the data during storage. For example, the memory unit improves the accuracy of memory by referring to relevant literature on the data. For example, the memory unit improves the accuracy of memory by analyzing relevant literature. The memory unit also selects an efficient storage method based on the relevant literature. For example, the memory unit analyzes relevant literature and selects an efficient storage method. Furthermore, the memory unit improves the storage algorithm by referring to relevant literature. For example, the memory unit analyzes relevant literature and improves the storage algorithm. As a result, the accuracy of memory is improved by referring to relevant literature on the data. Some or all of the above processing in the memory unit may be performed using AI, for example, or without AI. For example, the memory unit can have AI perform the process of analyzing relevant literature and improving the accuracy of memory.

[0120] The classification unit estimates the emotions of the craftsman and adjusts the classification criteria based on the estimated emotions. For example, if the craftsman is relaxed, the classification unit applies detailed classification criteria. For example, the classification unit captures the craftsman's facial expression with a camera, uses an emotion estimation algorithm to determine if they are relaxed, and then applies detailed classification criteria. Also, if the craftsman is in a hurry, the classification unit applies concise classification criteria. For example, the classification unit records the craftsman's voice, uses voice analysis technology to determine if they are in a hurry, and then applies concise classification criteria. Furthermore, if the craftsman is excited, the classification unit applies visually stimulating classification criteria. For example, the classification unit collects the craftsman's biometric data (heart rate and skin electrical activity) with sensors, uses an emotion estimation algorithm to determine if they are excited, and then applies visually stimulating classification criteria. This allows for more appropriate classification by adjusting the classification criteria according to the craftsman's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can have AI perform the process of taking a picture of the craftsman's face with a camera, using an emotion estimation algorithm to determine whether they are relaxed, and applying detailed classification criteria.

[0121] The classification unit improves the accuracy of classification by considering the interrelationships of the data during classification. For example, the classification unit analyzes the interrelationships of the data and classifies related data together. For example, the classification unit analyzes the interrelationships of the data and classifies related data together. The classification unit also selects an efficient classification method by considering the interrelationships of the data. For example, the classification unit analyzes the interrelationships of the data and selects an efficient classification method. Furthermore, the classification unit improves the accuracy of classification based on the interrelationships of the data. For example, the classification unit analyzes the interrelationships of the data and improves the accuracy of classification. As a result, the accuracy of classification is improved by considering the interrelationships of the data. Some or all of the above processes in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can have AI perform the process of analyzing the interrelationships of the data and classifying related data together.

[0122] The classification unit considers the attribute information of the data submitter when classifying data. For example, if the data submitter is a craftsman, the classification unit classifies the data based on their skills and know-how. For example, the classification unit analyzes the submitter's attribute information and classifies the data based on the craftsman's skills and know-how. Also, if the data submitter is an engineer, the classification unit classifies the data based on their field of expertise. For example, the classification unit analyzes the submitter's attribute information and classifies the data based on the engineer's field of expertise. Furthermore, the classification unit selects the optimal classification method based on the attribute information of the data submitter. For example, the classification unit analyzes the submitter's attribute information and selects the optimal classification method. This makes it possible to perform more appropriate classification by considering the attribute information of the data submitter. Some or all of the above processing in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can have AI perform the process of analyzing the submitter's attribute information and classifying the data based on the craftsman's skills and know-how.

[0123] The classification unit estimates the emotions of the craftsman and adjusts the order in which the classification results are displayed based on the estimated emotions. For example, if the craftsman is relaxed, the classification unit prioritizes displaying detailed classification results. For example, the classification unit may capture the craftsman's facial expression with a camera, use an emotion estimation algorithm to determine if they are relaxed, and prioritize displaying detailed classification results. Also, if the craftsman is in a hurry, the classification unit prioritizes displaying concise classification results. For example, the classification unit may record the craftsman's voice, use voice analysis technology to determine if they are in a hurry, and prioritize displaying concise classification results. Furthermore, if the craftsman is excited, the classification unit prioritizes displaying visually stimulating classification results. For example, the classification unit may collect the craftsman's biometric data (heart rate and skin electrical activity) with sensors, use an emotion estimation algorithm to determine if they are excited, and prioritize displaying visually stimulating classification results. This allows for the provision of more appropriate information by adjusting the order in which classification results are displayed according to the craftsman's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI is, but is not limited to, text-generating AI (e.g., LLM) or multimodal generative AI. Some or all of the processing described above in the classification unit may be performed using AI, or not using AI. For example, the classification unit can have the AI ​​take a picture of a craftsman's face with a camera, use an emotion estimation algorithm to determine whether they are relaxed, and then prioritize displaying the detailed classification results.

[0124] The classification unit considers the geographical distribution of the data when classifying it. For example, the classification unit analyzes the geographical distribution of the data and classifies it by region. For example, the classification unit analyzes the geographical distribution and classifies it by region. The classification unit also classifies related data together based on the geographical distribution. For example, the classification unit analyzes the geographical distribution and classifies related data together. Furthermore, the classification unit selects an efficient classification method considering the geographical distribution. For example, the classification unit analyzes the geographical distribution and selects an efficient classification method. This makes it possible to classify data appropriately by region by considering its geographical distribution. Some or all of the above processes in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can have AI perform the process of analyzing the geographical distribution and classifying it by region.

[0125] The classification unit improves the accuracy of classification by referring to relevant literature for the data during the classification process. For example, the classification unit improves the accuracy of classification by referring to relevant literature for the data. For example, the classification unit improves the accuracy of classification by analyzing relevant literature. The classification unit also selects an efficient classification method based on the relevant literature. For example, the classification unit analyzes relevant literature and selects an efficient classification method. Furthermore, the classification unit improves the classification algorithm by referring to relevant literature. For example, the classification unit analyzes relevant literature and improves the classification algorithm. As a result, the accuracy of classification is improved by referring to relevant literature for the data. Some or all of the above processes in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can have AI perform the process of analyzing relevant literature and improving the accuracy of classification.

[0126] The output unit estimates the craftsman's emotions and adjusts the output method based on the estimated emotions. For example, if the craftsman is relaxed, the output unit provides detailed output. For example, it might capture the craftsman's facial expression with a camera, use an emotion estimation algorithm to determine if they are relaxed, and then provide detailed output. If the craftsman is in a hurry, the output unit provides concise output that gets straight to the point. For example, it might record the craftsman's voice, use voice analysis technology to determine if they are in a hurry, and then provide concise output. Furthermore, if the craftsman is excited, the output unit provides visually stimulating output. For example, it might collect the craftsman's biometric data (heart rate and skin electrical activity) with sensors, use an emotion estimation algorithm to determine if they are excited, and then provide visually stimulating output. This allows for more appropriate information to be provided by adjusting the output method according to the craftsman's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit could have AI perform the process of capturing the craftsman's facial expression with a camera, using an emotion estimation algorithm to determine whether the craftsman is relaxed, and providing a detailed output.

[0127] The output unit adjusts the level of detail of the output based on the importance of the data. For example, the output unit provides detailed output for important data. For example, the output unit evaluates the importance of the data and provides detailed output for important data. The output unit also provides concise output for less important data. For example, the output unit evaluates the importance of the data and provides concise output for less important data. Furthermore, the output unit determines the priority of the output according to the importance of the data. For example, the output unit evaluates the importance of the data and prioritizes outputting important data. This allows for efficient information provision by adjusting the level of detail of the output based on the importance of the data. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can have AI perform the process of evaluating the importance of the data and providing detailed output for important data.

[0128] The output unit applies different output algorithms depending on the data category during output. For example, the output unit applies a natural language generation algorithm to language data. For example, the output unit outputs language data using natural language generation technology. The output unit also applies an image generation algorithm to image data. For example, the output unit outputs image data using image generation technology. Furthermore, the output unit applies a video generation algorithm to video data. For example, the output unit outputs video data using video generation technology. By applying different output algorithms depending on the data category, the accuracy of information provision is improved. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can have AI perform the process of outputting language data using natural language generation technology.

[0129] The output unit estimates the emotions of the craftsman and determines the priority of the output based on the estimated emotions. For example, if the craftsman is relaxed, the output unit prioritizes providing detailed output. For example, the output unit captures the craftsman's facial expression with a camera, uses an emotion estimation algorithm to determine if they are relaxed, and prioritizes providing detailed output. Also, if the craftsman is in a hurry, the output unit prioritizes providing concise output that gets straight to the point. For example, the output unit records the craftsman's voice, uses voice analysis technology to determine if they are in a hurry, and prioritizes providing concise output. Furthermore, if the craftsman is excited, the output unit prioritizes providing visually stimulating output. For example, the output unit collects the craftsman's biometric data (heart rate and skin electrical activity) with sensors, uses an emotion estimation algorithm to determine if they are excited, and prioritizes providing visually stimulating output. In this way, by determining the priority of the output according to the craftsman's emotions, important information can be provided preferentially. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI may include, but is not limited to, text-generating AI (e.g., LLM) or multimodal generative AI. Some or all of the processing described above in the output unit may be performed using AI, or not using AI. For example, the output unit could have the AI ​​perform the process of capturing the craftsman's facial expression with a camera, using an emotion estimation algorithm to determine whether the craftsman is relaxed, and prioritizing the provision of detailed output.

[0130] The output unit adjusts the order of outputs based on the data collection timing. For example, the output unit prioritizes outputting recently collected data. For example, the output unit evaluates the data collection timing and prioritizes outputting recently collected data. The output unit also prioritizes outputting data collected during important periods. For example, the output unit evaluates the data collection timing and prioritizes outputting data collected during important periods. Furthermore, the output unit determines the order of outputs based on the data collection timing. For example, the output unit evaluates the data collection timing and determines the order of outputs. This allows for the priority provision of the latest information by adjusting the order of outputs based on the data collection timing. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can have AI perform the process of evaluating the data collection timing and prioritizing the output of recently collected data.

[0131] The output unit adjusts the order of outputs based on the relevance of the data during output. For example, the output unit prioritizes outputting highly relevant data. For example, the output unit evaluates the relevance of the data and prioritizes outputting highly relevant data. The output unit also postpones outputting less relevant data. For example, the output unit evaluates the relevance of the data and postpones outputting less relevant data. Furthermore, the output unit determines the order of outputs based on the relevance of the data. For example, the output unit evaluates the relevance of the data and determines the order of outputs. This allows for the priority provision of highly relevant information by adjusting the order of outputs based on the relevance of the data. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can have AI perform the process of evaluating the relevance of the data and prioritizing the output of highly relevant data.

[0132] The output unit improves the accuracy of the output based on user feedback during output. For example, the output unit analyzes user feedback to improve the accuracy of the output. For example, the output unit analyzes user feedback to improve the accuracy of the output. The output unit also selects an efficient output method based on user feedback. For example, the output unit analyzes user feedback to select an efficient output method. Furthermore, the output unit improves the output algorithm by referring to user feedback. For example, the output unit analyzes user feedback to improve the output algorithm. This improves the accuracy of the output based on user feedback, enabling the provision of more appropriate information. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can have AI perform the process of analyzing user feedback and improving the accuracy of the output.

[0133] The output unit selects the optimal display method when outputting, taking into account the user's device information. For example, if the user is using a smartphone, the output unit provides a display method that matches the screen size. For example, the output unit analyzes the user's device information and provides a display method optimized for the smartphone screen size. Also, if the user is using a tablet, the output unit provides a display method optimized for the larger screen. For example, the output unit analyzes the user's device information and provides a display method optimized for the tablet screen size. Furthermore, if the user is using a smartwatch, the output unit provides a concise and highly visible display method. For example, the output unit analyzes the user's device information and provides a display method optimized for the smartwatch screen size. In this way, the optimal display method can be provided by taking the user's device information into consideration. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can have AI perform the process of analyzing the user's device information and providing a display method optimized for the smartphone screen size.

[0134] The output unit provides multilingual output according to the user's language settings when outputting. For example, the output unit automatically sets the output language based on the language settings of the user's device. For example, the output unit analyzes the user's device information and automatically sets the output language based on the language settings. The output unit also provides a language switching function when the user uses multiple languages. For example, the output unit analyzes the user's language settings and provides output that supports multiple languages. Furthermore, if the user selects a specific language, the output unit provides output in that language. For example, the output unit analyzes the user's language settings and provides output in the selected language. This makes it possible to provide information that is easy for the user to understand by providing multilingual output according to the user's language settings. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can have AI perform the process of analyzing the user's device information and automatically setting the output language based on the language settings.

[0135] The output unit selects the optimal display method when outputting, taking into account the user's health condition. For example, if the user is tired, the output unit provides a simple and highly visible display method. For example, the output unit analyzes the user's health condition and provides a simple and highly visible display method when the user is tired. Furthermore, if the user is healthy, the output unit provides a display method that includes detailed information. For example, the output unit analyzes the user's health condition and provides a display method that includes detailed information when the user is healthy. In addition, if the user is unwell, the output unit provides a less burdensome display method. For example, the output unit analyzes the user's health condition and provides a less burdensome display method when the user is unwell. In this way, a less burdensome display method can be provided by taking the user's health condition into consideration. Some or all of the above processing in the output unit may be performed using AI, for example, or without using AI. For example, the output unit can have AI perform the process of analyzing the user's health condition and providing a simple and highly visible display method when the user is tired.

[0136] The output unit selects the optimal display method when outputting, taking into account the user's past usage history. For example, the output unit prioritizes providing display methods that the user has previously preferred. For example, the output unit analyzes the user's past usage history and prioritizes providing preferred display methods. The output unit also learns and provides the optimal display method from the user's past usage history. For example, the output unit uses a machine learning algorithm to analyze the user's past usage history, learns and provides the optimal display method. Furthermore, the output unit provides a customized display method based on the user's past usage history. For example, the output unit analyzes the user's past usage history and provides a customized display method. This allows for the provision of a customized display method by considering the user's past usage history. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can have AI perform the process of analyzing the user's past usage history and prioritizing the provision of preferred display methods.

[0137] The output unit selects the optimal display method when outputting, taking into account the user's current environmental information. For example, if the user is outdoors, the output unit provides a display method that is highly visible even in bright environments. For example, the output unit analyzes the user's current environmental information and provides a display method that is highly visible even in bright environments when the user is outdoors. Furthermore, if the user is indoors, the output unit provides a display method that includes detailed information. For example, the output unit analyzes the user's current environmental information and provides a display method that includes detailed information when the user is indoors. In addition, the output unit selects the optimal display method based on the user's current environmental information. For example, the output unit analyzes the user's current environmental information and selects the optimal display method. This allows the system to provide the optimal display method by taking into account the user's current environmental information. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can have AI perform the process of analyzing the user's current environmental information and providing a display method that is highly visible even in bright environments when the user is outdoors.

[0138] The output unit selects the optimal display method when outputting, taking into account the battery level of the user's device. For example, if the battery level of the user's device is low, the output unit provides a simple and power-saving display method. For example, the output unit analyzes the user's device information and provides a simple and power-saving display method when the battery level is low. Furthermore, if the battery level of the user's device is sufficient, the output unit provides a display method that includes detailed information. For example, the output unit analyzes the user's device information and provides a display method that includes detailed information when the battery level is sufficient. In addition, the output unit selects the optimal display method based on the battery level of the user's device. For example, the output unit analyzes the user's device information and selects the optimal display method. This allows for the provision of a power-saving display method by considering the battery level of the user's device. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can have AI perform the process of analyzing the user's device information and providing a simple and power-saving display method when the battery level is low.

[0139] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0140] The data collection unit can also estimate the emotions of the craftsman and adjust the timing of data collection based on the estimated emotions. For example, when the craftsman is relaxed, a detailed interview can be conducted to extract deeper knowledge. The data collection unit captures the craftsman's facial expressions with a camera and uses an emotion estimation algorithm to determine if they are relaxed. It can also video record the craftsman's work when they are concentrating to capture natural movements. The data collection unit records the craftsman's voice and uses voice analysis technology to determine if they are concentrating. Furthermore, when the craftsman is tired, a short interview can be conducted to reduce their burden. The data collection unit collects the craftsman's biometric data (heart rate and skin electrical activity) with sensors and uses an emotion estimation algorithm to determine if they are tired. This allows for the collection of more appropriate data by adjusting the timing of data collection according to the craftsman's emotions.

[0141] The analysis unit can also determine the priority of analysis based on the data collection period when analyzing collected data and extracting important points. For example, it can prioritize the analysis of recently collected data. The analysis unit evaluates the data collection period and prioritizes the analysis of recently collected data. It can also prioritize the analysis of data collected at important periods. The analysis unit evaluates the data collection period and prioritizes the analysis of data collected at important periods. Furthermore, it can also determine the order of analysis based on the data collection period. The analysis unit evaluates the data collection period and determines the order of analysis. This enables efficient analysis by determining the priority of analysis based on the data collection period.

[0142] The storage unit can improve the accuracy of data storage by considering the interrelationships between analyzed data. For example, it can analyze the interrelationships between data and store related data together. The storage unit analyzes the interrelationships between data and stores related data together. It can also select an efficient storage method by considering the interrelationships between data. The storage unit analyzes the interrelationships between data and selects an efficient storage method. Furthermore, it can improve the accuracy of storage based on the interrelationships between data. The storage unit analyzes the interrelationships between data and improves the accuracy of storage. As a result, the accuracy of storage is improved by considering the interrelationships between data.

[0143] The memory unit can also estimate the emotions of the craftsman when storing accumulated data, and select the data to store based on the estimated emotions. For example, if the craftsman is relaxed, detailed techniques and know-how can be stored. The memory unit captures the craftsman's facial expressions with a camera, uses an emotion estimation algorithm to determine if they are relaxed, and stores detailed techniques and know-how. Also, if the craftsman is focused, important work data can be stored. The memory unit records the craftsman's voice, uses voice analysis technology to determine if they are focused, and stores important work data. Furthermore, if the craftsman is tired, simpler data can be stored. The memory unit collects the craftsman's biometric data (heart rate and skin electrical activity) with sensors, uses an emotion estimation algorithm to determine if they are tired, and stores simpler data. In this way, by selecting the data to store according to the craftsman's emotions, important data can be prioritized for storage.

[0144] The classification unit can also classify stored data by considering the attribute information of the data submitter. For example, if the data submitter is a craftsman, the data can be classified based on their skills and know-how. The classification unit analyzes the submitter's attribute information and classifies the data based on the craftsman's skills and know-how. Similarly, if the data submitter is an engineer, the data can be classified based on their area of ​​expertise. The classification unit analyzes the submitter's attribute information and classifies the data based on the engineer's area of ​​expertise. Furthermore, the classification unit can select the optimal classification method based on the data submitter's attribute information. The classification unit analyzes the submitter's attribute information and selects the optimal classification method. This allows for more appropriate classification by considering the attribute information of the data submitter.

[0145] The output unit can estimate the craftsman's emotions when providing specific instructions based on classified data, and adjust the output method based on the estimated emotions. For example, if the craftsman is relaxed, detailed output can be provided. The output unit captures the craftsman's facial expressions with a camera, uses an emotion estimation algorithm to determine if they are relaxed, and provides detailed output. Also, if the craftsman is in a hurry, concise output focusing on the key points can be provided. The output unit records the craftsman's voice, uses voice analysis technology to determine if they are in a hurry, and provides concise output. Furthermore, if the craftsman is excited, visually stimulating output can be provided. The output unit collects the craftsman's biometric data (heart rate and skin electrical activity) with sensors, uses an emotion estimation algorithm to determine if they are excited, and provides visually stimulating output. In this way, by adjusting the output method according to the craftsman's emotions, more appropriate information can be provided.

[0146] The data collection department can also analyze a craftsman's past work history and select the optimal data collection method. For example, it can analyze videos of a craftsman's past work, extract key points, and create interview questions. The data collection department uses video analysis technology to analyze past work videos and extract key points. It can also identify particularly important techniques and know-how from a craftsman's past work history and focus data collection on those. The data collection department uses text analysis technology to analyze past work history and identify important techniques and know-how. Furthermore, it can determine the optimal timing and method of data collection based on a craftsman's past work history. The data collection department uses machine learning algorithms to analyze past work history and determine the optimal timing and method of data collection. This allows for the selection of the optimal data collection method by analyzing past work history.

[0147] The analysis unit can also estimate the craftsman's emotions when analyzing collected data and extracting key points, and adjust the presentation of the analysis based on the estimated emotions. For example, if the craftsman is relaxed, it can provide detailed analysis results. The analysis unit captures the craftsman's facial expressions with a camera, uses an emotion estimation algorithm to determine if they are relaxed, and provides detailed analysis results. If the craftsman is in a hurry, it can provide concise analysis results that get straight to the point. The analysis unit records the craftsman's voice, uses voice analysis technology to determine if they are in a hurry, and provides concise analysis results. Furthermore, if the craftsman is excited, it can provide analysis results with visually stimulating effects. The analysis unit collects the craftsman's biometric data (heart rate and skin electrical activity) with sensors, uses an emotion estimation algorithm to determine if they are excited, and provides analysis results with visually stimulating effects. In this way, by adjusting the presentation of the analysis according to the craftsman's emotions, more appropriate analysis results can be provided.

[0148] The storage unit can optimize its storage algorithm by referencing past stored data when storing accumulated data. For example, it can analyze past stored data and select the optimal storage algorithm. The storage unit analyzes past stored data and selects the optimal storage algorithm. It can also learn efficient storage methods from past stored data. The storage unit uses machine learning algorithms to analyze past stored data and learn efficient storage methods. Furthermore, it can improve the storage algorithm based on past stored data. The storage unit analyzes past stored data and improves the storage algorithm. In this way, the storage algorithm can be optimized by referring to past stored data.

[0149] The output unit can improve the accuracy of its output based on user feedback when providing specific procedures based on classified data. For example, it can analyze user feedback to improve the accuracy of the output. The output unit analyzes user feedback and improves the accuracy of the output. It can also select an efficient output method based on user feedback. The output unit analyzes user feedback and selects an efficient output method. Furthermore, it can improve the output algorithm by referring to user feedback. The output unit analyzes user feedback and improves the output algorithm. As a result, by improving the accuracy of the output based on user feedback, it becomes possible to provide more appropriate information.

[0150] The following briefly describes the processing flow for example form 2.

[0151] Step 1: The data collection unit digitizes the know-how of craftsmen and technicians. For example, it collects language data and image data, and records what craftsmen say and converts it into text data. It can also videotape craftsmen at work and save it as image data. Furthermore, it can scan drawings and blueprints created by craftsmen and convert them into digital data. Step 2: The analysis unit analyzes the collected data. For example, it can analyze the collected data to extract important points and extract frequently occurring keywords from text data. It can also detect specific patterns from image data and extract motion characteristics from video data. Step 3: The storage unit stores the analyzed data. For example, it can save the analyzed data to a database and save text data to a database. It can also save image data to cloud storage and perform backups for long-term storage of video data. Step 4: The memory unit stores the accumulated data. For example, it performs backups for long-term storage of accumulated data and implements data redundancy to prevent data loss. It can also encrypt data to ensure security. Furthermore, it can set data access permissions to prevent unauthorized use of data. Step 5: The classification unit categorizes the stored data. For example, it categorizes stored data, classifying text data into technical categories or work procedure categories. It can also classify image data into product categories or parts categories, and video data into work process categories or motion pattern categories. Step 6: The output section provides specific procedures based on the classified data. For example, it can generate work manuals based on classified data and create work procedure documents based on data classified into technical categories. It can also create operation guides based on data classified into product categories and procedure documents based on data classified into work process categories.

[0152] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0153] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0154] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0155] Each of the multiple elements described above, including the data acquisition unit, analysis unit, storage unit, memory unit, classification unit, and output unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the data acquisition unit records the craftsman's work using the camera 42 and microphone 38B of the smart device 14 and collects the data using the control unit 46A. The analysis unit is implemented in the identification processing unit 290 of the data processing unit 12, for example, and analyzes the collected data to extract important points. The storage unit stores the analyzed data in the database 24 of the data processing unit 12, for example. The memory unit stores the data long-term in the storage 32 of the data processing unit 12, for example. The classification unit categorizes the data using the identification processing unit 290 of the data processing unit 12, for example. The output unit generates a work manual using the control unit 46A of the smart device 14 and displays it on the display 40A. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0156] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0157] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0158] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0159] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0160] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0161] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0162] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0163] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0164] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0165] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0166] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0167] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0168] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0169] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0170] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0171] Each of the multiple elements described above, including the data acquisition unit, analysis unit, storage unit, memory unit, classification unit, and output unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the data acquisition unit records the craftsman's work using the camera 42 and microphone 238 of the smart glasses 214 and collects the data with the control unit 46A. The analysis unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, which analyzes the collected data and extracts important points. The storage unit stores the analyzed data in, for example, the database 24 of the data processing unit 12. The memory unit stores the data long-term in, for example, the storage 32 of the data processing unit 12. The classification unit categorizes the data by, for example, the identification processing unit 290 of the data processing unit 12. The output unit generates a work manual by, for example, the control unit 46A of the smart glasses 214 and displays it on the display. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0172] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0173] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0174] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0175] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0176] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0177] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0178] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0179] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0180] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0181] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0182] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0183] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0184] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0185] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0186] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0187] Each of the multiple elements described above, including the data acquisition unit, analysis unit, storage unit, memory unit, classification unit, and output unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the data acquisition unit records the craftsman's work using the camera 42 and microphone 238 of the headset terminal 314 and collects the data using the control unit 46A. The analysis unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, which analyzes the collected data and extracts important points. The storage unit stores the analyzed data in, for example, the database 24 of the data processing unit 12. The memory unit stores the data long-term in, for example, the storage 32 of the data processing unit 12. The classification unit categorizes the data using, for example, the identification processing unit 290 of the data processing unit 12. The output unit generates a work manual using, for example, the control unit 46A of the headset terminal 314 and displays it on the display 343. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0188] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0189] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0190] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0191] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0192] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0193] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0194] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0195] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0196] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0197] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0198] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0199] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0200] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0201] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0202] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0203] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0204] Each of the multiple elements described above, including the data acquisition unit, analysis unit, storage unit, memory unit, classification unit, and output unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the data acquisition unit records the worker's work using the camera 42 and microphone 238 of the robot 414 and collects the data using the control unit 46A. The analysis unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, which analyzes the collected data and extracts important points. The storage unit stores the analyzed data in, for example, the database 24 of the data processing unit 12. The memory unit stores the data long-term in, for example, the storage 32 of the data processing unit 12. The classification unit categorizes the data using, for example, the identification processing unit 290 of the data processing unit 12. The output unit generates a work manual using, for example, the control unit 46A of the robot 414 and displays it on the display device. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0205] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0206] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0207] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0208] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0209] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0210] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0211] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0212] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0213] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0214] 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.

[0215] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0216] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0217] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0218] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0219] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0220] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0221] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0222] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0223] (Note 1) The data collection department digitizes the know-how of craftsmen and technicians, An analysis unit analyzes the data collected by the data acquisition unit, A storage unit that stores the data analyzed by the aforementioned analysis unit, A storage unit that stores the data stored by the aforementioned storage unit, A classification unit that classifies the data stored by the aforementioned storage unit, The system includes an output unit that provides output based on the data classified by the classification unit. A system characterized by the following features. (Note 2) The aforementioned data acquisition unit is Collect language data and image data. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit, Analyze the collected data to extract key points. The system described in Appendix 1, characterized by the features described herein. (Note 4) The storage unit is Accumulate the analyzed data. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned storage unit is Stores accumulated data The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned classification unit is Classify stored data The system described in Appendix 1, characterized by the features described herein. (Note 7) The output unit is, Provide specific procedures based on classified data. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned data acquisition unit is The system estimates the emotions of the craftsmen and adjusts the timing of data collection based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned data acquisition unit is Analyze the craftsman's past work history and select the optimal data collection method. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned data acquisition unit is When collecting data, filtering is performed based on the craftsman's current work status and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned data acquisition unit is The system estimates the emotions of the craftsmen and prioritizes the data to collect based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned data acquisition unit is When collecting data, the geographical location of the craftsmen is taken into consideration, and the collection of highly relevant data is prioritized. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned data acquisition unit is During data collection, analyze the social media activity of artisans and collect relevant data. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, We estimate the emotions of the craftsman and adjust the representation of the analysis based on the estimated emotions of the craftsman. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, During analysis, adjust the level of detail based on the importance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, During analysis, different analysis algorithms are applied depending on the data category. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, The system estimates the emotions of the craftsman and adjusts the length of the analysis based on the estimated emotions of the craftsman. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, During analysis, the priority of the analysis is determined based on when the data was collected. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned analysis unit, During analysis, adjust the order of analysis based on the relevance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 20) The storage unit is The system estimates the emotions of the craftsmen and selects the data to be stored based on the estimated emotions of the craftsmen. The system described in Appendix 1, characterized by the features described herein. (Note 21) The storage unit is During data storage, the storage algorithm is optimized by referring to past stored data. The system described in Appendix 1, characterized by the features described herein. (Note 22) The storage unit is During data storage, the accuracy of the storage is improved by considering the interrelationships between the data. The system described in Appendix 1, characterized by the features described herein. (Note 23) The storage unit is The system estimates the emotions of the craftsmen and adjusts the frequency of accumulation based on the estimated emotions of the craftsmen. The system described in Appendix 1, characterized by the features described herein. (Note 24) The storage unit is During data storage, the stored data is weighted based on the time of data collection. The system described in Appendix 1, characterized by the features described herein. (Note 25) The storage unit is During data storage, we improve the accuracy of the storage by referring to relevant literature. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned storage unit is The system estimates the emotions of the craftsmen and selects data to store based on the estimated emotions of the craftsmen. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned storage unit is During memory storage, the memory algorithm is optimized by referencing past memory data. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned storage unit is During memorization, the accuracy of memory is improved by considering the interrelationships between data. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned storage unit is The system estimates the emotions of the craftsman and adjusts the frequency of memories based on the estimated emotions of the craftsman. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned storage unit is During storage, the stored data is weighted based on when it was collected. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned storage unit is When memorizing data, referencing relevant literature improves the accuracy of memory. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned classification unit is We estimate the emotions of the craftsmen and adjust the classification criteria based on the estimated emotions of the craftsmen. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned classification unit is When classifying data, consider the interrelationships between data to improve classification accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned classification unit is When classifying data, the attribute information of the data submitter is taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned classification unit is The system estimates the emotions of the craftsmen and adjusts the order in which the classification results are displayed based on the estimated emotions of the craftsmen. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned classification unit is When classifying data, consider its geographical distribution. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned classification unit is When classifying data, we refer to relevant literature to improve the accuracy of the classification. The system described in Appendix 1, characterized by the features described herein. (Note 38) The output unit is, The system estimates the emotions of the craftsman and adjusts the output method based on the estimated emotions of the craftsman. The system described in Appendix 1, characterized by the features described herein. (Note 39) The output unit is, When outputting, adjust the level of detail in the output based on the importance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 40) The output unit is, When outputting data, different output algorithms are applied depending on the data category. The system described in Appendix 1, characterized by the features described herein. (Note 41) The output unit is, The system estimates the emotions of the craftsmen and determines the priority of the output based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 42) The output unit is, At the time of output, adjust the order of output based on the data collection time The system according to Appendix 1, characterized in that (Appendix 43) The output unit At the time of output, adjust the order of output based on the relevance of the data The system according to Appendix 1, characterized in that (Appendix 44) The output unit At the time of output, improve the accuracy of output based on the user's feedback The system according to Appendix 1, characterized in that (Appendix 45) The output unit At the time of output, select an optimal display method considering the user's device information The system according to Appendix 1, characterized in that (Appendix 46) The output unit At the time of output, provide a multilingual output according to the user's language setting The system according to Appendix 1, characterized in that (Appendix 47) The output unit At the time of output, select an optimal display method considering the user's health status The system according to Appendix 1, characterized in that (Appendix 48) The output unit At the time of output, select an optimal display method considering the user's past usage history The system according to Appendix 1, characterized in that (Appendix 49) The output unit At the time of output, select an optimal display method considering the user's current environmental information The system according to Appendix 1, characterized in that (Appendix 50) The output unit When outputting data, the system selects the optimal display method considering the battery level of the user's device. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0224] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The data collection department digitizes the know-how of craftsmen and technicians, An analysis unit analyzes the data collected by the data acquisition unit, A storage unit that stores the data analyzed by the aforementioned analysis unit, A storage unit that stores the data stored by the aforementioned storage unit, A classification unit that classifies the data stored by the aforementioned storage unit, The system includes an output unit that provides output based on the data classified by the classification unit. A system characterized by the following features.

2. The aforementioned data acquisition unit is Collect language data and image data. The system according to feature 1.

3. The aforementioned analysis unit, Analyze the collected data to extract key points. The system according to feature 1.

4. The storage unit is Accumulate the analyzed data. The system according to feature 1.

5. The aforementioned storage unit is Stores accumulated data The system according to feature 1.

6. The aforementioned classification unit is Classify stored data The system according to feature 1.

7. The output unit is, Provide specific procedures based on classified data. The system according to feature 1.

8. The aforementioned data acquisition unit is The system estimates the emotions of the craftsmen and adjusts the timing of data collection based on the estimated emotions. The system according to feature 1.

9. The aforementioned data acquisition unit is Analyze the craftsman's past work history and select the optimal data collection method. The system according to feature 1.

10. The aforementioned data acquisition unit is When collecting data, filtering is performed based on the craftsman's current work status and areas of interest. The system according to feature 1.

Images