system

Abstract

The system according to this embodiment aims to efficiently transfer the skills and knowledge of craftsmen to younger engineers. [Solution] The system according to the embodiment comprises a data collection unit, an analysis unit, a learning unit, and an answering unit. The data collection unit records the work and procedures of craftsmen in video and photographs. The analysis unit analyzes the data recorded by the data collection unit. The learning unit learns skills based on the data analyzed by the analysis unit. The answering unit answers questions from young engineers based on the skills learned by the learning unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, it is difficult to efficiently convey the skills and knowledge of craftsmen to young engineers, and there are problems in the inheritance of technology.

[0005] The system according to the embodiment aims to efficiently convey the skills and knowledge of craftsmen to young engineers.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a data collection unit, an analysis unit, a learning unit, and a response unit. The data collection unit records the work and procedures of craftsmen in video and photographs. The analysis unit analyzes the data recorded by the data collection unit. The learning unit learns skills based on the data analyzed by the analysis unit. The response unit answers questions from junior engineers based on the skills learned by the learning unit. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently transfer the skills and knowledge of craftsmen to younger engineers. [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 controls communication between multiple computers. Examples of communication standards applied 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 expert AI system according to an embodiment of the present invention is a system that creates an expert AI by recording the work and procedures of a craftsman in video and photographs and training a generative AI with it, and constructs a training environment and successor matching platform that enables the AI ​​to answer questions from young technicians based on the knowledge and experience of an expert craftsman. The expert AI system meticulously records the work and procedures of a craftsman in video and photographs, explains the work procedures and key points in detail, and conveys the accuracy of the procedures and the subtle nuances of the techniques. Next, the recorded video and photographic data is input into the generative AI, and the AI ​​model is trained to acquire skills. Based on the learned skills, the generative AI can generate new work procedures and products. Furthermore, an interactive training platform utilizing the generative AI is developed to transfer skills through dialogue with the craftsman. Through the interaction between the craftsman and the AI, it is possible to reproduce judgments and technical guidance during actual work. In addition, the AI ​​provides real-time feedback, making suggestions and giving advice, so that craftsmen can improve their skills during actual work. Furthermore, VR technology is used to reproduce the work of a craftsman, enabling practice and training in a simulated environment. Using generative AI, it is also possible to simulate challenges and situations that craftsmen might encounter during actual work. This allows craftsmen to acquire skills in a setting close to their actual work environment. Furthermore, a successor matching platform can be built to match young technicians with experienced craftsmen. This allows young technicians to receive direct instruction from experienced craftsmen, ensuring a smooth transfer of skills. In addition, craftsmen themselves can train AI models and provide their skills and knowledge as content. Other craftsmen and learners can then use this content to acquire skills. This system ensures that craftsmen's skills and knowledge are passed on to the next generation, enabling the preservation and reproduction of traditional crafts and techniques. It also promotes the training of young technicians, resolving the problem of successor shortages. Moreover, by utilizing VR technology, it is possible to recreate destroyed world heritage sites and preserve traditional crafts, thus maintaining their cultural value. This allows the expert AI system to record, analyze, and learn from the work and procedures of craftsmen, and answer questions from young technicians.

[0029] The expert AI system according to this embodiment comprises a data collection unit, an analysis unit, a learning unit, and an answering unit. The data collection unit records the work and procedures of an expert in video and photographs. The work and procedures of an expert include, but are not limited to, woodworking, metalworking, cooking, etc. The data collection unit can, for example, film the work of an expert with a high-resolution camera and save it as video data. The data collection unit can also record the work of an expert as a series of photographs and save the detailed procedures as photographic data. Furthermore, the data collection unit can film the work of an expert from multiple angles and record it from a three-dimensional perspective. For example, the data collection unit can film the hands of an expert in close-up and record their fine movements in detail. The analysis unit analyzes the data recorded by the data collection unit. The analysis unit can, for example, use image analysis technology to analyze the movements of the expert's hands and how they use tools. The analysis unit can also use motion analysis technology to analyze the work procedures of an expert. Furthermore, the analysis unit can use data mining technology to extract important patterns and features from the work data of an expert. For example, the analysis unit uses image analysis technology to analyze the trajectory of a craftsman's hand movements and evaluate the accuracy of the movements. The learning unit learns skills based on the data analyzed by the analysis unit. The learning unit learns the craftsman's work data, for example, using machine learning algorithms. The learning unit can also learn the craftsman's work procedures using supervised learning. Furthermore, the learning unit can discover new patterns from the craftsman's work data using unsupervised learning. For example, the learning unit uses machine learning algorithms to classify the craftsman's work data and learn the characteristics of each work procedure. The answering unit answers questions from junior engineers based on the skills learned by the learning unit. The answering unit analyzes the junior engineer's questions and generates appropriate answers, for example, using natural language processing technology. The answering unit can also provide answers to the junior engineer's questions using an FAQ database. Furthermore, the answering unit can provide expert answers to the junior engineer's questions using an expert system. For example, the answering unit analyzes the junior engineer's questions using natural language processing technology, searches for relevant knowledge, and generates answers.As a result, the expert AI system according to this embodiment can record, analyze, and learn from the work and procedures of craftsmen, and answer questions from young engineers.

[0030] The data collection unit records the work and procedures of craftsmen using video and photographs. These include, but are not limited to, woodworking, metalworking, and cooking. For example, the unit can film the craftsmen's work with a high-resolution camera and save it as video data. Specifically, using 4K or 8K high-resolution cameras allows for clear recording of even the smallest details. The unit can also record the craftsmen's work as a series of photographs, saving detailed procedures as photographic data. For example, by taking dozens of photos per second, subtle changes in movement can be captured. Furthermore, the unit can film the craftsmen's work from multiple angles, recording it from a three-dimensional perspective. For example, by positioning multiple cameras and filming simultaneously from different viewpoints, a 3D model can be generated. This allows for close-ups of the craftsmen's hands, recording even the smallest movements in detail. Additionally, the unit can record audio, simultaneously capturing the craftsmen's explanations and work sounds, enabling the collection of more comprehensive data. This allows the data collection unit to comprehensively record the craftsman's work and provide detailed data.

[0031] The analysis unit analyzes the data recorded by the collection unit. For example, the analysis unit uses image analysis technology to analyze the hand movements and tool usage of craftsmen. Specifically, it applies image recognition algorithms using deep learning to analyze hand movements, tool position, angle, and movement speed in detail. The analysis unit can also analyze the work procedures of craftsmen using motion analysis technology. For example, motion capture technology can be used to reproduce the movements of a craftsman's body as a 3D model and evaluate the accuracy and efficiency of the movements. Furthermore, the analysis unit can use data mining technology to extract important patterns and features from the craftsman's work data. For example, it can identify frequently used movement patterns and efficient movements in specific work procedures. By combining these technologies, the analysis unit can perform a detailed analysis of the craftsman's work, evaluate skills, and identify areas for improvement. Furthermore, the analysis unit can visualize the analysis results and present them in an easy-to-understand format as graphs and charts. In this way, the analysis unit can analyze the collected data from multiple angles and support a detailed understanding of the craftsman's skills and work procedures.

[0032] The learning unit learns skills based on data analyzed by the analysis unit. For example, the learning unit learns from craftsmen's work data using machine learning algorithms. Specifically, it constructs a neural network using deep learning to model the craftsmen's actions and procedures. The learning unit can also learn craftsmen's work procedures using supervised learning. For example, it trains the model using ground truth data of tasks performed by craftsmen to accurately reproduce procedures. Furthermore, the learning unit can discover new patterns from craftsmen's work data using unsupervised learning. For example, it can use clustering algorithms to group similar work procedures and extract common features. By combining these techniques, the learning unit can learn craftsmen's skills with high accuracy and improve the accuracy of the model. Moreover, the learning unit can perform continuous learning, updating the model whenever new data is added to reflect the latest skills and procedures. This allows the learning unit to efficiently learn craftsmen's skills and always provide up-to-date information.

[0033] The answering unit responds to questions from junior engineers based on skills learned by the learning unit. For example, the answering unit uses natural language processing techniques to analyze junior engineers' questions and generate appropriate answers. Specifically, it performs topic modeling and contextual analysis to understand the intent of the questions and searches for relevant knowledge. The answering unit can also provide answers to junior engineers' questions using an FAQ database. For example, it searches a database of previously accumulated questions and answers to present the most appropriate answer. Furthermore, the answering unit can provide expert answers to junior engineers' questions using an expert system. For example, it uses a rule-based inference engine to generate answers based on specific conditions. By combining these technologies, the answering unit can respond quickly and accurately to a wide range of questions from junior engineers. In addition, the answering unit can collect user feedback and continuously improve the accuracy and usefulness of its answers. For example, it revises its answers based on evaluations and comments to provide better answers. The answering unit also provides an interactive interface, allowing junior engineers to obtain more detailed information by repeatedly asking questions. This allows the answer section to support the skill development of young engineers and promote efficient learning.

[0034] The reproduction unit can reproduce the work of a craftsman using VR technology. For example, the reproduction unit can reproduce the work of a craftsman in a virtual reality space using a head-mounted display. The reproduction unit can also reproduce the movements of a craftsman in real time using motion capture technology. Furthermore, the reproduction unit can reproduce the work environment of a craftsman in a virtual space using 3D modeling technology. For example, the reproduction unit allows a user wearing a head-mounted display to experience the work of a craftsman from a 360-degree perspective. This allows the work of a craftsman to be reproduced using VR technology. Some or all of the above processing in the reproduction unit may be performed using, for example, a generative AI, or without a generative AI. For example, the reproduction unit can input the craftsman's motion data into a generative AI and have the generative AI perform the motion reproduction in the virtual space.

[0035] The matching unit can build a successor matching platform. The matching unit can, for example, use a skill matching algorithm to match young engineers with skilled craftsmen. The matching unit can also match young engineers with skilled craftsmen based on shared interests. Furthermore, the matching unit can also match young engineers with skilled craftsmen while considering regional characteristics. For example, the matching unit compares the skill profiles of young engineers with those of skilled craftsmen to perform the optimal match. This enables the construction of a successor matching platform. Some or all of the above processes in the matching unit may be performed using, for example, a generative AI, or not. For example, the matching unit can input profile data of young engineers and skilled craftsmen into a generative AI and have the generative AI perform the optimal match.

[0036] The data collection unit can analyze a craftsman's past work history and select the optimal recording method. For example, the data collection unit can record similar procedures based on work procedures that the craftsman has successfully performed in the past. Alternatively, the data collection unit can record different procedures to avoid work procedures that the craftsman has failed at in the past. Furthermore, the data collection unit can select the most efficient recording method from the craftsman's past work history. For example, the data collection unit can input the craftsman's work history data into a generating AI and have the generating AI execute the optimal recording method. This allows the data collection unit to analyze the craftsman's past work history and select the optimal recording method. Some or all of the above processing in the data collection unit may be performed using a generating AI, for example, or without using a generating AI.

[0037] The data collection unit can filter recordings based on the craftsman's current work environment and the tools they use. For example, the unit can select the optimal camera angle depending on the type of tools the craftsman uses. The unit can also adjust the exposure settings of the recordings based on the lighting conditions of the work environment. Furthermore, the unit can filter audio recordings based on the noise level of the work environment. For example, the unit can select the optimal camera angle depending on the type of tools the craftsman uses and record detailed work procedures. This allows for filtering based on the craftsman's current work environment and the tools they use. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not. For example, the data collection unit can input work environment data into the AI ​​and have the AI ​​perform the optimal filtering method.

[0038] The data collection unit can prioritize recording highly relevant tasks by considering the geographical location information of the craftsman during recording. For example, the data collection unit can prioritize recording tasks performed by a craftsman in a specific region. The data collection unit can also record region-specific techniques and procedures based on geographical location information. Furthermore, the data collection unit can record tasks performed by craftsmen while they are on the move in real time. For example, the data collection unit can acquire the geographical location information of a craftsman and prioritize recording highly relevant tasks. This allows for the priority recording of highly relevant tasks by considering the geographical location information of the craftsman. Some or all of the above processing in the data collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data collection unit can input geographical location information into a generative AI and cause the generative AI to execute a method for prioritizing the recording of highly relevant tasks.

[0039] The data collection unit can analyze the craftsman's social media activity and record relevant tasks during recording. For example, the data collection unit can record relevant tasks based on the work content shared by the craftsman on social media. The data collection unit can also analyze reactions and comments on social media and record tasks with high demand. Furthermore, the data collection unit can record in detail the techniques and procedures introduced by the craftsman on social media. For example, the data collection unit can analyze the craftsman's social media activity and record relevant tasks. This allows the data collection unit to analyze the craftsman's social media activity and record relevant tasks. Some or all of the above processing in the data collection unit may be performed using, for example, generative AI, or not using generative AI. For example, the data collection unit can input social media data into a generative AI and have the generative AI execute a method for recording relevant tasks.

[0040] The analysis unit can adjust the level of detail of the analysis based on the importance of the task during the analysis. For example, the analysis unit will perform a detailed analysis for important work procedures. It can also perform a concise analysis for general work procedures. Furthermore, the analysis unit can adjust the depth of the analysis according to the importance of the task. For example, the analysis unit will evaluate the importance of the task and perform a detailed analysis for important work procedures. This allows the level of detail of the analysis to be adjusted based on the importance of the task. Some or all of the above processing in the analysis unit may be performed using, for example, a generating AI, or without a generating AI. For example, the analysis unit can input work data into a generating AI and have the generating AI execute a method to adjust the level of detail of the analysis based on importance.

[0041] The analysis unit can apply different analysis algorithms depending on the category of work during analysis. For example, for woodworking work, the analysis unit can apply an analysis algorithm that takes into account the properties of wood. Similarly, for metalworking work, the analysis unit can apply an analysis algorithm that takes into account the properties of metal. Furthermore, for weaving work, the analysis unit can apply an analysis algorithm that takes into account the properties of fiber. For example, the analysis unit analyzes woodworking work data and applies an analysis algorithm that takes into account the properties of wood. This allows for the application of different analysis algorithms depending on the category of work. Some or all of the above-described processes in the analysis unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the analysis unit can input work data into a generative AI and have the generative AI execute an analysis algorithm appropriate to the category.

[0042] The analysis unit can determine the priority of analysis based on the timing of the work performed. For example, the analysis unit can prioritize the analysis of the most recent work. It can also postpone the analysis of past work. Furthermore, the analysis unit can adjust the order of analysis according to the timing of the work performed. For example, the analysis unit can evaluate the timing of the work and prioritize the analysis of the most recent work. This allows the analysis priority to be determined based on the timing of the work performed. Some or all of the above processing in the analysis unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the analysis unit can input work data into a generating AI and have the generating AI execute a method for determining the priority of analysis based on the timing of the work performed.

[0043] The analysis unit can adjust the order of analysis based on the relevance of the tasks during the analysis. For example, the analysis unit can prioritize the analysis of tasks with high relevance. It can also postpone the analysis of tasks with low relevance. Furthermore, the analysis unit can adjust the order of analysis according to the relevance of the tasks. For example, the analysis unit can evaluate the relevance of the tasks and prioritize the analysis of tasks with high relevance. This allows the order of analysis to be adjusted based on the relevance of the tasks. Some or all of the above processing in the analysis unit may be performed using, for example, a generating AI, or without a generating AI. For example, the analysis unit can input task data into a generating AI and have the generating AI execute a method for adjusting the order of analysis based on relevance.

[0044] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal learning algorithm based on past learning data. The learning unit can also extract effective learning methods from past learning data. Furthermore, the learning unit can analyze past learning data and optimize the learning algorithm. For example, the learning unit can refer to past learning data and select the optimal learning algorithm. This allows the learning algorithm to be optimized by referring to past learning data. Some or all of the above processes in the learning unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the learning unit can input past learning data into a generative AI and have the generative AI perform the optimization of the learning algorithm.

[0045] The learning unit can apply different learning methods to each category of work during the learning process. For example, the learning unit can apply a learning method that takes into account the properties of wood to woodworking tasks. It can also apply a learning method that takes into account the properties of metal to metalworking tasks. Furthermore, it can apply a learning method that takes into account the properties of fibers to weaving tasks. For example, the learning unit learns woodworking task data and applies a learning method that takes into account the properties of wood. This allows different learning methods to be applied to each category of work. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input work data into a generative AI and have the generative AI execute a learning method appropriate to the category.

[0046] The learning unit can weight the training data based on the timing of the work performed during training. For example, the learning unit can give a higher weight to the most recent work data. It can also give a lower weight to past work data. Furthermore, the learning unit can adjust the weighting of the training data according to the timing of the work performed. For example, the learning unit can evaluate the timing of the work and give a higher weight to the most recent work data. This allows the training data to be weighted based on the timing of the work performed. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input work data into a generative AI and have the generative AI perform a method of weighting the training data based on the timing of the work performed.

[0047] The learning unit can improve the accuracy of its learning by referring to relevant literature during the learning process. For example, the learning unit improves the accuracy of the learning data based on relevant literature. The learning unit can also extract effective learning methods from the relevant literature. Furthermore, the learning unit can optimize the learning algorithm by referring to relevant literature. For example, the learning unit improves the accuracy of its learning by referring to relevant literature for the task. This allows the learning unit to improve the accuracy of its learning by referring to relevant literature for the task. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input relevant literature into a generative AI and have the generative AI execute methods to improve the accuracy of its learning.

[0048] The answering unit can adjust the level of detail in its answers based on the importance of the question. For example, it can provide detailed answers to important questions. It can also provide concise answers to general questions. Furthermore, the answering unit can adjust the level of detail in its answers according to the importance of the question. For example, it can evaluate the importance of the question and provide detailed answers to important questions. This allows the level of detail in the answers to be adjusted based on the importance of the question. Some or all of the above processing in the answering unit may be performed using, for example, a generative AI, or without a generative AI. For example, the answering unit can input question data into a generative AI and have the generative AI perform a method to adjust the level of detail in the answers based on importance.

[0049] The answering unit can apply different answering algorithms depending on the category of the question when providing an answer. For example, for technical questions, the answering unit can apply an answering algorithm that includes technical details. It can also apply a step-by-step answering algorithm to procedural questions. Furthermore, it can apply a problem-solving answering algorithm to troubleshooting questions. For example, for technical questions, the answering unit can apply an answering algorithm that includes technical details. This allows for the application of different answering algorithms depending on the category of the question. Some or all of the above processing in the answering unit may be performed using, for example, a generative AI, or without a generative AI. For example, the answering unit can input question data into a generative AI and have the generative AI execute a category-appropriate answering algorithm.

[0050] The answering unit can determine the priority of answers based on when the questions were submitted. For example, it can prioritize answers to recently submitted questions. It can also postpone answers to questions submitted in the past. Furthermore, the answering unit can adjust the order of answers according to when the questions were submitted. For example, it can evaluate when the questions were submitted and prioritize answers to recently submitted questions. This allows the answering unit to determine the priority of answers based on when the questions were submitted. Some or all of the above processing in the answering unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the answering unit can input question data into a generative AI and have the generative AI execute a method for determining the priority of answers based on the submission date.

[0051] The answering unit can adjust the order of answers based on the relevance of the questions when answering. For example, the answering unit will prioritize answering questions that are highly relevant. It can also postpone answering questions that are less relevant. Furthermore, the answering unit can adjust the order of answers according to the relevance of the questions. For example, the answering unit will evaluate the relevance of the questions and prioritize answering questions that are highly relevant. This allows the order of answers to be adjusted based on the relevance of the questions. Some or all of the above processing in the answering unit may be performed using, for example, a generative AI, or without a generative AI. For example, the answering unit can input question data into a generative AI and cause the generative AI to perform a method of adjusting the order of answers based on relevance.

[0052] The reproduction unit can optimize the reproduction algorithm by referring to past reproduction data during reproduction. For example, the reproduction unit can select the optimal reproduction algorithm based on past reproduction data. The reproduction unit can also extract effective reproduction methods from past reproduction data. Furthermore, the reproduction unit can analyze past reproduction data and optimize the reproduction algorithm. For example, the reproduction unit can refer to past reproduction data and select the optimal reproduction algorithm. This allows the reproduction algorithm to be optimized by referring to past reproduction data. Some or all of the above processing in the reproduction unit may be performed using, for example, a generative AI, or without a generative AI. For example, the reproduction unit can input past reproduction data into a generative AI and have the generative AI perform the optimization of the reproduction algorithm.

[0053] The reproduction unit can apply different reproduction methods to each category of work during reproduction. For example, for woodworking work, the reproduction unit can apply a reproduction method that takes into account the properties of wood. Similarly, for metalworking work, the reproduction unit can apply a reproduction method that takes into account the properties of metal. Furthermore, for weaving work, the reproduction unit can apply a reproduction method that takes into account the properties of fibers. For example, the reproduction unit can reproduce woodworking work data and apply a reproduction method that takes into account the properties of wood. This allows for the application of different reproduction methods to each category of work. Some or all of the above-described processing in the reproduction unit may be performed using, for example, a generation AI, or without a generation AI. For example, the reproduction unit can input work data into a generation AI and have the generation AI execute a reproduction method appropriate to the category.

[0054] The reproduction unit can weight the reproduced data based on the timing of the work performed during the reproduction process. For example, the reproduction unit can give a higher weight to the most recent work data. Conversely, the reproduction unit can also give a lower weight to past work data. Furthermore, the reproduction unit can adjust the weighting of the reproduced data according to the timing of the work performed. For example, the reproduction unit can evaluate the timing of the work and give a higher weight to the most recent work data. This allows the reproduction data to be weighted based on the timing of the work performed. Some or all of the above processing in the reproduction unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the reproduction unit can input work data into a generating AI and have the generating AI execute a method for weighting the reproduced data based on the timing of the work performed.

[0055] The reproduction unit can improve the accuracy of reproduction by referring to relevant literature during the reproduction process. For example, the reproduction unit improves the accuracy of the reproduced data based on relevant literature. The reproduction unit can also extract effective reproduction methods from the relevant literature. Furthermore, the reproduction unit can optimize the reproduction algorithm by referring to relevant literature. For example, the reproduction unit improves the accuracy of reproduction by referring to relevant literature for the work. This allows the reproduction unit to improve the accuracy of reproduction by referring to relevant literature for the work. Some or all of the above processing in the reproduction unit may be performed using, for example, a generative AI, or without a generative AI. For example, the reproduction unit can input relevant literature into a generative AI and have the generative AI execute methods to improve the accuracy of reproduction.

[0056] The matching unit can optimize the matching algorithm by referring to past matching data during the matching process. For example, the matching unit can select the optimal matching algorithm based on past matching data. The matching unit can also extract effective matching methods from past matching data. Furthermore, the matching unit can analyze past matching data and optimize the matching algorithm. For example, the matching unit can refer to past matching data and select the optimal matching algorithm. This allows the matching algorithm to be optimized by referring to past matching data. Some or all of the above processes in the matching unit may be performed using, for example, a generative AI, or without a generative AI. For example, the matching unit can input past matching data into a generative AI and have the generative AI perform the optimization of the matching algorithm.

[0057] The matching unit can apply different matching methods to each category of technician during the matching process. For example, the matching unit can apply a matching method that takes into account the properties of wood to woodworking technicians. It can also apply a matching method that takes into account the properties of metal to metalworking technicians. Furthermore, it can apply a matching method that takes into account the properties of fibers to textile technicians. For example, the matching unit matches the data of woodworking technicians and applies a matching method that takes into account the properties of wood. This allows different matching methods to be applied to each category of technician. Some or all of the above processing in the matching unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the matching unit can input technician data into a generation AI and have the generation AI execute a matching method according to the category.

[0058] The matching unit can weight the matching data based on the timing of the engineers' work during the matching process. For example, the matching unit can give a higher weight to recent engineer data. Conversely, it can also give a lower weight to past engineer data. Furthermore, the matching unit can adjust the weighting of the matching data according to the timing of the engineers' work. For example, the matching unit can evaluate the timing of the engineers' work and give a higher weight to recent engineer data. This allows the matching data to be weighted based on the timing of the engineers' work. Some or all of the above processing in the matching unit may be performed using, for example, a generation AI, or without a generation AI. For example, the matching unit can input engineer data into a generation AI and have the generation AI execute a method for weighting the matching data based on the timing of the work.

[0059] The matching unit can improve the accuracy of matching by referring to relevant literature for engineers during the matching process. For example, the matching unit improves the accuracy of matching data based on relevant literature. The matching unit can also extract effective matching methods from relevant literature. Furthermore, the matching unit can optimize the matching algorithm by referring to relevant literature. For example, the matching unit improves the accuracy of matching by referring to relevant literature for engineers. This allows the matching accuracy to be improved by referring to relevant literature for engineers. Some or all of the above processing in the matching unit may be performed using, for example, a generative AI, or without a generative AI. For example, the matching unit can input relevant literature into a generative AI and have the generative AI execute methods to improve the accuracy of matching.

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

[0061] The expert AI system can also be equipped with a data integration unit. This unit centrally manages the work data of skilled craftsmen and the learning data of junior technicians, facilitating their use in the analysis and learning units. For example, the data integration unit can integrate work videos and photos of craftsmen and feedback data from junior technicians, streamlining analysis in the analysis unit. It can also integrate data from different data sources and utilize it for learning in the learning unit. Furthermore, the data integration unit can ensure data consistency and quality, improving the overall reliability of the system. For instance, it can maintain data quality by detecting data duplication and missing data and performing appropriate processing.

[0062] The expert AI system can also be equipped with a performance monitoring unit. This unit monitors the work performance of junior engineers in real time and issues alerts as needed. For example, if a junior engineer makes a mistake during work, the performance monitoring unit can detect the mistake and provide immediate feedback. The performance monitoring unit can also monitor the junior engineer's work speed and efficiency and suggest areas for improvement. Furthermore, the performance monitoring unit can accumulate the junior engineer's work data and analyze long-term performance trends. For instance, it can analyze the junior engineer's work data to identify areas for skill improvement and identify areas for improvement.

[0063] The expert AI system can also be equipped with a knowledge base. This knowledge base systematically organizes information about the craftsman's knowledge and skills, making it easily accessible to younger engineers. For example, the knowledge base can database explanations of the craftsman's work procedures and techniques, and provide a search function. It can also store answers to questions from younger engineers and provide them in an FAQ format. Furthermore, the knowledge base can estimate the craftsman's emotions and adjust the way knowledge is delivered based on those emotions. For example, if the craftsman is relaxed, it can provide detailed explanations; if the craftsman is in a hurry, it can provide concise information.

[0064] The expert AI system can also be equipped with a training simulation unit. This unit provides functions for junior engineers to simulate actual work in a virtual environment and acquire skills. For example, the training simulation unit can use VR technology to recreate the work environment of a skilled craftsman, allowing junior engineers to practice their work in a virtual space. Furthermore, the training simulation unit can estimate the emotions of junior engineers and adjust the difficulty and content of the simulation based on these estimates. For example, if a junior engineer is nervous, the difficulty of the simulation can be lowered to help them relax. Additionally, the training simulation unit can analyze the simulation results and provide feedback to the junior engineers.

[0065] The expert AI system can also be equipped with a data visualization unit. This unit visually displays and simplifies the understanding of the work data of skilled craftsmen and the learning data of junior engineers. For example, it can display a craftsman's work procedures using flowcharts and graphs, making them visually understandable to junior engineers. It can also display the learning progress of junior engineers using graphs and dashboards, allowing for a quick overview of their learning achievements. Furthermore, the data visualization unit can estimate the emotions of junior engineers and adjust the data display based on the estimated emotions. For example, it can display detailed data when a junior engineer is relaxed, and concise, to-the-point data when a junior engineer is in a hurry.

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

[0067] Step 1: The recording unit records the craftsman's work and procedures with video and photographs. For example, tasks such as woodworking, metalworking, and cooking are filmed with a high-resolution camera and saved as video data. It is also possible to record as a series of photographs and save detailed procedures as photographic data. Furthermore, it is possible to film from multiple angles and record from a three-dimensional perspective. For example, close-ups of the craftsman's hands can be filmed to record intricate movements in detail. Step 2: The analysis unit analyzes the data recorded by the collection unit. For example, it can use image analysis technology to analyze the hand movements and tool usage of a craftsman, and motion analysis technology to analyze work procedures. Furthermore, it is possible to extract important patterns and features using data mining technology. For example, it can analyze the trajectory of hand movements to evaluate the accuracy of the movements. Step 3: The learning unit learns skills based on the data analyzed by the analysis unit. For example, it can learn work data of craftsmen using machine learning algorithms and learn work procedures and new patterns using supervised or unsupervised learning. For example, it can classify work data and learn the characteristics of each work procedure. Step 4: The answering unit answers questions from junior engineers based on the skills learned by the learning unit. For example, it can analyze questions using natural language processing technology and generate appropriate answers. It can also provide expert answers using FAQ databases and expert systems. For example, it can search for relevant knowledge and generate answers.

[0068] (Example of form 2) The expert AI system according to an embodiment of the present invention is a system that creates an expert AI by recording the work and procedures of a craftsman in video and photographs and training a generative AI with it, and constructs a training environment and successor matching platform that enables the AI ​​to answer questions from young technicians based on the knowledge and experience of an expert craftsman. The expert AI system meticulously records the work and procedures of a craftsman in video and photographs, explains the work procedures and key points in detail, and conveys the accuracy of the procedures and the subtle nuances of the techniques. Next, the recorded video and photographic data is input into the generative AI, and the AI ​​model is trained to acquire skills. Based on the learned skills, the generative AI can generate new work procedures and products. Furthermore, an interactive training platform utilizing the generative AI is developed to transfer skills through dialogue with the craftsman. Through the interaction between the craftsman and the AI, it is possible to reproduce judgments and technical guidance during actual work. In addition, the AI ​​provides real-time feedback, making suggestions and giving advice, so that craftsmen can improve their skills during actual work. Furthermore, VR technology is used to reproduce the work of a craftsman, enabling practice and training in a simulated environment. Using generative AI, it is also possible to simulate challenges and situations that craftsmen might encounter during actual work. This allows craftsmen to acquire skills in a setting close to their actual work environment. Furthermore, a successor matching platform can be built to match young technicians with experienced craftsmen. This allows young technicians to receive direct instruction from experienced craftsmen, ensuring a smooth transfer of skills. In addition, craftsmen themselves can train AI models and provide their skills and knowledge as content. Other craftsmen and learners can then use this content to acquire skills. This system ensures that craftsmen's skills and knowledge are passed on to the next generation, enabling the preservation and reproduction of traditional crafts and techniques. It also promotes the training of young technicians, resolving the problem of successor shortages. Moreover, by utilizing VR technology, it is possible to recreate destroyed world heritage sites and preserve traditional crafts, thus maintaining their cultural value. This allows the expert AI system to record, analyze, and learn from the work and procedures of craftsmen, and answer questions from young technicians.

[0069] The expert AI system according to this embodiment comprises a data collection unit, an analysis unit, a learning unit, and an answering unit. The data collection unit records the work and procedures of an expert in video and photographs. The work and procedures of an expert include, but are not limited to, woodworking, metalworking, cooking, etc. The data collection unit can, for example, film the work of an expert with a high-resolution camera and save it as video data. The data collection unit can also record the work of an expert as a series of photographs and save the detailed procedures as photographic data. Furthermore, the data collection unit can film the work of an expert from multiple angles and record it from a three-dimensional perspective. For example, the data collection unit can film the hands of an expert in close-up and record their fine movements in detail. The analysis unit analyzes the data recorded by the data collection unit. The analysis unit can, for example, use image analysis technology to analyze the movements of the expert's hands and how they use tools. The analysis unit can also use motion analysis technology to analyze the work procedures of an expert. Furthermore, the analysis unit can use data mining technology to extract important patterns and features from the work data of an expert. For example, the analysis unit uses image analysis technology to analyze the trajectory of a craftsman's hand movements and evaluate the accuracy of the movements. The learning unit learns skills based on the data analyzed by the analysis unit. The learning unit learns the craftsman's work data, for example, using machine learning algorithms. The learning unit can also learn the craftsman's work procedures using supervised learning. Furthermore, the learning unit can discover new patterns from the craftsman's work data using unsupervised learning. For example, the learning unit uses machine learning algorithms to classify the craftsman's work data and learn the characteristics of each work procedure. The answering unit answers questions from junior engineers based on the skills learned by the learning unit. The answering unit analyzes the junior engineer's questions and generates appropriate answers, for example, using natural language processing technology. The answering unit can also provide answers to the junior engineer's questions using an FAQ database. Furthermore, the answering unit can provide expert answers to the junior engineer's questions using an expert system. For example, the answering unit analyzes the junior engineer's questions using natural language processing technology, searches for relevant knowledge, and generates answers.As a result, the expert AI system according to this embodiment can record, analyze, and learn from the work and procedures of craftsmen, and answer questions from young engineers.

[0070] The data collection unit records the work and procedures of craftsmen using video and photographs. These include, but are not limited to, woodworking, metalworking, and cooking. For example, the unit can film the craftsmen's work with a high-resolution camera and save it as video data. Specifically, using 4K or 8K high-resolution cameras allows for clear recording of even the smallest details. The unit can also record the craftsmen's work as a series of photographs, saving detailed procedures as photographic data. For example, by taking dozens of photos per second, subtle changes in movement can be captured. Furthermore, the unit can film the craftsmen's work from multiple angles, recording it from a three-dimensional perspective. For example, by positioning multiple cameras and filming simultaneously from different viewpoints, a 3D model can be generated. This allows for close-ups of the craftsmen's hands, recording even the smallest movements in detail. Additionally, the unit can record audio, simultaneously capturing the craftsmen's explanations and work sounds, enabling the collection of more comprehensive data. This allows the data collection unit to comprehensively record the craftsman's work and provide detailed data.

[0071] The analysis unit analyzes the data recorded by the collection unit. For example, the analysis unit uses image analysis technology to analyze the hand movements and tool usage of craftsmen. Specifically, it applies image recognition algorithms using deep learning to analyze hand movements, tool position, angle, and movement speed in detail. The analysis unit can also analyze the work procedures of craftsmen using motion analysis technology. For example, motion capture technology can be used to reproduce the movements of a craftsman's body as a 3D model and evaluate the accuracy and efficiency of the movements. Furthermore, the analysis unit can use data mining technology to extract important patterns and features from the craftsman's work data. For example, it can identify frequently used movement patterns and efficient movements in specific work procedures. By combining these technologies, the analysis unit can perform a detailed analysis of the craftsman's work, evaluate skills, and identify areas for improvement. Furthermore, the analysis unit can visualize the analysis results and present them in an easy-to-understand format as graphs and charts. In this way, the analysis unit can analyze the collected data from multiple angles and support a detailed understanding of the craftsman's skills and work procedures.

[0072] The learning unit learns skills based on data analyzed by the analysis unit. For example, the learning unit learns from craftsmen's work data using machine learning algorithms. Specifically, it constructs a neural network using deep learning to model the craftsmen's actions and procedures. The learning unit can also learn craftsmen's work procedures using supervised learning. For example, it trains the model using ground truth data of tasks performed by craftsmen to accurately reproduce procedures. Furthermore, the learning unit can discover new patterns from craftsmen's work data using unsupervised learning. For example, it can use clustering algorithms to group similar work procedures and extract common features. By combining these techniques, the learning unit can learn craftsmen's skills with high accuracy and improve the accuracy of the model. Moreover, the learning unit can perform continuous learning, updating the model whenever new data is added to reflect the latest skills and procedures. This allows the learning unit to efficiently learn craftsmen's skills and always provide up-to-date information.

[0073] The answering unit responds to questions from junior engineers based on skills learned by the learning unit. For example, the answering unit uses natural language processing techniques to analyze junior engineers' questions and generate appropriate answers. Specifically, it performs topic modeling and contextual analysis to understand the intent of the questions and searches for relevant knowledge. The answering unit can also provide answers to junior engineers' questions using an FAQ database. For example, it searches a database of previously accumulated questions and answers to present the most appropriate answer. Furthermore, the answering unit can provide expert answers to junior engineers' questions using an expert system. For example, it uses a rule-based inference engine to generate answers based on specific conditions. By combining these technologies, the answering unit can respond quickly and accurately to a wide range of questions from junior engineers. In addition, the answering unit can collect user feedback and continuously improve the accuracy and usefulness of its answers. For example, it revises its answers based on evaluations and comments to provide better answers. The answering unit also provides an interactive interface, allowing junior engineers to obtain more detailed information by repeatedly asking questions. This allows the answer section to support the skill development of young engineers and promote efficient learning.

[0074] The reproduction unit can reproduce the work of a craftsman using VR technology. For example, the reproduction unit can reproduce the work of a craftsman in a virtual reality space using a head-mounted display. The reproduction unit can also reproduce the movements of a craftsman in real time using motion capture technology. Furthermore, the reproduction unit can reproduce the work environment of a craftsman in a virtual space using 3D modeling technology. For example, the reproduction unit allows a user wearing a head-mounted display to experience the work of a craftsman from a 360-degree perspective. This allows the work of a craftsman to be reproduced using VR technology. Some or all of the above processing in the reproduction unit may be performed using, for example, a generative AI, or without a generative AI. For example, the reproduction unit can input the craftsman's motion data into a generative AI and have the generative AI perform the motion reproduction in the virtual space.

[0075] The matching unit can build a successor matching platform. The matching unit can, for example, use a skill matching algorithm to match young engineers with skilled craftsmen. The matching unit can also match young engineers with skilled craftsmen based on shared interests. Furthermore, the matching unit can also match young engineers with skilled craftsmen while considering regional characteristics. For example, the matching unit compares the skill profiles of young engineers with those of skilled craftsmen to perform the optimal match. This enables the construction of a successor matching platform. Some or all of the above processes in the matching unit may be performed using, for example, a generative AI, or not. For example, the matching unit can input profile data of young engineers and skilled craftsmen into a generative AI and have the generative AI perform the optimal match.

[0076] The data collection unit can estimate the emotions of the craftsman and adjust the timing of recording based on the estimated emotions. For example, if the craftsman is concentrating, the data collection unit can adjust the timing of recording to avoid interrupting the work. The data collection unit can also start recording when the craftsman is relaxed and requests a detailed explanation. Furthermore, if the craftsman is tired, the data collection unit can adjust the timing to resume recording after a break. For example, the data collection unit can capture the craftsman's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. This allows the timing of recording to be adjusted based on the craftsman's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using a generative AI, or not. For example, the data collection unit can input the craftsman's facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0077] The data collection unit can analyze a craftsman's past work history and select the optimal recording method. For example, the data collection unit can record similar procedures based on work procedures that the craftsman has successfully performed in the past. Alternatively, the data collection unit can record different procedures to avoid work procedures that the craftsman has failed at in the past. Furthermore, the data collection unit can select the most efficient recording method from the craftsman's past work history. For example, the data collection unit can input the craftsman's work history data into a generating AI and have the generating AI execute the optimal recording method. This allows the data collection unit to analyze the craftsman's past work history and select the optimal recording method. Some or all of the above processing in the data collection unit may be performed using a generating AI, for example, or without using a generating AI.

[0078] The data collection unit can filter recordings based on the craftsman's current work environment and the tools they use. For example, the unit can select the optimal camera angle depending on the type of tools the craftsman uses. The unit can also adjust the exposure settings of the recordings based on the lighting conditions of the work environment. Furthermore, the unit can filter audio recordings based on the noise level of the work environment. For example, the unit can select the optimal camera angle depending on the type of tools the craftsman uses and record detailed work procedures. This allows for filtering based on the craftsman's current work environment and the tools they use. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not. For example, the data collection unit can input work environment data into the AI ​​and have the AI ​​perform the optimal filtering method.

[0079] The data collection unit can estimate the emotions of the craftsman and determine the priority of tasks to record based on the estimated emotions. For example, if the craftsman is focused, the data collection unit may prioritize recording important work procedures. If the craftsman is relaxed, the data collection unit may also prioritize recording work procedures that require detailed explanations. Furthermore, if the craftsman is tired, the data collection unit may also prioritize recording simple work procedures. For example, the data collection unit can capture the craftsman's facial expressions with a camera, estimate their emotions using an emotion estimation algorithm, and determine the priority of tasks. This allows the priority of tasks to be recorded to be determined based on the craftsman's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using a generative AI, or not. For example, the data collection unit can input the craftsman's facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0080] The data collection unit can prioritize recording highly relevant tasks by considering the geographical location information of the craftsman during recording. For example, the data collection unit can prioritize recording tasks performed by a craftsman in a specific region. The data collection unit can also record region-specific techniques and procedures based on geographical location information. Furthermore, the data collection unit can record tasks performed by craftsmen while they are on the move in real time. For example, the data collection unit can acquire the geographical location information of a craftsman and prioritize recording highly relevant tasks. This allows for the priority recording of highly relevant tasks by considering the geographical location information of the craftsman. Some or all of the above processing in the data collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data collection unit can input geographical location information into a generative AI and cause the generative AI to execute a method for prioritizing the recording of highly relevant tasks.

[0081] The data collection unit can analyze the craftsman's social media activity and record relevant tasks during recording. For example, the data collection unit can record relevant tasks based on the work content shared by the craftsman on social media. The data collection unit can also analyze reactions and comments on social media and record tasks with high demand. Furthermore, the data collection unit can record in detail the techniques and procedures introduced by the craftsman on social media. For example, the data collection unit can analyze the craftsman's social media activity and record relevant tasks. This allows the data collection unit to analyze the craftsman's social media activity and record relevant tasks. Some or all of the above processing in the data collection unit may be performed using, for example, generative AI, or not using generative AI. For example, the data collection unit can input social media data into a generative AI and have the generative AI execute a method for recording relevant tasks.

[0082] The analysis unit can estimate the emotions of the craftsman and adjust the presentation of the analysis based on the estimated emotions. For example, if the craftsman is relaxed, the analysis unit can provide detailed analysis results. If the craftsman is in a hurry, the analysis unit can also provide concise analysis results that get straight to the point. Furthermore, if the craftsman is excited, the analysis unit can provide visually stimulating analysis results. For example, the analysis unit can capture the craftsman's facial expression with a camera, estimate the emotion using an emotion estimation algorithm, and adjust the presentation of the analysis. This allows the presentation of the analysis to be adjusted based on the craftsman's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using a generative AI, for example, or not using a generative AI. For example, the analysis unit can input the craftsman's facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0083] The analysis unit can adjust the level of detail of the analysis based on the importance of the task during the analysis. For example, the analysis unit will perform a detailed analysis for important work procedures. It can also perform a concise analysis for general work procedures. Furthermore, the analysis unit can adjust the depth of the analysis according to the importance of the task. For example, the analysis unit will evaluate the importance of the task and perform a detailed analysis for important work procedures. This allows the level of detail of the analysis to be adjusted based on the importance of the task. Some or all of the above processing in the analysis unit may be performed using, for example, a generating AI, or without a generating AI. For example, the analysis unit can input work data into a generating AI and have the generating AI execute a method to adjust the level of detail of the analysis based on importance.

[0084] The analysis unit can apply different analysis algorithms depending on the category of work during analysis. For example, for woodworking work, the analysis unit can apply an analysis algorithm that takes into account the properties of wood. Similarly, for metalworking work, the analysis unit can apply an analysis algorithm that takes into account the properties of metal. Furthermore, for weaving work, the analysis unit can apply an analysis algorithm that takes into account the properties of fiber. For example, the analysis unit analyzes woodworking work data and applies an analysis algorithm that takes into account the properties of wood. This allows for the application of different analysis algorithms depending on the category of work. Some or all of the above-described processes in the analysis unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the analysis unit can input work data into a generative AI and have the generative AI execute an analysis algorithm appropriate to the category.

[0085] The analysis unit can estimate the emotions of the craftsman and adjust the length of the analysis based on the estimated emotions. For example, if the craftsman is relaxed, the analysis unit can provide a detailed analysis. It can also provide a concise analysis if the craftsman is in a hurry. Furthermore, if the craftsman is excited, the analysis unit can provide a visually stimulating analysis. For example, the analysis unit can capture the craftsman's facial expression with a camera, estimate the emotion using an emotion estimation algorithm, and adjust the length of the analysis. This allows the length of the analysis to be adjusted based on the craftsman's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the analysis unit can input the craftsman's facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0086] The analysis unit can determine the priority of analysis based on the timing of the work performed. For example, the analysis unit can prioritize the analysis of the most recent work. It can also postpone the analysis of past work. Furthermore, the analysis unit can adjust the order of analysis according to the timing of the work performed. For example, the analysis unit can evaluate the timing of the work and prioritize the analysis of the most recent work. This allows the analysis priority to be determined based on the timing of the work performed. Some or all of the above processing in the analysis unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the analysis unit can input work data into a generating AI and have the generating AI execute a method for determining the priority of analysis based on the timing of the work performed.

[0087] The analysis unit can adjust the order of analysis based on the relevance of the tasks during the analysis. For example, the analysis unit can prioritize the analysis of tasks with high relevance. It can also postpone the analysis of tasks with low relevance. Furthermore, the analysis unit can adjust the order of analysis according to the relevance of the tasks. For example, the analysis unit can evaluate the relevance of the tasks and prioritize the analysis of tasks with high relevance. This allows the order of analysis to be adjusted based on the relevance of the tasks. Some or all of the above processing in the analysis unit may be performed using, for example, a generating AI, or without a generating AI. For example, the analysis unit can input task data into a generating AI and have the generating AI execute a method for adjusting the order of analysis based on relevance.

[0088] The learning unit can estimate the emotions of a craftsman and select training data based on the estimated emotions. For example, if the craftsman is relaxed, the learning unit will select detailed training data. If the craftsman is in a hurry, the learning unit can also select training data that focuses on the essentials. Furthermore, if the craftsman is excited, the learning unit can select visually stimulating training data. For example, the learning unit can capture the craftsman's facial expressions with a camera, estimate the emotions using an emotion estimation algorithm, and select training data. This allows for the selection of training data based on the craftsman's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the learning unit may be performed using a generative AI, or not. For example, the learning unit can input the craftsman's facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0089] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal learning algorithm based on past learning data. The learning unit can also extract effective learning methods from past learning data. Furthermore, the learning unit can analyze past learning data and optimize the learning algorithm. For example, the learning unit can refer to past learning data and select the optimal learning algorithm. This allows the learning algorithm to be optimized by referring to past learning data. Some or all of the above processes in the learning unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the learning unit can input past learning data into a generative AI and have the generative AI perform the optimization of the learning algorithm.

[0090] The learning unit can apply different learning methods to each category of work during the learning process. For example, the learning unit can apply a learning method that takes into account the properties of wood to woodworking tasks. It can also apply a learning method that takes into account the properties of metal to metalworking tasks. Furthermore, it can apply a learning method that takes into account the properties of fibers to weaving tasks. For example, the learning unit learns woodworking task data and applies a learning method that takes into account the properties of wood. This allows different learning methods to be applied to each category of work. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input work data into a generative AI and have the generative AI execute a learning method appropriate to the category.

[0091] The learning unit can estimate the emotions of the craftsman and adjust the frequency of learning based on the estimated emotions. For example, the learning unit will learn more frequently if the craftsman is relaxed. It can also reduce the frequency of learning if the craftsman is in a hurry. Furthermore, it can adjust the frequency of learning if the craftsman is excited. For example, the learning unit can capture the craftsman's facial expressions with a camera, estimate the emotions using an emotion estimation algorithm, and adjust the frequency of learning. This allows the learning frequency to be adjusted based on the craftsman's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using a generative AI, or not using a generative AI. For example, the learning unit can input the craftsman's facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0092] The learning unit can weight the training data based on the timing of the work performed during training. For example, the learning unit can give a higher weight to the most recent work data. It can also give a lower weight to past work data. Furthermore, the learning unit can adjust the weighting of the training data according to the timing of the work performed. For example, the learning unit can evaluate the timing of the work and give a higher weight to the most recent work data. This allows the training data to be weighted based on the timing of the work performed. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input work data into a generative AI and have the generative AI perform a method of weighting the training data based on the timing of the work performed.

[0093] The learning unit can improve the accuracy of its learning by referring to relevant literature during the learning process. For example, the learning unit improves the accuracy of the learning data based on relevant literature. The learning unit can also extract effective learning methods from the relevant literature. Furthermore, the learning unit can optimize the learning algorithm by referring to relevant literature. For example, the learning unit improves the accuracy of its learning by referring to relevant literature for the task. This allows the learning unit to improve the accuracy of its learning by referring to relevant literature for the task. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input relevant literature into a generative AI and have the generative AI execute methods to improve the accuracy of its learning.

[0094] The response unit can estimate the emotions of the young engineer and adjust the way the response is expressed based on the estimated emotions. For example, if the young engineer is nervous, the response unit will provide a simple and easily understandable response. If the young engineer is relaxed, the response unit can also provide a response that includes detailed information. Furthermore, if the young engineer is in a hurry, the response unit can provide a concise response that gets straight to the point. For example, the response unit can capture the young engineer's facial expression with a camera, estimate their emotions using an emotion estimation algorithm, and adjust the way the response is expressed. This allows the response to be expressed based on the young engineer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the response unit may be performed using, for example, generative AI, or not using generative AI. For example, the response unit can input facial expression data from young engineers into a generating AI and have the AI ​​perform emotion estimation.

[0095] The answering unit can adjust the level of detail in its answers based on the importance of the question. For example, it can provide detailed answers to important questions. It can also provide concise answers to general questions. Furthermore, the answering unit can adjust the level of detail in its answers according to the importance of the question. For example, it can evaluate the importance of the question and provide detailed answers to important questions. This allows the level of detail in the answers to be adjusted based on the importance of the question. Some or all of the above processing in the answering unit may be performed using, for example, a generative AI, or without a generative AI. For example, the answering unit can input question data into a generative AI and have the generative AI perform a method to adjust the level of detail in the answers based on importance.

[0096] The answering unit can apply different answering algorithms depending on the category of the question when providing an answer. For example, for technical questions, the answering unit can apply an answering algorithm that includes technical details. It can also apply a step-by-step answering algorithm to procedural questions. Furthermore, it can apply a problem-solving answering algorithm to troubleshooting questions. For example, for technical questions, the answering unit can apply an answering algorithm that includes technical details. This allows for the application of different answering algorithms depending on the category of the question. Some or all of the above processing in the answering unit may be performed using, for example, a generative AI, or without a generative AI. For example, the answering unit can input question data into a generative AI and have the generative AI execute a category-appropriate answering algorithm.

[0097] The response unit can estimate the emotions of the young engineer and adjust the length of the response based on the estimated emotions. For example, if the young engineer is nervous, the response unit will provide a short, to-the-point response. If the young engineer is relaxed, the response unit can also provide a longer response with more detailed explanations. Furthermore, if the young engineer is in a hurry, the response unit can provide a quick and concise response. For example, the response unit can capture the young engineer's facial expression with a camera, estimate their emotions using an emotion estimation algorithm, and adjust the length of the response. This allows the response length to be adjusted based on the young engineer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the response unit may be performed using a generative AI, or not. For example, the response unit can input the young engineer's facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0098] The answering unit can determine the priority of answers based on when the questions were submitted. For example, it can prioritize answers to recently submitted questions. It can also postpone answers to questions submitted in the past. Furthermore, the answering unit can adjust the order of answers according to when the questions were submitted. For example, it can evaluate when the questions were submitted and prioritize answers to recently submitted questions. This allows the answering unit to determine the priority of answers based on when the questions were submitted. Some or all of the above processing in the answering unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the answering unit can input question data into a generative AI and have the generative AI execute a method for determining the priority of answers based on the submission date.

[0099] The answering unit can adjust the order of answers based on the relevance of the questions when answering. For example, the answering unit will prioritize answering questions that are highly relevant. It can also postpone answering questions that are less relevant. Furthermore, the answering unit can adjust the order of answers according to the relevance of the questions. For example, the answering unit will evaluate the relevance of the questions and prioritize answering questions that are highly relevant. This allows the order of answers to be adjusted based on the relevance of the questions. Some or all of the above processing in the answering unit may be performed using, for example, a generative AI, or without a generative AI. For example, the answering unit can input question data into a generative AI and cause the generative AI to perform a method of adjusting the order of answers based on relevance.

[0100] The reproduction unit can estimate the emotions of the craftsman and adjust the reproduction method based on the estimated emotions. For example, if the craftsman is relaxed, the reproduction unit can provide a detailed reproduction method. It can also provide a concise reproduction method if the craftsman is in a hurry. Furthermore, if the craftsman is excited, the reproduction unit can provide a visually stimulating reproduction method. For example, the reproduction unit can capture the craftsman's facial expression with a camera, estimate the emotion using an emotion estimation algorithm, and adjust the reproduction method. This allows the reproduction method to be adjusted based on the craftsman's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the reproduction unit may be performed using, for example, a generative AI, or not. For example, the reproduction unit can input the craftsman's facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0101] The reproduction unit can optimize the reproduction algorithm by referring to past reproduction data during reproduction. For example, the reproduction unit can select the optimal reproduction algorithm based on past reproduction data. The reproduction unit can also extract effective reproduction methods from past reproduction data. Furthermore, the reproduction unit can analyze past reproduction data and optimize the reproduction algorithm. For example, the reproduction unit can refer to past reproduction data and select the optimal reproduction algorithm. This allows the reproduction algorithm to be optimized by referring to past reproduction data. Some or all of the above processing in the reproduction unit may be performed using, for example, a generative AI, or without a generative AI. For example, the reproduction unit can input past reproduction data into a generative AI and have the generative AI perform the optimization of the reproduction algorithm.

[0102] The reproduction unit can apply different reproduction methods to each category of work during reproduction. For example, for woodworking work, the reproduction unit can apply a reproduction method that takes into account the properties of wood. Similarly, for metalworking work, the reproduction unit can apply a reproduction method that takes into account the properties of metal. Furthermore, for weaving work, the reproduction unit can apply a reproduction method that takes into account the properties of fibers. For example, the reproduction unit can reproduce woodworking work data and apply a reproduction method that takes into account the properties of wood. This allows for the application of different reproduction methods to each category of work. Some or all of the above-described processing in the reproduction unit may be performed using, for example, a generation AI, or without a generation AI. For example, the reproduction unit can input work data into a generation AI and have the generation AI execute a reproduction method appropriate to the category.

[0103] The reproduction unit can estimate the emotions of the craftsman and determine the reproduction priority based on the estimated emotions. For example, if the craftsman is relaxed, the reproduction unit will prioritize reproducing important work procedures. It can also prioritize reproducing simple work procedures if the craftsman is in a hurry. Furthermore, if the craftsman is excited, it can prioritize reproducing visually stimulating work procedures. For example, the reproduction unit can capture the craftsman's facial expressions with a camera, estimate their emotions using an emotion estimation algorithm, and determine the reproduction priority. This allows the reproduction priority to be determined based on the craftsman's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the reproduction unit may be performed using, for example, a generative AI, or not. For example, the reproduction unit can input the craftsman's facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0104] The reproduction unit can weight the reproduced data based on the timing of the work performed during the reproduction process. For example, the reproduction unit can give a higher weight to the most recent work data. Conversely, the reproduction unit can also give a lower weight to past work data. Furthermore, the reproduction unit can adjust the weighting of the reproduced data according to the timing of the work performed. For example, the reproduction unit can evaluate the timing of the work and give a higher weight to the most recent work data. This allows the reproduction data to be weighted based on the timing of the work performed. Some or all of the above processing in the reproduction unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the reproduction unit can input work data into a generating AI and have the generating AI execute a method for weighting the reproduced data based on the timing of the work performed.

[0105] The reproduction unit can improve the accuracy of reproduction by referring to relevant literature during the reproduction process. For example, the reproduction unit improves the accuracy of the reproduced data based on relevant literature. The reproduction unit can also extract effective reproduction methods from the relevant literature. Furthermore, the reproduction unit can optimize the reproduction algorithm by referring to relevant literature. For example, the reproduction unit improves the accuracy of reproduction by referring to relevant literature for the work. This allows the reproduction unit to improve the accuracy of reproduction by referring to relevant literature for the work. Some or all of the above processing in the reproduction unit may be performed using, for example, a generative AI, or without a generative AI. For example, the reproduction unit can input relevant literature into a generative AI and have the generative AI execute methods to improve the accuracy of reproduction.

[0106] The matching unit can estimate the emotions of young engineers and adjust the matching method based on the estimated emotions of the young engineers. For example, if a young engineer is nervous, the matching unit can provide a simple and highly visible matching method. Furthermore, if a young engineer is relaxed, the matching unit can provide a matching method that includes more detailed information. Additionally, if a young engineer is in a hurry, the matching unit can provide a quick and concise matching method. For example, the matching unit can capture the young engineer's facial expression with a camera, estimate their emotions using an emotion estimation algorithm, and adjust the matching method. This allows the matching method to be adjusted based on the young engineer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the matching unit may be performed using, for example, a generative AI, or not. For example, the matching unit can input the young engineer's facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0107] The matching unit can optimize the matching algorithm by referring to past matching data during the matching process. For example, the matching unit can select the optimal matching algorithm based on past matching data. The matching unit can also extract effective matching methods from past matching data. Furthermore, the matching unit can analyze past matching data and optimize the matching algorithm. For example, the matching unit can refer to past matching data and select the optimal matching algorithm. This allows the matching algorithm to be optimized by referring to past matching data. Some or all of the above processes in the matching unit may be performed using, for example, a generative AI, or without a generative AI. For example, the matching unit can input past matching data into a generative AI and have the generative AI perform the optimization of the matching algorithm.

[0108] The matching unit can apply different matching methods to each category of technician during the matching process. For example, the matching unit can apply a matching method that takes into account the properties of wood to woodworking technicians. It can also apply a matching method that takes into account the properties of metal to metalworking technicians. Furthermore, it can apply a matching method that takes into account the properties of fibers to textile technicians. For example, the matching unit matches the data of woodworking technicians and applies a matching method that takes into account the properties of wood. This allows different matching methods to be applied to each category of technician. Some or all of the above processing in the matching unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the matching unit can input technician data into a generation AI and have the generation AI execute a matching method according to the category.

[0109] The matching unit can estimate the emotions of young engineers and determine matching priorities based on the estimated emotions. For example, if a young engineer is nervous, the matching unit will prioritize important matches. If a young engineer is relaxed, the matching unit can also prioritize matches containing detailed information. Furthermore, if a young engineer is in a hurry, the matching unit can prioritize quick and concise matches. For example, the matching unit can capture a young engineer's facial expression with a camera, estimate their emotions using an emotion estimation algorithm, and determine matching priorities. This allows the matching priorities to be determined based on the young engineer'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 matching unit may be performed using, for example, generative AI, or without generative AI. For example, the matching unit can input facial expression data of young engineers into a generating AI and have the AI ​​perform emotion estimation.

[0110] The matching unit can weight the matching data based on the timing of the engineers' work during the matching process. For example, the matching unit can give a higher weight to recent engineer data. Conversely, it can also give a lower weight to past engineer data. Furthermore, the matching unit can adjust the weighting of the matching data according to the timing of the engineers' work. For example, the matching unit can evaluate the timing of the engineers' work and give a higher weight to recent engineer data. This allows the matching data to be weighted based on the timing of the engineers' work. Some or all of the above processing in the matching unit may be performed using, for example, a generation AI, or without a generation AI. For example, the matching unit can input engineer data into a generation AI and have the generation AI execute a method for weighting the matching data based on the timing of the work.

[0111] The matching unit can improve the accuracy of matching by referring to relevant literature for engineers during the matching process. For example, the matching unit improves the accuracy of matching data based on relevant literature. The matching unit can also extract effective matching methods from relevant literature. Furthermore, the matching unit can optimize the matching algorithm by referring to relevant literature. For example, the matching unit improves the accuracy of matching by referring to relevant literature for engineers. This allows the matching accuracy to be improved by referring to relevant literature for engineers. Some or all of the above processing in the matching unit may be performed using, for example, a generative AI, or without a generative AI. For example, the matching unit can input relevant literature into a generative AI and have the generative AI execute methods to improve the accuracy of matching.

[0112] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0113] The expert AI system can also be equipped with a feedback unit. The feedback unit can collect data from when the junior technician actually performs a task and provide individualized feedback based on the results of the analysis performed by the analysis unit. For example, if a junior technician performs woodworking, the feedback unit will collect a video of the task and the analysis unit will analyze the hand movements and tool usage. Based on the results, the feedback unit can provide the junior technician with specific areas for improvement and advice. The feedback unit can also track the junior technician's progress and provide regular feedback. Furthermore, the feedback unit can estimate the junior technician's emotions and adjust the content and timing of the feedback based on the estimated emotions. For example, if the junior technician is feeling down, the feedback unit can provide encouraging words to boost their motivation.

[0114] The expert AI system can also be equipped with an evaluation unit. This unit can assess the skill level of junior technicians and customize training programs based on the results. For example, if a junior technician performs a metalworking task, the evaluation unit can analyze a video of the task and evaluate the accuracy and efficiency of the technique. Based on these results, the evaluation unit can propose an appropriate training program for the junior technician. Furthermore, the evaluation unit can estimate the junior technician's emotions and adjust the evaluation feedback based on these estimates. For example, if a junior technician is feeling stressed, the evaluation feedback can be delivered gently to reduce stress. Additionally, the evaluation unit can track the junior technician's growth and support skill improvement through regular evaluations.

[0115] The expert AI system can also be equipped with a communication unit. This unit can support communication between junior engineers and expert craftsmen, facilitating smooth information sharing. For example, if a junior engineer asks a question, the communication unit can relay the question to the expert craftsman, ensuring an appropriate answer is obtained. Furthermore, the communication unit can estimate the junior engineer's emotions and adjust its communication style based on those emotions. For instance, if the junior engineer is nervous, the communication unit can choose words to help them relax, facilitating a smoother conversation. Additionally, the communication unit can record information shared between junior engineers and expert craftsmen for later reference.

[0116] The expert AI system can also be equipped with a motivation function. This function provides features to maintain and improve the motivation of junior engineers. For example, when a junior engineer acquires a specific skill, the motivation function can display a message celebrating that achievement. Furthermore, the motivation function can estimate the junior engineer's emotions and suggest actions to boost their motivation based on those estimates. For instance, if a junior engineer is feeling discouraged, the motivation function can help restore their motivation by presenting encouraging messages and success stories. Additionally, the motivation function can track the junior engineer's progress and provide support towards achieving their goals.

[0117] The expert AI system can also be equipped with a collaboration section. This section supports collaborative work among junior engineers and between junior engineers and experienced craftsmen. For example, when junior engineers work on a project as a team, the collaboration section can assist with task allocation and progress sharing. Furthermore, the collaboration section can estimate the emotions of junior engineers and adjust the collaboration method based on these estimations. For instance, if a junior engineer is feeling stressed, the collaboration section can suggest task redistribution or provide support. Additionally, the collaboration section can record the results of collaborative work for later reference.

[0118] The expert AI system can also be equipped with a data integration unit. This unit centrally manages the work data of skilled craftsmen and the learning data of junior technicians, facilitating their use in the analysis and learning units. For example, the data integration unit can integrate work videos and photos of craftsmen and feedback data from junior technicians, streamlining analysis in the analysis unit. It can also integrate data from different data sources and utilize it for learning in the learning unit. Furthermore, the data integration unit can ensure data consistency and quality, improving the overall reliability of the system. For instance, it can maintain data quality by detecting data duplication and missing data and performing appropriate processing.

[0119] The expert AI system can also be equipped with a performance monitoring unit. This unit monitors the work performance of junior engineers in real time and issues alerts as needed. For example, if a junior engineer makes a mistake during work, the performance monitoring unit can detect the mistake and provide immediate feedback. The performance monitoring unit can also monitor the junior engineer's work speed and efficiency and suggest areas for improvement. Furthermore, the performance monitoring unit can accumulate the junior engineer's work data and analyze long-term performance trends. For instance, it can analyze the junior engineer's work data to identify areas for skill improvement and identify areas for improvement.

[0120] The expert AI system can also be equipped with a knowledge base. This knowledge base systematically organizes information about the craftsman's knowledge and skills, making it easily accessible to younger engineers. For example, the knowledge base can database explanations of the craftsman's work procedures and techniques, and provide a search function. It can also store answers to questions from younger engineers and provide them in an FAQ format. Furthermore, the knowledge base can estimate the craftsman's emotions and adjust the way knowledge is delivered based on those emotions. For example, if the craftsman is relaxed, it can provide detailed explanations; if the craftsman is in a hurry, it can provide concise information.

[0121] The expert AI system can also be equipped with a training simulation unit. This unit provides functions for junior engineers to simulate actual work in a virtual environment and acquire skills. For example, the training simulation unit can use VR technology to recreate the work environment of a skilled craftsman, allowing junior engineers to practice their work in a virtual space. Furthermore, the training simulation unit can estimate the emotions of junior engineers and adjust the difficulty and content of the simulation based on these estimates. For example, if a junior engineer is nervous, the difficulty of the simulation can be lowered to help them relax. Additionally, the training simulation unit can analyze the simulation results and provide feedback to the junior engineers.

[0122] The expert AI system can also be equipped with a data visualization unit. This unit visually displays and simplifies the understanding of the work data of skilled craftsmen and the learning data of junior engineers. For example, it can display a craftsman's work procedures using flowcharts and graphs, making them visually understandable to junior engineers. It can also display the learning progress of junior engineers using graphs and dashboards, allowing for a quick overview of their learning achievements. Furthermore, the data visualization unit can estimate the emotions of junior engineers and adjust the data display based on the estimated emotions. For example, it can display detailed data when a junior engineer is relaxed, and concise, to-the-point data when a junior engineer is in a hurry.

[0123] The following briefly describes the processing flow for example form 2.

[0124] Step 1: The recording unit records the craftsman's work and procedures with video and photographs. For example, tasks such as woodworking, metalworking, and cooking are filmed with a high-resolution camera and saved as video data. It is also possible to record as a series of photographs and save detailed procedures as photographic data. Furthermore, it is possible to film from multiple angles and record from a three-dimensional perspective. For example, close-ups of the craftsman's hands can be filmed to record intricate movements in detail. Step 2: The analysis unit analyzes the data recorded by the collection unit. For example, it can use image analysis technology to analyze the hand movements and tool usage of a craftsman, and motion analysis technology to analyze work procedures. Furthermore, it is possible to extract important patterns and features using data mining technology. For example, it can analyze the trajectory of hand movements to evaluate the accuracy of the movements. Step 3: The learning unit learns skills based on the data analyzed by the analysis unit. For example, it can learn work data of craftsmen using machine learning algorithms and learn work procedures and new patterns using supervised or unsupervised learning. For example, it can classify work data and learn the characteristics of each work procedure. Step 4: The answering unit answers questions from junior engineers based on the skills learned by the learning unit. For example, it can analyze questions using natural language processing technology and generate appropriate answers. It can also provide expert answers using FAQ databases and expert systems. For example, it can search for relevant knowledge and generate answers.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] Each of the multiple elements described above, including the data collection unit, analysis unit, learning unit, and response unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the data collection unit records the work of a craftsman using the camera 42 of the smart device 14 and analyzes it using the specific processing unit 290 of the data processing unit 12. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12, and the learning unit is also implemented by the specific processing unit 290 of the data processing unit 12. The response unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates appropriate answers to questions from junior engineers. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0129] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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).

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.).

[0141] 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.

[0142] 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 (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 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.

[0143] 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.

[0144] Each of the multiple elements described above, including the data collection unit, analysis unit, learning unit, and response unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the data collection unit records the work of a craftsman using the camera 42 of the smart glasses 214 and analyzes it using the specific processing unit 290 of the data processing unit 12. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12, and the learning unit is also implemented by the specific processing unit 290 of the data processing unit 12. The response unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates appropriate answers to questions from young engineers. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0145] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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).

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.).

[0157] 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.

[0158] 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 (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 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.

[0159] 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.

[0160] Each of the multiple elements described above, including the data collection unit, analysis unit, learning unit, and response unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the data collection unit records the work of a craftsman using the camera 42 of the headset terminal 314 and analyzes it using the specific processing unit 290 of the data processing unit 12. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12, and the learning unit is also implemented by the specific processing unit 290 of the data processing unit 12. The response unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates appropriate answers to questions from junior engineers. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0161] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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).

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.).

[0174] 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.

[0175] 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 (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 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.

[0176] 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 external devices, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or external devices.

[0177] Each of the multiple elements described above, including the data collection unit, analysis unit, learning unit, and response unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the data collection unit records the work of a craftsman using the camera 42 of the robot 414 and analyzes it using the specific processing unit 290 of the data processing unit 12. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12, and the learning unit is also implemented by the specific processing unit 290 of the data processing unit 12. The response unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates appropriate answers to questions from junior engineers. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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."

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] (Note 1) A collection department that records the work and procedures of craftsmen with video and photographs, An analysis unit analyzes the data recorded by the aforementioned collection unit, A learning unit that learns skills based on the data analyzed by the aforementioned analysis unit, The learning unit provides answers to questions from young engineers based on the skills learned by the learning unit, Equipped with A system characterized by the following features. (Note 2) It features a reproduction unit that uses VR technology to recreate the work of craftsmen. The system described in Appendix 1, characterized by the features described herein. (Note 3) It includes a matching department that builds a successor matching platform. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned collection unit is The system estimates the emotions of the craftsman and adjusts the timing of recording based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned collection unit is Analyze the craftsman's past work history and select the optimal record-keeping method. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned collection unit is During recording, filtering is performed based on the craftsman's current work environment and the tools they use. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is Estimate the emotions of the craftsmen and determine the priority of tasks to record based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is When recording, the system prioritizes recording highly relevant tasks, taking into account the geographical location of the craftsman. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is During recording, analyze the craftsman's social media activity and record the relevant work. The system described in Appendix 1, characterized by the features described herein. (Note 10) 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 11) The aforementioned analysis unit, During analysis, adjust the level of detail based on the importance of the task. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, During analysis, different analysis algorithms are applied depending on the category of work. The system described in Appendix 1, characterized by the features described herein. (Note 13) 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 14) The aforementioned analysis unit, During the analysis, the priority of the analysis is determined based on the timing of the work. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, During analysis, adjust the order of analysis based on the relevance of the tasks. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned learning unit, The system estimates the emotions of the craftsmen and selects training data based on the estimated emotions of the craftsmen. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned learning unit, During training, the learning algorithm is optimized by referring to past training data. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned learning unit, During learning, different learning methods are applied to each category of work. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned learning unit, It estimates the emotions of the craftsmen and adjusts the learning frequency based on the estimated emotions of the craftsmen. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned learning unit, During training, the training data is weighted based on when the tasks were performed. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned learning unit, During learning, refer to relevant literature to improve the accuracy of your learning. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned response section is, The system estimates the emotions of young engineers and adjusts the way responses are expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned response section is, When responding, adjust the level of detail in your answer based on the importance of the question. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned response section is, When answering, different answer algorithms are applied depending on the question category. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned response section is, The system estimates the emotions of young engineers and adjusts the length of the responses based on the estimated emotions of those young engineers. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned response section is, When responding, prioritize your answers based on when the questions were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned response section is, When answering, adjust the order of your answers based on their relevance to the questions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The reproduction unit is, We estimate the emotions of the craftsman and adjust the reproduction method based on the estimated emotions of the craftsman. The system described in Appendix 2, characterized by the features described herein. (Note 29) The reproduction unit is, During reproduction, the reproduction algorithm is optimized by referring to past reproduction data. The system described in Appendix 2, characterized by the features described herein. (Note 30) The reproduction unit is, When reproducing the problem, different reproduction methods are applied to each category of work. The system described in Appendix 2, characterized by the features described herein. (Note 31) The reproduction unit is, The system estimates the emotions of the craftsmen and determines the priority of reproduction based on the estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 32) The reproduction unit is, During the reproduction process, the reproduction data is weighted based on when the work was performed. The system described in Appendix 2, characterized by the features described herein. (Note 33) The reproduction unit is, When reproducing the process, refer to relevant literature to improve the accuracy of the reproduction. The system described in Appendix 2, characterized by the features described herein. (Note 34) The matching unit is The system estimates the emotions of young engineers and adjusts the matching method based on the estimated emotions of those young engineers. The system described in Appendix 3, characterized by the features described herein. (Note 35) The matching unit is During the matching process, the matching algorithm is optimized by referring to past matching data. The system described in Appendix 3, characterized by the features described herein. (Note 36) The matching unit is During the matching process, different matching methods are applied to each category of engineer. The system described in Appendix 3, characterized by the features described herein. (Note 37) The matching unit is The system estimates the emotions of young engineers and determines matching priorities based on these estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 38) The matching unit is During the matching process, the matching data is weighted based on the timing of the engineers' work. The system described in Appendix 3, characterized by the features described herein. (Note 39) The matching unit is During the matching process, we improve the accuracy of the matching by referring to relevant literature for engineers. The system described in Appendix 3, characterized by the features described herein. [Explanation of Symbols]

[0197] 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. A collection department that records the work and procedures of craftsmen with video and photographs, An analysis unit analyzes the data recorded by the aforementioned collection unit, A learning unit that learns skills based on the data analyzed by the aforementioned analysis unit, The learning unit provides answers to questions from young engineers based on the skills learned by the learning unit, Equipped with A system characterized by the following features.

2. It features a reproduction unit that uses VR technology to recreate the work of craftsmen. The system according to feature 1.

3. It includes a matching department that builds a successor matching platform. The system according to feature 1.

4. The aforementioned collection unit is The system estimates the emotions of the craftsman and adjusts the timing of recording based on the estimated emotions. The system according to feature 1.

5. The aforementioned collection unit is Analyze the craftsman's past work history and select the optimal record-keeping method. The system according to feature 1.

6. The aforementioned collection unit is During recording, filtering is performed based on the craftsman's current work environment and the tools they use. The system according to feature 1.

7. The aforementioned collection unit is Estimate the emotions of the craftsmen and determine the priority of tasks to record based on those estimated emotions. The system according to feature 1.

8. The aforementioned collection unit is When recording, the system prioritizes recording highly relevant tasks, taking into account the geographical location of the craftsman. The system according to feature 1.

9. The aforementioned collection unit is During recording, analyze the craftsman's social media activity and record the relevant work. The system according to feature 1.

10. 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 according to feature 1.

Images