System

Abstract

An object of the system according to the embodiment is to efficiently take over skills and procedures of a craftsman and train a successor.SOLUTION: A system includes a collection unit, an analysis unit, a provision unit, and a matching unit. The collection component records the craftsman's work or procedures with video and photographs. The analysis unit analyzes the information recorded by the collection unit. The providing unit provides a training environment based on the information analyzed by the analysis unit. The matching unit matches the successor based on the training environment provided by the providing unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional techniques, there is a lack of successors to take over the skills and procedures of artisans, raising concerns that traditional crafts will decline.

[0005] The system according to the embodiment aims to efficiently transfer the skills and procedures of craftsmen and train successors. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, a provision unit, and a matching unit. The collection unit records the work or procedures of a craftsman using video and photographs. The analysis unit analyzes the information recorded by the collection unit. The provision unit provides a training environment based on the information analyzed by the analysis unit. The matching unit matches a successor based on the training environment provided by the provision unit. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently transfer the skills and procedures of craftsmen and train successors. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A platform according to an embodiment of the present invention is a system that records and analyzes the work and procedures of artisans in detail, provides a training environment, and matches successors. The platform records the work and procedures of artisans using video and photographs, analyzes them using a generation AI, provides a training environment, and matches successors. For example, the platform records the work of artisans using video and photographs, and converts the data into a format that is easy for the generation AI to analyze. Next, the platform uses the generation AI to analyze the work of artisans and provide a detailed description of the work. The input to the generation AI is the work itself, and the generation AI generates a detailed description based on that content. For example, the generation AI receives a prompt such as "Please explain the steps of this work," extracts the work steps, and creates an explanation. Next, the platform provides a training environment based on the explanation created by the generation AI. For example, a successor watches a training video created by the generation AI and actually performs the work. During this process, the generation AI provides real-time feedback to help the successor improve their skills. Finally, the platform matches the training environment with the successor. For example, a successor can input their skill level and interests, and the generation AI can suggest the optimal training program. This allows the platform to solve the problems of artisans lacking skills to take over and the lack of successors, thereby efficiently passing on traditional crafts. This allows the platform to record and analyze artisans' work and procedures in detail, provide a training environment, and match successors, thereby efficiently passing on traditional crafts. For example, by videotaping an artisan's work and taking photos of each step, detailed records can be kept. The generation AI can convert this into a format that is easy to analyze, improving the accuracy of the analysis. By providing a training environment based on the explanations created by the generation AI, successors can efficiently acquire skills. Real-time feedback can be provided to support successors in improving their skills. By matching a training environment with a successor, the optimal training program can be suggested. This allows the platform to solve the problems of artisans lacking skills to take over and the lack of successors, thereby efficiently passing on traditional crafts.

[0029] A platform according to an embodiment includes a collection unit, an analysis unit, a provision unit, and a matching unit. The collection unit records the work or procedures of a craftsman using video and photographs. Examples of the work or procedures of a craftsman include, but are not limited to, woodworking, pottery, and metalworking. For example, the collection unit may film the work of the craftsman with a high-resolution video camera and take photos of each step. The collection unit may also record the craftsman's hand movements and details of the tools used. For example, the collection unit may use motion capture technology to record the hand movements of the craftsman. The collection unit may also record the types of tools used and how often they are used. The analysis unit analyzes the information recorded by the collection unit. The analysis may be performed using, for example, an image analysis algorithm or data mining technology, but is not limited to, examples. For example, the analysis unit may analyze the video and photographs to generate detailed descriptions of each step. The generation AI may generate detailed descriptions using a text generation AI (e.g., LLM). The analysis unit may also use the generation AI to analyze the content of the video and photographs and extract important points of each step. The providing unit provides a training environment based on the information analyzed by the analyzing unit. The training environment may be provided using, for example, a virtual reality (VR) environment or simulation software, but is not limited to these examples. For example, the providing unit provides an environment in which the successor watches a training video created by the generating AI and actually performs the work. The providing unit may also include a feedback unit in which the generating AI provides feedback in real time. For example, the providing unit supports skill improvement by having the generating AI provide feedback in real time as the successor performs the work. The matching unit matches a successor based on the training environment provided by the providing unit. Matching is performed based on, for example, the successor's skill level, interests, geographical conditions, etc., but is not limited to these examples. For example, the matching unit allows the successor to input their skill level and interests, and the generating AI proposes an optimal training program.As a result, the platform according to the embodiment can efficiently pass on traditional crafts by recording and analyzing the work and procedures of artisans in detail, providing a training environment, and matching them with successors.

[0030] The providing unit includes a feedback unit that provides feedback in real time using the generation AI. The feedback unit provides feedback in real time using the generation AI. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. For example, the feedback unit allows the generation AI to provide feedback in real time when the successor performs work. For example, the feedback unit can allow the generation AI to provide voice feedback when the successor performs work. The feedback unit can also allow the generation AI to provide text feedback. For example, the feedback unit allows the generation AI to provide text feedback in real time when the successor performs work. In this way, by providing feedback in real time, it is possible to support the successor's skill improvement.

[0031] The matching unit includes an evaluation unit that evaluates the skill level of the successor. The evaluation unit evaluates the skill level of the successor. The skill level evaluation is performed, for example, based on test results, practical evaluation, etc., but is not limited to these examples. For example, the evaluation unit may have the successor take a practical test and evaluate the skill level based on the results. The evaluation unit may also have the successor take an online test and evaluate the skill level based on the results. For example, the evaluation unit may have the successor take an online skill test and evaluate the skill level based on the results. In this way, by evaluating the skill level of the successor, an optimal training program can be proposed.

[0032] The collection unit records the hand movements of the craftsman or details of the tools used. The collection unit records the hand movements of the craftsman or details of the tools used. Recording of hand movements is performed using, for example, motion capture technology or video analysis, but is not limited to these examples. For example, the collection unit records the hand movements of the craftsman using motion capture technology. The collection unit can also record the hand movements of the craftsman using video analysis. For example, the collection unit captures the hand movements of the craftsman with a high-resolution video camera and records the hand movements using video analysis technology. Recording of details of the tools used is performed based on, for example, the type of tool and frequency of use, but is not limited to these examples. For example, the collection unit records the type of tool used by the craftsman. The collection unit can also record the frequency of tool use by the craftsman. For example, the collection unit records the type of tool used by the craftsman and frequency of use. In this way, by recording the hand movements of the craftsman and details of the tools used, a more accurate training environment can be provided.

[0033] The analysis unit analyzes the video or photos and generates a detailed description of each step. The analysis unit analyzes the video or photos and generates a detailed description of each step. The generation of the detailed description of each step is performed using, for example, natural language generation technology or template-based description, but is not limited to these examples. For example, the analysis unit analyzes the video or photos using a generation AI and generates a detailed description of each step. The generation AI can generate the detailed description using a text generation AI (e.g., LLM). The analysis unit can also generate the detailed description of each step using template-based description. For example, the analysis unit analyzes the content of the video or photos and generates a detailed description of each step based on a template. By generating a detailed description of each step in this way, a training environment that is easy for successors to understand can be provided.

[0034] The providing unit provides an environment in which the successor watches the training video created by the generation AI and actually performs the work. The providing unit provides an environment in which the successor watches the training video created by the generation AI and actually performs the work. The content of the training video is determined based on, for example, the length of the video and the details of the content, but is not limited to such examples. For example, the providing unit provides an environment in which the successor watches the training video created by the generation AI and actually performs the work. The generation AI can create the training video using a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the providing unit provides an environment in which the successor watches the training video created by the generation AI and actually performs the work. This allows the successor to efficiently acquire skills by watching and actually performing the work.

[0035] The collection unit analyzes the craftsman's past work history and selects the optimal recording method. The collection unit analyzes the craftsman's past work history and selects the optimal recording method. Analysis of the past work history is performed using, for example, work logs or video recordings, but is not limited to these examples. For example, the collection unit records similar procedures based on work procedures that the craftsman has previously successfully performed. The collection unit can also select procedures with a higher success rate, avoiding work procedures that the craftsman has previously failed at. For example, the collection unit selects the most efficient recording method from the craftsman's past work history. This improves the accuracy of recording by selecting the optimal recording method based on the past work history. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit can input the craftsman's past work history data into a generation AI and have the generation AI select the optimal recording method.

[0036] The collection unit filters data based on the craftsman's work environment and the materials used when recording. The collection unit filters data based on the craftsman's work environment and the materials used when recording. Filtering of the work environment is performed based on, for example, the temperature, humidity, and lighting conditions of the work area, but is not limited to these examples. For example, the collection unit records by focusing on specific tools used by the craftsman. The collection unit can also adjust the recording method depending on the craftsman's work environment (indoors, outdoors, etc.). For example, the collection unit selects an appropriate recording method based on the characteristics of the materials used. This enables appropriate recording by filtering based on the work environment and the materials used. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the craftsman's work environment data and the material data used into the generation AI and have the generation AI perform the filtering.

[0037] The collection unit selects an appropriate recording means depending on the input method of the craftsman when recording. The collection unit selects an appropriate recording means depending on the input method of the craftsman (audio, text, image, etc.). The selection of the input method is performed based on, for example, audio input, text input, image input, etc., but is not limited to these examples. For example, if the craftsman provides audio explanations, the collection unit prioritizes audio recording. Also, if the craftsman provides text explanations, the collection unit can prioritize text recording. For example, if the craftsman provides images or videos, the collection unit prioritizes visual recording. This enables efficient recording by selecting the optimal recording means depending on the input method. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit may input the craftsman's input data to a generation AI and have the generation AI select the optimal recording means.

[0038] When recording, the collection unit takes into consideration the geographical location information of the craftsman and prioritizes recording highly relevant tasks. When recording, the collection unit takes into consideration the geographical location information of the craftsman and prioritizes recording highly relevant tasks. Consideration of geographical location information is performed, for example, using GPS data or location information services, but is not limited to these examples. For example, the collection unit prioritizes recording tasks performed by the craftsman in a specific area. The collection unit can also record tasks performed by the craftsman while traveling in real time. For example, the collection unit prioritizes recording important tasks performed by the craftsman in a specific location. In this way, by taking geographical location information into consideration, highly relevant tasks can be prioritized and recorded. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit may input the geographical location information data of the craftsman into the generation AI and cause the generation AI to record highly relevant tasks.

[0039] The collection unit analyzes the artisan's social media activity at the time of recording and records related tasks. The collection unit analyzes the artisan's social media activity at the time of recording and records related tasks. Analysis of social media activity is performed, for example, based on the content of posts, the number of followers, the engagement rate, etc., but is not limited to these examples. For example, the collection unit records tasks shared by the artisan on social media. The collection unit can also record related tasks based on the content of the artisan's social media activity. For example, the collection unit records important tasks with reference to the reactions of the artisan's social media followers. In this way, related tasks can be efficiently recorded by analyzing social media activity. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the artisan's social media activity data into a generation AI and cause the generation AI to record related tasks.

[0040] The collection unit customizes the recording method by reflecting the craftsman's past feedback when recording. The collection unit customizes the recording method by reflecting the craftsman's past feedback when recording. Reflecting past feedback is performed, for example, based on survey results, review comments, etc., but is not limited to such examples. For example, the collection unit improves the recording method based on feedback the craftsman received in the past. The collection unit can also select the optimal recording method by referring to the content of the craftsman's past feedback. For example, the collection unit reflects the craftsman's feedback to improve the accuracy of the recording. In this way, the recording method can be optimized by reflecting the past feedback. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the craftsman's past feedback data into the generation AI and cause the generation AI to customize the recording method.

[0041] The analysis unit adjusts the level of detail of the analysis based on the importance of the task during analysis. The analysis unit adjusts the level of detail of the analysis based on the importance of the task during analysis. The evaluation of the importance of the task is performed, for example, based on the impact or urgency of the task, but is not limited to these examples. For example, the analysis unit performs a detailed analysis of important tasks. The analysis unit can also perform a concise analysis of general tasks. For example, the analysis unit performs a quick analysis of highly urgent tasks. This enables efficient analysis by adjusting the level of detail of the analysis based on the importance of the task. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input task importance data to the generation AI and cause the generation AI to adjust the level of detail of the analysis.

[0042] The analysis unit applies different analysis algorithms depending on the category of work during analysis. The analysis unit applies different analysis algorithms depending on the category of work during analysis. Work categories are classified based on, for example, woodworking, metalworking, pottery, etc., but are not limited to these examples. For example, the analysis unit applies an analysis algorithm dedicated to pottery work to pottery work. The analysis unit can also apply an analysis algorithm dedicated to woodworking to woodworking work. For example, the analysis unit applies an analysis algorithm dedicated to dyeing work to dyeing work. In this way, by applying different analysis algorithms depending on the category of work, the accuracy of the analysis is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input work category data to the generation AI and cause the generation AI to apply the analysis algorithm.

[0043] During analysis, the analysis unit improves the accuracy of the analysis by referring to the craftsman's past analysis results. During analysis, the analysis unit improves the accuracy of the analysis by referring to the craftsman's past analysis results. Reference to past analysis results can be made, for example, using a database or analysis report, but is not limited to such examples. For example, the analysis unit improves the analysis algorithm based on the craftsman's past analysis results. The analysis unit can also improve the accuracy of the analysis by referring to the craftsman's past analysis results. For example, the analysis unit adjusts the level of detail of the analysis by reflecting the craftsman's past analysis results. In this way, the accuracy of the analysis is improved by referring to the past analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the craftsman's past analysis result data into the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0044] During analysis, the analysis unit determines the analysis priority based on the time when the work is performed. During analysis, the analysis unit determines the analysis priority based on the time when the work is performed. The time when the work is performed is considered based on, for example, the start date and end date of the work, but is not limited to such examples. For example, the analysis unit prioritizes analysis of work with high urgency. The analysis unit can also prioritize analysis of work that is performed periodically. For example, the analysis unit prioritizes analysis of work that is performed seasonally. This enables efficient analysis by determining the analysis priority based on the time when the work is performed. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input work performance time data into the generation AI and have the generation AI determine the analysis priority.

[0045] The analysis unit adjusts the order of analysis based on the relevance of tasks during analysis. The analysis unit adjusts the order of analysis based on the relevance of tasks during analysis. The evaluation of the relevance of tasks is performed, for example, based on the dependency relationships between tasks or commonalities between tasks, but is not limited to such examples. For example, the analysis unit prioritizes the analysis of highly related tasks. The analysis unit can also postpone less related tasks. For example, the analysis unit optimizes the order of analysis based on the relevance of tasks. This enables efficient analysis by adjusting the order of analysis based on the relevance of tasks. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input task relevance data to a generation AI and cause the generation AI to adjust the order of analysis.

[0046] During analysis, the analysis unit adjusts the use of technical terms in the analysis according to the craftsman's level of expertise. During analysis, the analysis unit adjusts the use of technical terms in the analysis according to the craftsman's level of expertise. The evaluation of the craftsman's level of expertise is based on, for example, the craftsman's years of experience and past performance, but is not limited to such examples. For example, if the craftsman's level of expertise is high, the analysis unit uses a lot of technical terms. Furthermore, if the craftsman's level of expertise is low, the analysis unit can avoid technical terms and use concise expressions. For example, the analysis unit adjusts the use of technical terms in the analysis according to the craftsman's level of expertise. In this way, by adjusting the use of technical terms in the analysis according to the craftsman's level of expertise, it is possible to provide analysis results that are easier to understand. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input the craftsman's level of expertise data into the generation AI and cause the generation AI to adjust the use of technical terms.

[0047] The providing unit adjusts the level of detail provided based on the importance of the task when providing the training environment. The providing unit adjusts the level of detail provided based on the importance of the task when providing the training environment. The evaluation of the importance of the task is performed, for example, based on the impact or urgency of the task, but is not limited to such examples. For example, the providing unit provides a detailed training environment for important tasks. The providing unit can also provide a concise training environment for general tasks. For example, the providing unit provides a quick training environment for urgent tasks. This enables efficient training by adjusting the level of detail provided based on the importance of the task. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit may input task importance data to a generating AI and cause the generating AI to adjust the level of detail provided.

[0048] The providing unit applies different provision algorithms depending on the task category when providing a training environment. The providing unit applies different provision algorithms depending on the task category when providing a training environment. Task categories are classified based on, for example, woodworking, metalworking, pottery, etc., but are not limited to these examples. For example, the providing unit applies a training algorithm dedicated to pottery to pottery work. The providing unit can also apply a training algorithm dedicated to woodworking to woodworking work. For example, the providing unit applies a training algorithm dedicated to dyeing to dyeing work. In this way, by applying different provision algorithms depending on the task category, the accuracy of training is improved. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input task category data into a generation AI and cause the generation AI to apply the provision algorithm.

[0049] When providing a training environment, the providing unit improves the accuracy of the provision by referring to the craftsman's past training results. When providing a training environment, the providing unit improves the accuracy of the provision by referring to the craftsman's past training results. Reference to past training results is performed, for example, using training evaluations and feedback comments, but is not limited to such examples. For example, the providing unit improves the training algorithm based on the craftsman's past training results. The providing unit can also improve the accuracy of the training environment by referring to the craftsman's past training results. For example, the providing unit adjusts the level of detail of the training environment by reflecting the craftsman's past training results. This improves the accuracy of training by referring to the past training results. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the craftsman's past training result data into the generation AI and cause the generation AI to improve the accuracy of the provision.

[0050] The providing unit determines the priority of provision based on the timing of work execution when providing the training environment. The providing unit determines the priority of provision based on the timing of work execution when providing the training environment. The timing of work execution is considered based on, for example, the start date of work and the end date of work, but is not limited to such examples. For example, the providing unit provides in the training environment tasks with high urgency with priority. The providing unit can also provide in the training environment tasks that are performed periodically with priority. For example, the providing unit provides in the training environment tasks with priority on seasonal tasks with priority. This enables efficient training by determining the priority of provision based on the timing of work execution. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit may input data on the timing of work execution into the generating AI and cause the generating AI to determine the priority of provision.

[0051] The providing unit adjusts the order of providing the training environment based on the relevance of the tasks when providing the training environment. The providing unit adjusts the order of providing the training environment based on the relevance of the tasks when providing the training environment. The evaluation of the relevance of the tasks is performed, for example, based on the dependency relationship between the tasks or the commonalities between the tasks, but is not limited to such examples. For example, the providing unit prioritizes providing highly related tasks in the training environment. The providing unit can also provide less related tasks in the training environment later. For example, the providing unit optimizes the order of providing the training environment based on the relevance of the tasks. This enables efficient training by adjusting the order of providing the tasks based on the relevance of the tasks. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit may input task relevance data to a generating AI and cause the generating AI to adjust the order of providing the tasks.

[0052] The provision unit adjusts the use of provided terminology according to the expertise level of the craftsman when providing the training environment. The provision unit adjusts the use of provided terminology according to the expertise level of the craftsman when providing the training environment. The evaluation of the expertise level of the craftsman is performed, for example, based on the craftsman's years of experience and past performance, but is not limited to such examples. For example, if the expertise level of the craftsman is high, the provision unit uses a lot of terminology. Furthermore, if the expertise level of the craftsman is low, the provision unit can avoid terminology and use concise expressions. For example, the provision unit adjusts the use of provided terminology according to the expertise level of the craftsman. In this way, a training environment that is easier to understand can be provided by adjusting the use of provided terminology according to the expertise level of the craftsman. Some or all of the above-mentioned processing by the provision unit may be performed using, for example, AI, or may be performed without using AI. For example, the provision unit may input the expertise level data of the craftsman into the generation AI and cause the generation AI to adjust the use of terminology.

[0053] The matching unit adjusts the level of detail of the matching based on the skill level of the successor during matching. The matching unit adjusts the level of detail of the matching based on the skill level of the successor during matching. The evaluation of the skill level of the successor is performed, for example, based on test results or practical evaluation, but is not limited to these examples. For example, the matching unit provides detailed matching information when the skill level of the successor is high. The matching unit can also provide concise matching information when the skill level of the successor is low. For example, the matching unit adjusts the level of detail of the matching according to the skill level of the successor. This enables more appropriate matching by adjusting the level of detail of the matching based on the skill level of the successor. Some or all of the above-mentioned processing in the matching unit may be performed using, for example, AI, or may be performed without using AI. For example, the matching unit inputs the skill level data of the successor to the generation AI and causes the generation AI to adjust the level of detail of the matching.

[0054] The matching unit applies different matching algorithms depending on the interests of the successor during matching. The matching unit applies different matching algorithms depending on the interests of the successor during matching. The successor's interests are evaluated based on, for example, survey results or social media activity, but are not limited to these examples. For example, if the successor is interested in pottery, the matching unit applies a matching algorithm dedicated to pottery. Also, if the successor is interested in woodworking, the matching unit can apply a matching algorithm dedicated to woodworking. For example, if the successor is interested in dyeing, the matching unit applies a matching algorithm dedicated to dyeing. This enables more appropriate matching by applying different matching algorithms depending on the interests of the successor. Some or all of the above-mentioned processing in the matching unit may be performed using, for example, AI, or may be performed without using AI. For example, the matching unit can input the interests of the successor into the generation AI and cause the generation AI to apply a matching algorithm.

[0055] The matching unit improves the accuracy of matching by referring to the successor's past matching results during matching. The matching unit improves the accuracy of matching by referring to the successor's past matching results during matching. Reference to past matching results can be made, for example, using matching evaluations and feedback comments, but is not limited to these examples. For example, the matching unit improves the matching algorithm based on the successor's past matching results. The matching unit can also improve the accuracy of matching by referring to the successor's past matching results. For example, the matching unit adjusts the level of detail of matching by reflecting the successor's past matching results. By referring to the past matching results, the accuracy of matching is improved. Some or all of the above-mentioned processing in the matching unit may be performed, for example, using AI, or may be performed without using AI. For example, the matching unit can input the successor's past matching result data into the generation AI and cause the generation AI to improve the accuracy of matching.

[0056] During matching, the matching unit prioritizes highly relevant matching by taking into account the geographical location information of the successor. During matching, the matching unit prioritizes highly relevant matching by taking into account the geographical location information of the successor. Consideration of geographical location information is performed, for example, using GPS data or location information services, but is not limited to these examples. For example, if the successor lives in a specific area, the matching unit prioritizes matching with craftsmen in that area. The matching unit can also prioritize matching with craftsmen within a range that the successor can travel. For example, the matching unit performs optimal matching based on the geographical location information of the successor. This enables highly relevant matching by taking geographical location information into account. Some or all of the above-described processing in the matching unit may be performed using, for example, AI, or may be performed without using AI. For example, the matching unit can input the geographical location information data of the successor to the generation AI and cause the generation AI to perform highly relevant matching.

[0057] The matching unit analyzes the social media activity of the successor during matching and performs relevant matching. The matching unit analyzes the social media activity of the successor during matching and performs relevant matching. Analysis of social media activity is performed based on, for example, the content of posts, the number of followers, the engagement rate, etc., but is not limited to these examples. For example, the matching unit matches with relevant craftsmen based on the interests and concerns shared by the successor on social media. The matching unit can also match with the most suitable craftsmen based on the successor's social media activity. For example, the matching unit performs important matching based on the reactions of the successor's followers on social media. In this way, relevant matching can be performed efficiently by analyzing social media activity. Some or all of the above-mentioned processing in the matching unit may be performed using, for example, AI, or may be performed without using AI. For example, the matching unit can input the successor's social media activity data into the generation AI and cause the generation AI to perform relevant matching.

[0058] The matching unit customizes the matching method by reflecting the successor's past feedback during matching. The matching unit customizes the matching method by reflecting the successor's past feedback during matching. Reflecting past feedback is performed, for example, based on survey results, review comments, etc., but is not limited to these examples. For example, the matching unit improves the matching method based on feedback the successor has received in the past. The matching unit can also select the optimal matching method by referring to the successor's past feedback. For example, the matching unit reflects the successor's feedback to improve the accuracy of matching. In this way, the matching method can be optimized by reflecting the past feedback. Some or all of the above-mentioned processing in the matching unit may be performed using, for example, AI, or may be performed without using AI. For example, the matching unit can input the successor's past feedback data into the generation AI and cause the generation AI to customize the matching method.

[0059] The feedback unit adjusts the level of detail of the feedback based on the importance of the task when providing feedback. The feedback unit adjusts the level of detail of the feedback based on the importance of the task when providing feedback. The evaluation of the importance of the task is performed, for example, based on the impact or urgency of the task, but is not limited to these examples. For example, the feedback unit provides detailed feedback for important tasks. The feedback unit can also provide concise feedback for general tasks. For example, the feedback unit provides quick feedback for urgent tasks. This enables efficient feedback by adjusting the level of detail of the feedback based on the importance of the task. Some or all of the above-described processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit may input task importance data to a generation AI and cause the generation AI to adjust the level of detail of the feedback.

[0060] The feedback unit applies different feedback algorithms depending on the task category when providing feedback. The feedback unit applies different feedback algorithms depending on the task category when providing feedback. Task categories can be classified based on, for example, woodworking, metalworking, pottery, etc., but are not limited to these examples. For example, the feedback unit applies a feedback algorithm dedicated to pottery work to pottery work. The feedback unit can also apply a feedback algorithm dedicated to woodworking to woodworking work. For example, the feedback unit applies a feedback algorithm dedicated to dyeing work to dyeing work. In this way, by applying different feedback algorithms depending on the task category, the accuracy of the feedback is improved. Some or all of the above-mentioned processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit can input task category data to the generation AI and cause the generation AI to apply the feedback algorithm.

[0061] The feedback unit improves the accuracy of the feedback by referring to the successor's past feedback results when providing feedback. The feedback unit improves the accuracy of the feedback by referring to the successor's past feedback results when providing feedback. Reference to past feedback results can be made, for example, using feedback ratings or comments, but is not limited to these examples. For example, the feedback unit improves the feedback algorithm based on the successor's past feedback results. The feedback unit can also improve the accuracy of the feedback by referring to the successor's past feedback results. For example, the feedback unit adjusts the level of detail of the feedback by reflecting the successor's past feedback results. In this way, the accuracy of the feedback is improved by referring to the past feedback results. Some or all of the above-described processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit can input the successor's past feedback result data into the generation AI and cause the generation AI to improve the accuracy of the feedback.

[0062] The feedback unit determines the priority of the feedback based on the time when the work is performed at the time of feedback. The feedback unit determines the priority of the feedback based on the time when the work is performed at the time of feedback. The time when the work is performed is considered based on, for example, the start date of the work or the end date of the work, but is not limited to such examples. For example, the feedback unit provides feedback preferentially to work that is highly urgent. The feedback unit can also provide feedback preferentially to work that is performed periodically. For example, the feedback unit provides feedback preferentially to work that is performed seasonally. This enables efficient feedback by determining the priority of the feedback based on the time when the work is performed. Some or all of the above-mentioned processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit can input work performance time data to the generation AI and cause the generation AI to determine the priority of the feedback.

[0063] The feedback unit adjusts the order of feedback based on the relevance of tasks when providing feedback. The feedback unit adjusts the order of feedback based on the relevance of tasks when providing feedback. The evaluation of task relevance is performed, for example, based on task dependency or commonalities, but is not limited to such examples. For example, the feedback unit provides feedback preferentially to highly related tasks. The feedback unit can also provide feedback later to less related tasks. For example, the feedback unit optimizes the order of feedback based on the relevance of tasks. This enables efficient feedback by adjusting the order of feedback based on the relevance of tasks. Some or all of the above-described processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit inputs task relevance data to a generation AI and causes the generation AI to adjust the order of feedback.

[0064] The feedback unit adjusts the use of technical terms in the feedback according to the expertise level of the successor when providing feedback. The feedback unit adjusts the use of technical terms in the feedback according to the expertise level of the successor when providing feedback. The evaluation of the expertise level of the successor is based on, for example, the successor's years of experience and past performance, but is not limited to such examples. For example, if the expertise level of the successor is high, the feedback unit uses a lot of technical terms. Furthermore, if the expertise level of the successor is low, the feedback unit can avoid technical terms and use concise expressions. For example, the feedback unit adjusts the use of technical terms in the feedback according to the expertise level of the successor. In this way, by adjusting the use of technical terms in the feedback according to the expertise level of the successor, more understandable feedback can be provided. Some or all of the above-described processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit may input the expertise level data of the successor to the generation AI and cause the generation AI to adjust the use of technical terms.

[0065] The evaluation unit adjusts the level of detail of the evaluation based on the skill level of the successor during the evaluation. The evaluation unit adjusts the level of detail of the evaluation based on the skill level of the successor during the evaluation. The evaluation of the skill level of the successor is performed, for example, based on test results or practical evaluation, but is not limited to such examples. For example, the evaluation unit performs a detailed evaluation when the skill level of the successor is high. Furthermore, the evaluation unit can perform a brief evaluation when the skill level of the successor is low. For example, the evaluation unit adjusts the level of detail of the evaluation according to the skill level of the successor. This enables a more appropriate evaluation by adjusting the level of detail of the evaluation based on the skill level of the successor. Some or all of the above-described processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit may input the skill level data of the successor to the generation AI and cause the generation AI to adjust the level of detail of the evaluation.

[0066] The evaluation unit applies different evaluation algorithms depending on the successor's interests during evaluation. The evaluation unit applies different evaluation algorithms depending on the successor's interests during evaluation. Evaluation of the successor's interests is performed based on, for example, survey results, social media activity, etc., but is not limited to these examples. For example, if the successor is interested in pottery, the evaluation unit applies an evaluation algorithm dedicated to pottery. Also, if the successor is interested in woodworking, the evaluation unit can apply an evaluation algorithm dedicated to woodworking. For example, if the successor is interested in dyeing, the evaluation unit applies an evaluation algorithm dedicated to dyeing. This allows for more appropriate evaluation by applying different evaluation algorithms depending on the successor's interests. Some or all of the above-mentioned processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit may input the successor's interests data into the generation AI and cause the generation AI to apply the evaluation algorithm.

[0067] The evaluation unit improves the accuracy of the evaluation by referring to the successor's past evaluation results during the evaluation. The evaluation unit improves the accuracy of the evaluation by referring to the successor's past evaluation results during the evaluation. Reference to past evaluation results can be made, for example, using evaluation reports or feedback comments, but is not limited to these examples. For example, the evaluation unit improves the evaluation algorithm based on the successor's past evaluation results. The evaluation unit can also improve the accuracy of the evaluation by referring to the successor's past evaluation results. For example, the evaluation unit adjusts the level of detail of the evaluation by reflecting the successor's past evaluation results. In this way, the accuracy of the evaluation is improved by referring to the past evaluation results. Some or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can input the successor's past evaluation result data into the generation AI and cause the generation AI to improve the accuracy of the evaluation.

[0068] During evaluation, the evaluation unit prioritizes highly relevant evaluations by taking into account the geographical location information of the successor. During evaluation, the evaluation unit prioritizes highly relevant evaluations by taking into account the geographical location information of the successor. Consideration of geographical location information is performed, for example, using GPS data or location information services, but is not limited to such examples. For example, if the successor lives in a specific area, the evaluation unit prioritizes evaluations with craftsmen in that area. The evaluation unit can also prioritize evaluations with craftsmen within the successor's travel range. For example, the evaluation unit performs an optimal evaluation based on the geographical location information of the successor. This enables highly relevant evaluations by taking geographical location information into account. Some or all of the above-described processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit may input the geographical location information data of the successor into the generation AI and cause the generation AI to perform highly relevant evaluations.

[0069] During the evaluation, the evaluation unit analyzes the social media activity of the successor and performs a related evaluation. During the evaluation, the evaluation unit analyzes the social media activity of the successor and performs a related evaluation. The analysis of social media activity is performed, for example, based on the content of posts, the number of followers, the engagement rate, etc., but is not limited to these examples. For example, the evaluation unit evaluates related craftsmen based on the interests and concerns shared by the successor on social media. The evaluation unit can also evaluate the most suitable craftsmen based on the successor's social media activity. For example, the evaluation unit performs important evaluations based on the reactions of the successor's followers on social media. In this way, the related evaluations can be performed efficiently by analyzing social media activity. Some or all of the above-mentioned processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit may input the successor's social media activity data into the generation AI and cause the generation AI to perform the related evaluation.

[0070] The evaluation unit customizes the evaluation method by reflecting the successor's past feedback during evaluation. The evaluation unit customizes the evaluation method by reflecting the successor's past feedback during evaluation. Reflecting past feedback is performed, for example, based on survey results, review comments, etc., but is not limited to these examples. For example, the evaluation unit improves the evaluation method based on feedback the successor has received in the past. The evaluation unit can also select the optimal evaluation method by referring to the successor's past feedback. For example, the evaluation unit reflects the successor's feedback to improve the accuracy of the evaluation. In this way, the evaluation method can be optimized by reflecting past feedback. Some or all of the above-mentioned processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit can input the successor's past feedback data into the generation AI and cause the generation AI to customize the evaluation method.

[0071] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0072] The collection unit can also record audio data of the craftsman's work environment, and the analysis unit can analyze the audio data to recreate the atmosphere and environmental sounds of the work. For example, the sound of a saw made during woodworking or the sound of water heard during pottery making can be recorded, and a successor can listen to those sounds in the training environment to provide a more realistic work experience. The analysis unit can also analyze the audio data to understand the progress of the work, and the provision unit can adjust the content of the training video based on that information. Furthermore, the collection unit can record the craftsman's conversations and instructions while he or she is working, and the analysis unit can analyze the content and provide it to the successor.

[0073] The provision department can also customize the training environment according to the successor's learning style. For example, detailed videos and illustrations can be provided for successors who prefer visual learning, while audio guides and explanations can be enhanced for successors who prefer auditory learning. In addition, interactive simulations and practical practice opportunities can be increased for successors who prefer practical learning. This makes it possible to provide the optimal training environment according to the successor's learning style.

[0074] The analysis unit can also analyze the work data of craftsmen and suggest ways to improve work efficiency and improve areas. For example, it can detect unnecessary movements during work and suggest efficient work procedures. It can also suggest optimizing the tools and materials used, improving work quality. Furthermore, the analysis unit can compare the data of other craftsmen to extract best practices and provide them to successors. In this way, the work data of craftsmen can be used to improve work efficiency and quality.

[0075] The collection unit records environmental data (temperature, humidity, illuminance, etc.) while the craftsman is working, and the analysis unit analyzes the data to suggest the optimal work environment. For example, working at the appropriate temperature and humidity can maintain the quality of materials. Adjusting the illuminance can also improve the accuracy of work. Furthermore, the collection unit can adjust the recording method according to changes in the work environment and collect more accurate data. This makes it possible to optimize the craftsman's work environment and improve the quality of work.

[0076] The analysis unit can also analyze the work data of craftsmen, identify risk factors in the work, and propose safety measures. For example, it can identify the risk of accidents and injuries that may occur during work and propose safe work procedures. It can also evaluate the safety of tools and materials used and propose appropriate ways to use them. Furthermore, the analysis unit can compare the data of other craftsmen to extract best practices for safety measures and provide them to successors. In this way, a safe working environment can be achieved by utilizing the work data of craftsmen.

[0077] The collection unit records gaze data of craftsmen while they work, and the analysis unit analyzes the data to identify the key points of the work. For example, it can analyze where the craftsman focuses during a specific work step and emphasize those points to teach the successor. It can also make suggestions to improve work efficiency based on the gaze data. Furthermore, the collection unit can analyze the gaze data in real time and guide the successor so that they can focus on the same points. In this way, it is possible to utilize the gaze data of craftsmen to provide a more effective training environment.

[0078] The processing flow of the first embodiment will be briefly explained below.

[0079] Step 1: The collection department records the artisan's work or steps with video and photographs. The artisan's work may include woodworking, pottery, metalworking, etc. The collection department uses high-resolution video cameras to film and photograph each step. They can also record the artisan's hand movements and details of the tools they use. For example, they could use motion capture technology to record hand movements, as well as the type of tools they use and how often they use them. Step 2: The analysis unit analyzes the information recorded by the collection unit. This analysis is performed using image analysis algorithms and data mining techniques. For example, it analyzes videos and photos to generate detailed descriptions of each step. Generative AI is used to generate detailed descriptions and analyze the content of videos and photos to extract key points of each step. Step 3: The provision unit provides a training environment based on the information analyzed by the analysis unit. The training environment is provided using a virtual reality (VR) environment or simulation software. For example, an environment is provided in which the successor watches a training video created by the generative AI and actually performs the work. The provision unit may also be equipped with a feedback unit that provides feedback in real time. Step 4: The matching unit matches a successor based on the training environment provided by the provision unit. Matching is based on the successor's skill level, interests, geographical location, etc. For example, the successor inputs their skill level and interests, and the generation AI suggests the optimal training program.

[0080] (Example 2) A platform according to an embodiment of the present invention is a system that records and analyzes the work and procedures of artisans in detail, provides a training environment, and matches successors. The platform records the work and procedures of artisans using video and photographs, analyzes them using a generation AI, provides a training environment, and matches successors. For example, the platform records the work of artisans using video and photographs, and converts the data into a format that is easy for the generation AI to analyze. Next, the platform uses the generation AI to analyze the work of artisans and provide a detailed description of the work. The input to the generation AI is the work itself, and the generation AI generates a detailed description based on that content. For example, the generation AI receives a prompt such as "Please explain the steps of this work," extracts the work steps, and creates an explanation. Next, the platform provides a training environment based on the explanation created by the generation AI. For example, a successor watches a training video created by the generation AI and actually performs the work. During this process, the generation AI provides real-time feedback to help the successor improve their skills. Finally, the platform matches the training environment with the successor. For example, a successor can input their skill level and interests, and the generation AI can suggest the optimal training program. This allows the platform to solve the problems of artisans lacking skills to take over and the lack of successors, thereby efficiently passing on traditional crafts. This allows the platform to record and analyze artisans' work and procedures in detail, provide a training environment, and match successors, thereby efficiently passing on traditional crafts. For example, by videotaping an artisan's work and taking photos of each step, detailed records can be kept. The generation AI can convert this into a format that is easy to analyze, improving the accuracy of the analysis. By providing a training environment based on the explanations created by the generation AI, successors can efficiently acquire skills. Real-time feedback can be provided to support successors in improving their skills. By matching a training environment with a successor, the optimal training program can be suggested. This allows the platform to solve the problems of artisans lacking skills to take over and the lack of successors, thereby efficiently passing on traditional crafts.

[0081] A platform according to an embodiment includes a collection unit, an analysis unit, a provision unit, and a matching unit. The collection unit records the work or procedures of a craftsman using video and photographs. Examples of the work or procedures of a craftsman include, but are not limited to, woodworking, pottery, and metalworking. For example, the collection unit may film the work of the craftsman with a high-resolution video camera and take photos of each step. The collection unit may also record the craftsman's hand movements and details of the tools used. For example, the collection unit may use motion capture technology to record the hand movements of the craftsman. The collection unit may also record the types of tools used and how often they are used. The analysis unit analyzes the information recorded by the collection unit. The analysis may be performed using, for example, an image analysis algorithm or data mining technology, but is not limited to, examples. For example, the analysis unit may analyze the video and photographs to generate detailed descriptions of each step. The generation AI may generate detailed descriptions using a text generation AI (e.g., LLM). The analysis unit may also use the generation AI to analyze the content of the video and photographs and extract important points of each step. The providing unit provides a training environment based on the information analyzed by the analyzing unit. The training environment may be provided using, for example, a virtual reality (VR) environment or simulation software, but is not limited to these examples. For example, the providing unit provides an environment in which the successor watches a training video created by the generating AI and actually performs the work. The providing unit may also include a feedback unit in which the generating AI provides feedback in real time. For example, the providing unit supports skill improvement by having the generating AI provide feedback in real time as the successor performs the work. The matching unit matches a successor based on the training environment provided by the providing unit. Matching is performed based on, for example, the successor's skill level, interests, geographical conditions, etc., but is not limited to these examples. For example, the matching unit allows the successor to input their skill level and interests, and the generating AI proposes an optimal training program.As a result, the platform according to the embodiment can efficiently pass on traditional crafts by recording and analyzing the work and procedures of artisans in detail, providing a training environment, and matching them with successors.

[0082] The providing unit includes a feedback unit that provides feedback in real time using the generation AI. The feedback unit provides feedback in real time using the generation AI. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. For example, the feedback unit allows the generation AI to provide feedback in real time when the successor performs work. For example, the feedback unit can allow the generation AI to provide voice feedback when the successor performs work. The feedback unit can also allow the generation AI to provide text feedback. For example, the feedback unit allows the generation AI to provide text feedback in real time when the successor performs work. In this way, by providing feedback in real time, it is possible to support the successor's skill improvement.

[0083] The matching unit includes an evaluation unit that evaluates the skill level of the successor. The evaluation unit evaluates the skill level of the successor. The skill level evaluation is performed, for example, based on test results, practical evaluation, etc., but is not limited to these examples. For example, the evaluation unit may have the successor take a practical test and evaluate the skill level based on the results. The evaluation unit may also have the successor take an online test and evaluate the skill level based on the results. For example, the evaluation unit may have the successor take an online skill test and evaluate the skill level based on the results. In this way, by evaluating the skill level of the successor, an optimal training program can be proposed.

[0084] The collection unit records the hand movements of the craftsman or details of the tools used. The collection unit records the hand movements of the craftsman or details of the tools used. Recording of hand movements is performed using, for example, motion capture technology or video analysis, but is not limited to these examples. For example, the collection unit records the hand movements of the craftsman using motion capture technology. The collection unit can also record the hand movements of the craftsman using video analysis. For example, the collection unit captures the hand movements of the craftsman with a high-resolution video camera and records the hand movements using video analysis technology. Recording of details of the tools used is performed based on, for example, the type of tool and frequency of use, but is not limited to these examples. For example, the collection unit records the type of tool used by the craftsman. The collection unit can also record the frequency of tool use by the craftsman. For example, the collection unit records the type of tool used by the craftsman and frequency of use. In this way, by recording the hand movements of the craftsman and details of the tools used, a more accurate training environment can be provided.

[0085] The analysis unit analyzes the video or photos and generates a detailed description of each step. The analysis unit analyzes the video or photos and generates a detailed description of each step. The generation of the detailed description of each step is performed using, for example, natural language generation technology or template-based description, but is not limited to these examples. For example, the analysis unit analyzes the video or photos using a generation AI and generates a detailed description of each step. The generation AI can generate the detailed description using a text generation AI (e.g., LLM). The analysis unit can also generate the detailed description of each step using template-based description. For example, the analysis unit analyzes the content of the video or photos and generates a detailed description of each step based on a template. By generating a detailed description of each step in this way, a training environment that is easy for successors to understand can be provided.

[0086] The providing unit provides an environment in which the successor watches the training video created by the generation AI and actually performs the work. The providing unit provides an environment in which the successor watches the training video created by the generation AI and actually performs the work. The content of the training video is determined based on, for example, the length of the video and the details of the content, but is not limited to such examples. For example, the providing unit provides an environment in which the successor watches the training video created by the generation AI and actually performs the work. The generation AI can create the training video using a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the providing unit provides an environment in which the successor watches the training video created by the generation AI and actually performs the work. This allows the successor to efficiently acquire skills by watching and actually performing the work.

[0087] The collection unit estimates the craftsman's emotions and adjusts the timing of recording based on the estimated emotions. The collection unit estimates the craftsman's emotions and adjusts the timing of recording based on the estimated emotions. The estimation of the craftsman's emotions is performed using, for example, facial expression analysis or voice analysis, but is not limited to these examples. For example, the collection unit estimates the craftsman's emotions using facial expression analysis technology. The collection unit can also estimate the craftsman's emotions using voice analysis technology. For example, the collection unit captures the craftsman's facial expressions with a camera and estimates the emotions using facial expression analysis technology. By adjusting the timing of recording based on the estimated emotions of the craftsman, a more natural work flow can be recorded. For example, when the craftsman is concentrating, the frequency of recording can be increased to collect detailed data. When the craftsman is tired, the frequency of recording can be reduced and breaks can be inserted. When the craftsman is relaxed, the recording can be focused on the natural work flow. In this way, by adjusting the timing of recording according to the craftsman's emotions, a more natural work flow can be recorded. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit may be performed using AI, or may be performed without using AI. For example, the collection unit may input image data of a craftsman taken with a camera into the generation AI and cause the generation AI to estimate the craftsman's emotions.

[0088] The collection unit analyzes the craftsman's past work history and selects the optimal recording method. The collection unit analyzes the craftsman's past work history and selects the optimal recording method. Analysis of the past work history is performed using, for example, work logs or video recordings, but is not limited to these examples. For example, the collection unit records similar procedures based on work procedures that the craftsman has previously successfully performed. The collection unit can also select procedures with a higher success rate, avoiding work procedures that the craftsman has previously failed at. For example, the collection unit selects the most efficient recording method from the craftsman's past work history. This improves the accuracy of recording by selecting the optimal recording method based on the past work history. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit can input the craftsman's past work history data into a generation AI and have the generation AI select the optimal recording method.

[0089] The collection unit filters data based on the craftsman's work environment and the materials used when recording. The collection unit filters data based on the craftsman's work environment and the materials used when recording. Filtering of the work environment is performed based on, for example, the temperature, humidity, and lighting conditions of the work area, but is not limited to these examples. For example, the collection unit records by focusing on specific tools used by the craftsman. The collection unit can also adjust the recording method depending on the craftsman's work environment (indoors, outdoors, etc.). For example, the collection unit selects an appropriate recording method based on the characteristics of the materials used. This enables appropriate recording by filtering based on the work environment and the materials used. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the craftsman's work environment data and the material data used into the generation AI and have the generation AI perform the filtering.

[0090] The collection unit selects an appropriate recording means depending on the input method of the craftsman when recording. The collection unit selects an appropriate recording means depending on the input method of the craftsman (audio, text, image, etc.). The selection of the input method is performed based on, for example, audio input, text input, image input, etc., but is not limited to these examples. For example, if the craftsman provides audio explanations, the collection unit prioritizes audio recording. Also, if the craftsman provides text explanations, the collection unit can prioritize text recording. For example, if the craftsman provides images or videos, the collection unit prioritizes visual recording. This enables efficient recording by selecting the optimal recording means depending on the input method. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit may input the craftsman's input data to a generation AI and have the generation AI select the optimal recording means.

[0091] The collection unit estimates the emotions of the craftsman and determines the priority of tasks to be recorded based on the estimated emotions of the craftsman. The collection unit estimates the emotions of the craftsman and determines the priority of tasks to be recorded based on the estimated emotions of the craftsman. The estimation of the emotions of the craftsman is performed using, for example, facial expression analysis or voice analysis, but is not limited to these examples. For example, the collection unit estimates the emotions of the craftsman using facial expression analysis technology. The collection unit can also estimate the emotions of the craftsman using voice analysis technology. For example, the collection unit captures the facial expressions of the craftsman with a camera and estimates the emotions using facial expression analysis technology. By determining the priority of tasks to be recorded based on the estimated emotions of the craftsman, important tasks can be recorded preferentially. For example, if the craftsman is concentrating, important tasks can be recorded preferentially. Also, if the craftsman is tired, easy tasks can be recorded preferentially. Also, if the craftsman is relaxed, recording can be performed with an emphasis on the natural flow of work. In this way, by determining the priority of tasks according to the emotions of the craftsman, important tasks can be recorded preferentially. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit may be performed using AI, or may be performed without using AI. For example, the collection unit may input image data of a craftsman taken with a camera into the generation AI and cause the generation AI to estimate the craftsman's emotions.

[0092] When recording, the collection unit takes into consideration the geographical location information of the craftsman and prioritizes recording highly relevant tasks. When recording, the collection unit takes into consideration the geographical location information of the craftsman and prioritizes recording highly relevant tasks. Consideration of geographical location information is performed, for example, using GPS data or location information services, but is not limited to these examples. For example, the collection unit prioritizes recording tasks performed by the craftsman in a specific area. The collection unit can also record tasks performed by the craftsman while traveling in real time. For example, the collection unit prioritizes recording important tasks performed by the craftsman in a specific location. In this way, by taking geographical location information into consideration, highly relevant tasks can be prioritized and recorded. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit may input the geographical location information data of the craftsman into the generation AI and cause the generation AI to record highly relevant tasks.

[0093] The collection unit analyzes the artisan's social media activity at the time of recording and records related tasks. The collection unit analyzes the artisan's social media activity at the time of recording and records related tasks. Analysis of social media activity is performed, for example, based on the content of posts, the number of followers, the engagement rate, etc., but is not limited to these examples. For example, the collection unit records tasks shared by the artisan on social media. The collection unit can also record related tasks based on the content of the artisan's social media activity. For example, the collection unit records important tasks with reference to the reactions of the artisan's social media followers. In this way, related tasks can be efficiently recorded by analyzing social media activity. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the artisan's social media activity data into a generation AI and cause the generation AI to record related tasks.

[0094] The collection unit customizes the recording method by reflecting the craftsman's past feedback when recording. The collection unit customizes the recording method by reflecting the craftsman's past feedback when recording. Reflecting past feedback is performed, for example, based on survey results, review comments, etc., but is not limited to such examples. For example, the collection unit improves the recording method based on feedback the craftsman received in the past. The collection unit can also select the optimal recording method by referring to the content of the craftsman's past feedback. For example, the collection unit reflects the craftsman's feedback to improve the accuracy of the recording. In this way, the recording method can be optimized by reflecting the past feedback. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the craftsman's past feedback data into the generation AI and cause the generation AI to customize the recording method.

[0095] The analysis unit estimates the craftsman's emotions and adjusts the analysis presentation method based on the estimated emotions. The analysis unit estimates the craftsman's emotions and adjusts the analysis presentation method based on the estimated emotions. The estimation of the craftsman's emotions is performed using, for example, facial expression analysis or voice analysis, but is not limited to these examples. For example, the analysis unit estimates the craftsman's emotions using facial expression analysis technology. The analysis unit can also estimate the craftsman's emotions using voice analysis technology. For example, the analysis unit captures the craftsman's facial expressions with a camera and estimates the emotions using facial expression analysis technology. By adjusting the analysis presentation method based on the estimated emotions of the craftsman, more appropriate analysis results can be provided. For example, if the craftsman is relaxed, a detailed analysis result can be provided. If the craftsman is in a hurry, a concise analysis result can be provided. If the craftsman is excited, a visually stimulating analysis result can be provided. Thus, by adjusting the analysis presentation method according to the craftsman's emotions, more appropriate analysis results can be provided. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit may input image data of a craftsman taken with a camera into the generation AI and cause the generation AI to estimate the craftsman's emotions.

[0096] The analysis unit adjusts the level of detail of the analysis based on the importance of the task during analysis. The analysis unit adjusts the level of detail of the analysis based on the importance of the task during analysis. The evaluation of the importance of the task is performed, for example, based on the impact or urgency of the task, but is not limited to these examples. For example, the analysis unit performs a detailed analysis of important tasks. The analysis unit can also perform a concise analysis of general tasks. For example, the analysis unit performs a quick analysis of highly urgent tasks. This enables efficient analysis by adjusting the level of detail of the analysis based on the importance of the task. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input task importance data to the generation AI and cause the generation AI to adjust the level of detail of the analysis.

[0097] The analysis unit applies different analysis algorithms depending on the category of work during analysis. The analysis unit applies different analysis algorithms depending on the category of work during analysis. Work categories are classified based on, for example, woodworking, metalworking, pottery, etc., but are not limited to these examples. For example, the analysis unit applies an analysis algorithm dedicated to pottery work to pottery work. The analysis unit can also apply an analysis algorithm dedicated to woodworking to woodworking work. For example, the analysis unit applies an analysis algorithm dedicated to dyeing work to dyeing work. In this way, by applying different analysis algorithms depending on the category of work, the accuracy of the analysis is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input work category data to the generation AI and cause the generation AI to apply the analysis algorithm.

[0098] During analysis, the analysis unit improves the accuracy of the analysis by referring to the craftsman's past analysis results. During analysis, the analysis unit improves the accuracy of the analysis by referring to the craftsman's past analysis results. Reference to past analysis results can be made, for example, using a database or analysis report, but is not limited to such examples. For example, the analysis unit improves the analysis algorithm based on the craftsman's past analysis results. The analysis unit can also improve the accuracy of the analysis by referring to the craftsman's past analysis results. For example, the analysis unit adjusts the level of detail of the analysis by reflecting the craftsman's past analysis results. In this way, the accuracy of the analysis is improved by referring to the past analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the craftsman's past analysis result data into the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0099] The analysis unit estimates the craftsman's emotions and adjusts the length of the analysis based on the estimated emotions. The analysis unit estimates the craftsman's emotions and adjusts the length of the analysis based on the estimated emotions. The estimation of the craftsman's emotions is performed using, for example, facial expression analysis or voice analysis, but is not limited to these examples. For example, the analysis unit estimates the craftsman's emotions using facial expression analysis technology. The analysis unit can also estimate the craftsman's emotions using voice analysis technology. For example, the analysis unit captures the craftsman's facial expressions with a camera and estimates the emotions using facial expression analysis technology. By adjusting the length of the analysis based on the estimated emotions of the craftsman, more appropriate analysis results can be provided. For example, if the craftsman is in a hurry, a short and concise analysis can be performed. On the other hand, if the craftsman is relaxed, a detailed analysis can be performed. On the other hand, if the craftsman is excited, a visually stimulating analysis can be performed. In this way, by adjusting the length of the analysis according to the craftsman's emotions, more appropriate analysis results can be provided. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit may input image data of a craftsman taken with a camera into the generation AI and cause the generation AI to estimate the craftsman's emotions.

[0100] During analysis, the analysis unit determines the analysis priority based on the time when the work is performed. During analysis, the analysis unit determines the analysis priority based on the time when the work is performed. The time when the work is performed is considered based on, for example, the start date and end date of the work, but is not limited to such examples. For example, the analysis unit prioritizes analysis of work with high urgency. The analysis unit can also prioritize analysis of work that is performed periodically. For example, the analysis unit prioritizes analysis of work that is performed seasonally. This enables efficient analysis by determining the analysis priority based on the time when the work is performed. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input work performance time data into the generation AI and have the generation AI determine the analysis priority.

[0101] The analysis unit adjusts the order of analysis based on the relevance of tasks during analysis. The analysis unit adjusts the order of analysis based on the relevance of tasks during analysis. The evaluation of the relevance of tasks is performed, for example, based on the dependency relationships between tasks or commonalities between tasks, but is not limited to such examples. For example, the analysis unit prioritizes the analysis of highly related tasks. The analysis unit can also postpone less related tasks. For example, the analysis unit optimizes the order of analysis based on the relevance of tasks. This enables efficient analysis by adjusting the order of analysis based on the relevance of tasks. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input task relevance data to a generation AI and cause the generation AI to adjust the order of analysis.

[0102] During analysis, the analysis unit adjusts the use of technical terms in the analysis according to the craftsman's level of expertise. During analysis, the analysis unit adjusts the use of technical terms in the analysis according to the craftsman's level of expertise. The evaluation of the craftsman's level of expertise is based on, for example, the craftsman's years of experience and past performance, but is not limited to such examples. For example, if the craftsman's level of expertise is high, the analysis unit uses a lot of technical terms. Furthermore, if the craftsman's level of expertise is low, the analysis unit can avoid technical terms and use concise expressions. For example, the analysis unit adjusts the use of technical terms in the analysis according to the craftsman's level of expertise. In this way, by adjusting the use of technical terms in the analysis according to the craftsman's level of expertise, it is possible to provide analysis results that are easier to understand. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input the craftsman's level of expertise data into the generation AI and cause the generation AI to adjust the use of technical terms.

[0103] The providing unit estimates the emotions of the craftsman and adjusts the method of providing the training environment based on the estimated emotions of the craftsman. The providing unit estimates the emotions of the craftsman and adjusts the method of providing the training environment based on the estimated emotions of the craftsman. The estimation of the emotions of the craftsman is performed using, for example, facial expression analysis or voice analysis, but is not limited to these examples. For example, the providing unit estimates the emotions of the craftsman using facial expression analysis technology. The providing unit can also estimate the emotions of the craftsman using voice analysis technology. For example, the providing unit captures the facial expressions of the craftsman with a camera and estimates the emotions using facial expression analysis technology. By adjusting the method of providing the training environment based on the estimated emotions of the craftsman, more effective training is possible. For example, if the craftsman is relaxed, the training environment can be provided at a leisurely pace. On the other hand, if the craftsman is in a hurry, the training environment can be provided quickly. On the other hand, if the craftsman is excited, a visually stimulating training environment can be provided. Thus, by adjusting the method of providing the training environment according to the emotions of the craftsman, more effective training is possible. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the providing unit may be performed using AI, for example, or may be performed without using AI. For example, the providing unit may input image data of a craftsman taken with a camera into the generation AI and cause the generation AI to estimate the craftsman's emotions.

[0104] The providing unit adjusts the level of detail provided based on the importance of the task when providing the training environment. The providing unit adjusts the level of detail provided based on the importance of the task when providing the training environment. The evaluation of the importance of the task is performed, for example, based on the impact or urgency of the task, but is not limited to such examples. For example, the providing unit provides a detailed training environment for important tasks. The providing unit can also provide a concise training environment for general tasks. For example, the providing unit provides a quick training environment for urgent tasks. This enables efficient training by adjusting the level of detail provided based on the importance of the task. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit may input task importance data to a generating AI and cause the generating AI to adjust the level of detail provided.

[0105] The providing unit applies different provision algorithms depending on the task category when providing a training environment. The providing unit applies different provision algorithms depending on the task category when providing a training environment. Task categories are classified based on, for example, woodworking, metalworking, pottery, etc., but are not limited to these examples. For example, the providing unit applies a training algorithm dedicated to pottery to pottery work. The providing unit can also apply a training algorithm dedicated to woodworking to woodworking work. For example, the providing unit applies a training algorithm dedicated to dyeing to dyeing work. In this way, by applying different provision algorithms depending on the task category, the accuracy of training is improved. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input task category data into a generation AI and cause the generation AI to apply the provision algorithm.

[0106] When providing a training environment, the providing unit improves the accuracy of the provision by referring to the craftsman's past training results. When providing a training environment, the providing unit improves the accuracy of the provision by referring to the craftsman's past training results. Reference to past training results is performed, for example, using training evaluations and feedback comments, but is not limited to such examples. For example, the providing unit improves the training algorithm based on the craftsman's past training results. The providing unit can also improve the accuracy of the training environment by referring to the craftsman's past training results. For example, the providing unit adjusts the level of detail of the training environment by reflecting the craftsman's past training results. This improves the accuracy of training by referring to the past training results. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the craftsman's past training result data into the generation AI and cause the generation AI to improve the accuracy of the provision.

[0107] The providing unit estimates the craftsman's emotions and adjusts the length of the training environment based on the estimated emotions. The providing unit estimates the craftsman's emotions and adjusts the length of the training environment based on the estimated emotions. The estimation of the craftsman's emotions is performed using, for example, facial expression analysis or voice analysis, but is not limited to these examples. For example, the providing unit estimates the craftsman's emotions using facial expression analysis technology. The providing unit can also estimate the craftsman's emotions using voice analysis technology. For example, the providing unit captures the craftsman's facial expressions with a camera and estimates the emotions using facial expression analysis technology. Adjusting the length of the training environment based on the estimated emotions of the craftsman enables more appropriate training. For example, if the craftsman is in a hurry, a short and concise training environment can be provided. On the other hand, if the craftsman is relaxed, a longer training environment with detailed explanations can be provided. On the other hand, if the craftsman is excited, a visually stimulating training environment can be provided. Thus, adjusting the length of the training environment according to the craftsman's emotions enables more appropriate training. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the providing unit may be performed using AI, for example, or may be performed without using AI. For example, the providing unit may input image data of a craftsman taken with a camera into the generation AI and cause the generation AI to estimate the craftsman's emotions.

[0108] The providing unit determines the priority of provision based on the timing of work execution when providing the training environment. The providing unit determines the priority of provision based on the timing of work execution when providing the training environment. The timing of work execution is considered based on, for example, the start date of work and the end date of work, but is not limited to such examples. For example, the providing unit provides in the training environment tasks with high urgency with priority. The providing unit can also provide in the training environment tasks that are performed periodically with priority. For example, the providing unit provides in the training environment tasks with priority on seasonal tasks with priority. This enables efficient training by determining the priority of provision based on the timing of work execution. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit may input data on the timing of work execution into the generating AI and cause the generating AI to determine the priority of provision.

[0109] The providing unit adjusts the order of providing the training environment based on the relevance of the tasks when providing the training environment. The providing unit adjusts the order of providing the training environment based on the relevance of the tasks when providing the training environment. The evaluation of the relevance of the tasks is performed, for example, based on the dependency relationship between the tasks or the commonalities between the tasks, but is not limited to such examples. For example, the providing unit prioritizes providing highly related tasks in the training environment. The providing unit can also provide less related tasks in the training environment later. For example, the providing unit optimizes the order of providing the training environment based on the relevance of the tasks. This enables efficient training by adjusting the order of providing the tasks based on the relevance of the tasks. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit may input task relevance data to a generating AI and cause the generating AI to adjust the order of providing the tasks.

[0110] The provision unit adjusts the use of provided terminology according to the expertise level of the craftsman when providing the training environment. The provision unit adjusts the use of provided terminology according to the expertise level of the craftsman when providing the training environment. The evaluation of the expertise level of the craftsman is performed, for example, based on the craftsman's years of experience and past performance, but is not limited to such examples. For example, if the expertise level of the craftsman is high, the provision unit uses a lot of terminology. Furthermore, if the expertise level of the craftsman is low, the provision unit can avoid terminology and use concise expressions. For example, the provision unit adjusts the use of provided terminology according to the expertise level of the craftsman. In this way, a training environment that is easier to understand can be provided by adjusting the use of provided terminology according to the expertise level of the craftsman. Some or all of the above-mentioned processing by the provision unit may be performed using, for example, AI, or may be performed without using AI. For example, the provision unit may input the expertise level data of the craftsman into the generation AI and cause the generation AI to adjust the use of terminology.

[0111] The matching unit estimates the emotions of the successor and adjusts the matching criteria based on the estimated emotions of the successor. The matching unit estimates the emotions of the successor and adjusts the matching criteria based on the estimated emotions of the successor. The estimation of the emotions of the successor is performed using, for example, facial expression analysis or voice analysis, but is not limited to these examples. For example, the matching unit estimates the emotions of the successor using facial expression analysis technology. The matching unit can also estimate the emotions of the successor using voice analysis technology. For example, the matching unit captures the facial expression of the successor with a camera and estimates the emotions using facial expression analysis technology. Adjusting the matching criteria based on the estimated emotions of the successor enables more appropriate matching. For example, if the successor is relaxed, detailed matching criteria can be provided. Alternatively, if the successor is in a hurry, simple matching criteria can be provided. Alternatively, if the successor is excited, visually stimulating matching criteria can be provided. Thus, adjusting the matching criteria according to the emotions of the successor enables more appropriate matching. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the matching unit may be performed using AI, or may be performed without using AI. For example, the matching unit may input image data of the successor taken with a camera into the generation AI and cause the generation AI to estimate the successor's emotions.

[0112] The matching unit adjusts the level of detail of the matching based on the skill level of the successor during matching. The matching unit adjusts the level of detail of the matching based on the skill level of the successor during matching. The evaluation of the skill level of the successor is performed, for example, based on test results or practical evaluation, but is not limited to these examples. For example, the matching unit provides detailed matching information when the skill level of the successor is high. The matching unit can also provide concise matching information when the skill level of the successor is low. For example, the matching unit adjusts the level of detail of the matching according to the skill level of the successor. This enables more appropriate matching by adjusting the level of detail of the matching based on the skill level of the successor. Some or all of the above-mentioned processing in the matching unit may be performed using, for example, AI, or may be performed without using AI. For example, the matching unit inputs the skill level data of the successor to the generation AI and causes the generation AI to adjust the level of detail of the matching.

[0113] The matching unit applies different matching algorithms depending on the interests of the successor during matching. The matching unit applies different matching algorithms depending on the interests of the successor during matching. The successor's interests are evaluated based on, for example, survey results or social media activity, but are not limited to these examples. For example, if the successor is interested in pottery, the matching unit applies a matching algorithm dedicated to pottery. Also, if the successor is interested in woodworking, the matching unit can apply a matching algorithm dedicated to woodworking. For example, if the successor is interested in dyeing, the matching unit applies a matching algorithm dedicated to dyeing. This enables more appropriate matching by applying different matching algorithms depending on the interests of the successor. Some or all of the above-mentioned processing in the matching unit may be performed using, for example, AI, or may be performed without using AI. For example, the matching unit can input the interests of the successor into the generation AI and cause the generation AI to apply a matching algorithm.

[0114] The matching unit improves the accuracy of matching by referring to the successor's past matching results during matching. The matching unit improves the accuracy of matching by referring to the successor's past matching results during matching. Reference to past matching results can be made, for example, using matching evaluations and feedback comments, but is not limited to these examples. For example, the matching unit improves the matching algorithm based on the successor's past matching results. The matching unit can also improve the accuracy of matching by referring to the successor's past matching results. For example, the matching unit adjusts the level of detail of matching by reflecting the successor's past matching results. By referring to the past matching results, the accuracy of matching is improved. Some or all of the above-mentioned processing in the matching unit may be performed, for example, using AI, or may be performed without using AI. For example, the matching unit can input the successor's past matching result data into the generation AI and cause the generation AI to improve the accuracy of matching.

[0115] The matching unit estimates the emotions of the successor and determines the matching priority based on the estimated emotions of the successor. The matching unit estimates the emotions of the successor and determines the matching priority based on the estimated emotions of the successor. The estimation of the emotions of the successor is performed using, for example, facial expression analysis or voice analysis, but is not limited to these examples. For example, the matching unit estimates the emotions of the successor using facial expression analysis technology. The matching unit can also estimate the emotions of the successor using voice analysis technology. For example, the matching unit captures the facial expression of the successor with a camera and estimates the emotions using facial expression analysis technology. Determining the matching priority based on the estimated emotions of the successor enables more appropriate matching. For example, if the successor is relaxed, detailed matching information can be provided preferentially. Also, if the successor is in a hurry, brief matching information can be provided preferentially. Also, if the successor is excited, visually stimulating matching information can be provided preferentially. Thus, determining the matching priority based on the emotions of the successor enables more appropriate matching. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the matching unit may be performed using AI, or may be performed without using AI. For example, the matching unit may input image data of the successor taken with a camera into the generation AI and cause the generation AI to estimate the successor's emotions.

[0116] During matching, the matching unit prioritizes highly relevant matching by taking into account the geographical location information of the successor. During matching, the matching unit prioritizes highly relevant matching by taking into account the geographical location information of the successor. Consideration of geographical location information is performed, for example, using GPS data or location information services, but is not limited to these examples. For example, if the successor lives in a specific area, the matching unit prioritizes matching with craftsmen in that area. The matching unit can also prioritize matching with craftsmen within a range that the successor can travel. For example, the matching unit performs optimal matching based on the geographical location information of the successor. This enables highly relevant matching by taking geographical location information into account. Some or all of the above-described processing in the matching unit may be performed using, for example, AI, or may be performed without using AI. For example, the matching unit can input the geographical location information data of the successor to the generation AI and cause the generation AI to perform highly relevant matching.

[0117] The matching unit analyzes the social media activity of the successor during matching and performs relevant matching. The matching unit analyzes the social media activity of the successor during matching and performs relevant matching. Analysis of social media activity is performed based on, for example, the content of posts, the number of followers, the engagement rate, etc., but is not limited to these examples. For example, the matching unit matches with relevant craftsmen based on the interests and concerns shared by the successor on social media. The matching unit can also match with the most suitable craftsmen based on the successor's social media activity. For example, the matching unit performs important matching based on the reactions of the successor's followers on social media. In this way, relevant matching can be performed efficiently by analyzing social media activity. Some or all of the above-mentioned processing in the matching unit may be performed using, for example, AI, or may be performed without using AI. For example, the matching unit can input the successor's social media activity data into the generation AI and cause the generation AI to perform relevant matching.

[0118] The matching unit customizes the matching method by reflecting the successor's past feedback during matching. The matching unit customizes the matching method by reflecting the successor's past feedback during matching. Reflecting past feedback is performed, for example, based on survey results, review comments, etc., but is not limited to these examples. For example, the matching unit improves the matching method based on feedback the successor has received in the past. The matching unit can also select the optimal matching method by referring to the successor's past feedback. For example, the matching unit reflects the successor's feedback to improve the accuracy of matching. In this way, the matching method can be optimized by reflecting the past feedback. Some or all of the above-mentioned processing in the matching unit may be performed using, for example, AI, or may be performed without using AI. For example, the matching unit can input the successor's past feedback data into the generation AI and cause the generation AI to customize the matching method.

[0119] The feedback unit estimates the successor's emotions and adjusts the feedback expression method based on the estimated emotions of the successor. The feedback unit estimates the successor's emotions and adjusts the feedback expression method based on the estimated emotions of the successor. The successor's emotions can be estimated using, for example, facial expression analysis or voice analysis, but are not limited to these examples. For example, the feedback unit estimates the successor's emotions using facial expression analysis technology. The feedback unit can also estimate the successor's emotions using voice analysis technology. For example, the feedback unit captures the successor's facial expression with a camera and estimates the emotion using facial expression analysis technology. By adjusting the feedback expression method based on the estimated emotions of the successor, more appropriate feedback can be provided. For example, if the successor is relaxed, detailed feedback can be provided. On the other hand, if the successor is in a hurry, brief feedback can be provided. On the other hand, if the successor is excited, visually stimulating feedback can be provided. In this way, by adjusting the feedback expression method according to the successor's emotions, more appropriate feedback can be provided. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the feedback unit may be performed using AI, or may be performed without using AI. For example, the feedback unit may input image data of the successor taken with a camera into the generation AI and cause the generation AI to estimate the successor's emotions.

[0120] The feedback unit adjusts the level of detail of the feedback based on the importance of the task when providing feedback. The feedback unit adjusts the level of detail of the feedback based on the importance of the task when providing feedback. The evaluation of the importance of the task is performed, for example, based on the impact or urgency of the task, but is not limited to these examples. For example, the feedback unit provides detailed feedback for important tasks. The feedback unit can also provide concise feedback for general tasks. For example, the feedback unit provides quick feedback for urgent tasks. This enables efficient feedback by adjusting the level of detail of the feedback based on the importance of the task. Some or all of the above-described processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit may input task importance data to a generation AI and cause the generation AI to adjust the level of detail of the feedback.

[0121] The feedback unit applies different feedback algorithms depending on the task category when providing feedback. The feedback unit applies different feedback algorithms depending on the task category when providing feedback. Task categories can be classified based on, for example, woodworking, metalworking, pottery, etc., but are not limited to these examples. For example, the feedback unit applies a feedback algorithm dedicated to pottery work to pottery work. The feedback unit can also apply a feedback algorithm dedicated to woodworking to woodworking work. For example, the feedback unit applies a feedback algorithm dedicated to dyeing work to dyeing work. In this way, by applying different feedback algorithms depending on the task category, the accuracy of the feedback is improved. Some or all of the above-mentioned processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit can input task category data to the generation AI and cause the generation AI to apply the feedback algorithm.

[0122] The feedback unit improves the accuracy of the feedback by referring to the successor's past feedback results when providing feedback. The feedback unit improves the accuracy of the feedback by referring to the successor's past feedback results when providing feedback. Reference to past feedback results can be made, for example, using feedback ratings or comments, but is not limited to these examples. For example, the feedback unit improves the feedback algorithm based on the successor's past feedback results. The feedback unit can also improve the accuracy of the feedback by referring to the successor's past feedback results. For example, the feedback unit adjusts the level of detail of the feedback by reflecting the successor's past feedback results. In this way, the accuracy of the feedback is improved by referring to the past feedback results. Some or all of the above-described processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit can input the successor's past feedback result data into the generation AI and cause the generation AI to improve the accuracy of the feedback.

[0123] The feedback unit estimates the emotions of the successor and adjusts the length of the feedback based on the estimated emotions of the successor. The feedback unit estimates the emotions of the successor and adjusts the length of the feedback based on the estimated emotions of the successor. The estimation of the emotions of the successor is performed using, for example, facial expression analysis or voice analysis, but is not limited to these examples. For example, the feedback unit estimates the emotions of the successor using facial expression analysis technology. The feedback unit can also estimate the emotions of the successor using voice analysis technology. For example, the feedback unit captures the facial expression of the successor with a camera and estimates the emotions using facial expression analysis technology. By adjusting the length of the feedback based on the estimated emotions of the successor, more appropriate feedback can be provided. For example, if the successor is in a hurry, short and to the point feedback can be provided. On the other hand, if the successor is relaxed, detailed feedback can be provided. On the other hand, if the successor is excited, visually stimulating feedback can be provided. Thus, by adjusting the length of the feedback according to the emotions of the successor, more appropriate feedback can be provided. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the feedback unit may be performed using AI, or may be performed without using AI. For example, the feedback unit may input image data of the successor taken with a camera into the generation AI and cause the generation AI to estimate the successor's emotions.

[0124] The feedback unit determines the priority of the feedback based on the time when the work is performed at the time of feedback. The feedback unit determines the priority of the feedback based on the time when the work is performed at the time of feedback. The time when the work is performed is considered based on, for example, the start date of the work or the end date of the work, but is not limited to such examples. For example, the feedback unit provides feedback preferentially to work that is highly urgent. The feedback unit can also provide feedback preferentially to work that is performed periodically. For example, the feedback unit provides feedback preferentially to work that is performed seasonally. This enables efficient feedback by determining the priority of the feedback based on the time when the work is performed. Some or all of the above-mentioned processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit can input work performance time data to the generation AI and cause the generation AI to determine the priority of the feedback.

[0125] The feedback unit adjusts the order of feedback based on the relevance of tasks when providing feedback. The feedback unit adjusts the order of feedback based on the relevance of tasks when providing feedback. The evaluation of task relevance is performed, for example, based on task dependency or commonalities, but is not limited to such examples. For example, the feedback unit provides feedback preferentially to highly related tasks. The feedback unit can also provide feedback later to less related tasks. For example, the feedback unit optimizes the order of feedback based on the relevance of tasks. This enables efficient feedback by adjusting the order of feedback based on the relevance of tasks. Some or all of the above-described processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit inputs task relevance data to a generation AI and causes the generation AI to adjust the order of feedback.

[0126] The feedback unit adjusts the use of technical terms in the feedback according to the expertise level of the successor when providing feedback. The feedback unit adjusts the use of technical terms in the feedback according to the expertise level of the successor when providing feedback. The evaluation of the expertise level of the successor is based on, for example, the successor's years of experience and past performance, but is not limited to such examples. For example, if the expertise level of the successor is high, the feedback unit uses a lot of technical terms. Furthermore, if the expertise level of the successor is low, the feedback unit can avoid technical terms and use concise expressions. For example, the feedback unit adjusts the use of technical terms in the feedback according to the expertise level of the successor. In this way, by adjusting the use of technical terms in the feedback according to the expertise level of the successor, more understandable feedback can be provided. Some or all of the above-described processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit may input the expertise level data of the successor to the generation AI and cause the generation AI to adjust the use of technical terms.

[0127] The evaluation unit estimates the successor's emotions and adjusts the evaluation criteria based on the estimated emotions of the successor. The evaluation unit estimates the successor's emotions and adjusts the evaluation criteria based on the estimated emotions of the successor. The estimation of the successor's emotions is performed using, for example, facial expression analysis or voice analysis, but is not limited to these examples. For example, the evaluation unit estimates the successor's emotions using facial expression analysis technology. The evaluation unit can also estimate the successor's emotions using voice analysis technology. For example, the evaluation unit captures the successor's facial expression with a camera and estimates the emotions using facial expression analysis technology. Adjusting the evaluation criteria based on the estimated emotions of the successor enables more appropriate evaluation. For example, if the successor is relaxed, detailed evaluation criteria can be provided. If the successor is in a hurry, concise evaluation criteria can be provided. If the successor is excited, visually stimulating evaluation criteria can be provided. Thus, adjusting the evaluation criteria according to the successor's emotions enables more appropriate evaluation. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the evaluation unit may be performed using AI, or may be performed without using AI. For example, the evaluation unit may input image data of the successor taken with a camera into the generation AI and cause the generation AI to estimate the successor's emotions.

[0128] The evaluation unit adjusts the level of detail of the evaluation based on the skill level of the successor during the evaluation. The evaluation unit adjusts the level of detail of the evaluation based on the skill level of the successor during the evaluation. The evaluation of the skill level of the successor is performed, for example, based on test results or practical evaluation, but is not limited to such examples. For example, the evaluation unit performs a detailed evaluation when the skill level of the successor is high. Furthermore, the evaluation unit can perform a brief evaluation when the skill level of the successor is low. For example, the evaluation unit adjusts the level of detail of the evaluation according to the skill level of the successor. This enables a more appropriate evaluation by adjusting the level of detail of the evaluation based on the skill level of the successor. Some or all of the above-described processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit may input the skill level data of the successor to the generation AI and cause the generation AI to adjust the level of detail of the evaluation.

[0129] The evaluation unit applies different evaluation algorithms depending on the successor's interests during evaluation. The evaluation unit applies different evaluation algorithms depending on the successor's interests during evaluation. Evaluation of the successor's interests is performed based on, for example, survey results, social media activity, etc., but is not limited to these examples. For example, if the successor is interested in pottery, the evaluation unit applies an evaluation algorithm dedicated to pottery. Also, if the successor is interested in woodworking, the evaluation unit can apply an evaluation algorithm dedicated to woodworking. For example, if the successor is interested in dyeing, the evaluation unit applies an evaluation algorithm dedicated to dyeing. This allows for more appropriate evaluation by applying different evaluation algorithms depending on the successor's interests. Some or all of the above-mentioned processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit may input the successor's interests data into the generation AI and cause the generation AI to apply the evaluation algorithm.

[0130] The evaluation unit improves the accuracy of the evaluation by referring to the successor's past evaluation results during the evaluation. The evaluation unit improves the accuracy of the evaluation by referring to the successor's past evaluation results during the evaluation. Reference to past evaluation results can be made, for example, using evaluation reports or feedback comments, but is not limited to these examples. For example, the evaluation unit improves the evaluation algorithm based on the successor's past evaluation results. The evaluation unit can also improve the accuracy of the evaluation by referring to the successor's past evaluation results. For example, the evaluation unit adjusts the level of detail of the evaluation by reflecting the successor's past evaluation results. In this way, the accuracy of the evaluation is improved by referring to the past evaluation results. Some or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can input the successor's past evaluation result data into the generation AI and cause the generation AI to improve the accuracy of the evaluation.

[0131] The evaluation unit estimates the emotions of the successor and determines the priority of the evaluations based on the estimated emotions of the successor. The evaluation unit estimates the emotions of the successor and determines the priority of the evaluations based on the estimated emotions of the successor. The estimation of the emotions of the successor is performed using, for example, facial expression analysis or voice analysis, but is not limited to these examples. For example, the evaluation unit estimates the emotions of the successor using facial expression analysis technology. The evaluation unit can also estimate the emotions of the successor using voice analysis technology. For example, the evaluation unit captures the facial expression of the successor with a camera and estimates the emotions using facial expression analysis technology. Determining the priority of the evaluations based on the estimated emotions of the successor enables more appropriate evaluations. For example, if the successor is relaxed, a detailed evaluation can be prioritized. Also, if the successor is in a hurry, a brief evaluation can be prioritized. Also, if the successor is excited, a visually stimulating evaluation can be prioritized. Thus, determining the priority of the evaluations based on the emotions of the successor enables more appropriate evaluations. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the evaluation unit may be performed using AI, or may be performed without using AI. For example, the evaluation unit may input image data of the successor taken with a camera into the generation AI and cause the generation AI to estimate the successor's emotions.

[0132] During evaluation, the evaluation unit prioritizes highly relevant evaluations by taking into account the geographical location information of the successor. During evaluation, the evaluation unit prioritizes highly relevant evaluations by taking into account the geographical location information of the successor. Consideration of geographical location information is performed, for example, using GPS data or location information services, but is not limited to such examples. For example, if the successor lives in a specific area, the evaluation unit prioritizes evaluations with craftsmen in that area. The evaluation unit can also prioritize evaluations with craftsmen within the successor's travel range. For example, the evaluation unit performs an optimal evaluation based on the geographical location information of the successor. This enables highly relevant evaluations by taking geographical location information into account. Some or all of the above-described processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit may input the geographical location information data of the successor into the generation AI and cause the generation AI to perform highly relevant evaluations.

[0133] During the evaluation, the evaluation unit analyzes the social media activity of the successor and performs a related evaluation. During the evaluation, the evaluation unit analyzes the social media activity of the successor and performs a related evaluation. The analysis of social media activity is performed, for example, based on the content of posts, the number of followers, the engagement rate, etc., but is not limited to these examples. For example, the evaluation unit evaluates related craftsmen based on the interests and concerns shared by the successor on social media. The evaluation unit can also evaluate the most suitable craftsmen based on the successor's social media activity. For example, the evaluation unit performs important evaluations based on the reactions of the successor's followers on social media. In this way, the related evaluations can be performed efficiently by analyzing social media activity. Some or all of the above-mentioned processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit may input the successor's social media activity data into the generation AI and cause the generation AI to perform the related evaluation.

[0134] The evaluation unit customizes the evaluation method by reflecting the successor's past feedback during evaluation. The evaluation unit customizes the evaluation method by reflecting the successor's past feedback during evaluation. Reflecting past feedback is performed, for example, based on survey results, review comments, etc., but is not limited to these examples. For example, the evaluation unit improves the evaluation method based on feedback the successor has received in the past. The evaluation unit can also select the optimal evaluation method by referring to the successor's past feedback. For example, the evaluation unit reflects the successor's feedback to improve the accuracy of the evaluation. In this way, the evaluation method can be optimized by reflecting past feedback. Some or all of the above-mentioned processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit can input the successor's past feedback data into the generation AI and cause the generation AI to customize the evaluation method. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, analysis unit, provision unit, and matching unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit can record the work and procedures of the craftsman using the camera 42 and microphone 38B of the smart device 14. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the data obtained from the collection unit. The provision unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12 and provides a training environment based on the analysis results. The matching unit is realized by the specific processing unit 290 of the data processing device 12 and suggests an optimal training program based on the skill level and interests of the successor. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, analysis unit, provision unit, and matching unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit can record the work and procedures of the craftsman using the camera 42 and microphone 238 of the smart glasses 214. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the data obtained from the collection unit. The provision unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12 and provides a training environment based on the analysis results. The matching unit is realized by the specific processing unit 290 of the data processing device 12 and suggests an optimal training program based on the skill level and interests of the successor. === Hard Collateral 1-3 === Each of the multiple elements, including the collection unit, analysis unit, provision unit, and matching unit, described above, is realized, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the collection unit can record the work and procedures of the craftsman using the camera 42 or microphone 238 of the headset terminal 314. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the data obtained from the collection unit. The provision unit is realized by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12 and provides a training environment based on the analysis results. The matching unit is realized by the specific processing unit 290 of the data processing device 12 and suggests an optimal training program based on the skill level and interests of the successor. Each of the elements including the collection unit, analysis unit, provision unit, and matching unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit can record the work and procedures of the craftsman using the camera 42 or microphone 238 of the robot 414. The analysis unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes the data obtained from the collection unit. The provision unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12, and provides a training environment based on the analysis results. The matching unit is realized by the specific processing unit 290 of the data processing device 12, and proposes an optimal training program based on the skill level and interests of the successor.

[0135] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0136] The collection unit can also record audio data of the craftsman's work environment, and the analysis unit can analyze the audio data to recreate the atmosphere and environmental sounds of the work. For example, the sound of a saw made during woodworking or the sound of water heard during pottery making can be recorded, and a successor can listen to those sounds in the training environment to provide a more realistic work experience. The analysis unit can also analyze the audio data to understand the progress of the work, and the provision unit can adjust the content of the training video based on that information. Furthermore, the collection unit can record the craftsman's conversations and instructions while he or she is working, and the analysis unit can analyze the content and provide it to the successor.

[0137] The provision department can also customize the training environment according to the successor's learning style. For example, detailed videos and illustrations can be provided for successors who prefer visual learning, while audio guides and explanations can be enhanced for successors who prefer auditory learning. In addition, interactive simulations and practical practice opportunities can be increased for successors who prefer practical learning. This makes it possible to provide the optimal training environment according to the successor's learning style.

[0138] The matching unit can also evaluate the personality traits of the successor and match them with the craftsman, taking into consideration their compatibility. For example, an introverted successor can be matched with a craftsman who works in a quiet environment, while an extroverted successor can be matched with a craftsman who is more communicative. In addition, by evaluating personality traits such as stress tolerance and cooperativeness and matching with the most suitable craftsman, it is possible to provide a more comfortable learning environment for the successor.

[0139] The collection unit records biometric data (heart rate, electrodermal activity, etc.) of the craftsman while he works, and the analysis unit analyzes the data to understand the craftsman's concentration and stress level. For example, if a craftsman is working with a high level of concentration, the work procedure can be recorded in detail and provided to the successor. Also, if the craftsman is feeling stressed, the cause can be analyzed and improvement measures can be proposed. In this way, a more effective training environment can be provided by utilizing the craftsman's biometric data.

[0140] The analysis unit can also analyze the work data of craftsmen and suggest ways to improve work efficiency and improve areas. For example, it can detect unnecessary movements during work and suggest efficient work procedures. It can also suggest optimizing the tools and materials used, improving work quality. Furthermore, the analysis unit can compare the data of other craftsmen to extract best practices and provide them to successors. In this way, the work data of craftsmen can be used to improve work efficiency and quality.

[0141] The providing unit can also estimate the emotions of the successor and adjust the speed of the training progress based on the estimated emotions. For example, if the successor is feeling impatient or anxious, the training progress can be slowed down and detailed explanations can be added. Also, if the successor is confident, the training progress can be accelerated and the successor can move on to the next step. This makes it possible to achieve optimal training progress according to the emotions of the successor.

[0142] The collection unit records environmental data (temperature, humidity, illuminance, etc.) while the craftsman is working, and the analysis unit analyzes the data to suggest the optimal work environment. For example, working at the appropriate temperature and humidity can maintain the quality of materials. Adjusting the illuminance can also improve the accuracy of work. Furthermore, the collection unit can adjust the recording method according to changes in the work environment and collect more accurate data. This makes it possible to optimize the craftsman's work environment and improve the quality of work.

[0143] The analysis unit can also analyze the work data of craftsmen, identify risk factors in the work, and propose safety measures. For example, it can identify the risk of accidents and injuries that may occur during work and propose safe work procedures. It can also evaluate the safety of tools and materials used and propose appropriate ways to use them. Furthermore, the analysis unit can compare the data of other craftsmen to extract best practices for safety measures and provide them to successors. In this way, a safe working environment can be achieved by utilizing the work data of craftsmen.

[0144] The providing unit can also estimate the emotions of the successor and customize the training content based on the estimated emotions. For example, if the successor is excited, it can provide challenging tasks to increase the successor's motivation. Also, if the successor is tired, it can provide relaxing content to reduce the burden on the successor. In this way, it is possible to provide optimal training content according to the successor's emotions.

[0145] The collection unit records gaze data of craftsmen while they work, and the analysis unit analyzes the data to identify the key points of the work. For example, it can analyze where the craftsman focuses during a specific work step and emphasize those points to teach the successor. It can also make suggestions to improve work efficiency based on the gaze data. Furthermore, the collection unit can analyze the gaze data in real time and guide the successor so that they can focus on the same points. In this way, it is possible to utilize the gaze data of craftsmen to provide a more effective training environment.

[0146] The processing flow of the second embodiment will be briefly explained below.

[0147] Step 1: The collection department records the artisan's work or steps with video and photographs. The artisan's work may include woodworking, pottery, metalworking, etc. The collection department uses high-resolution video cameras to film and photograph each step. They can also record the artisan's hand movements and details of the tools they use. For example, they could use motion capture technology to record hand movements, as well as the type of tools they use and how often they use them. Step 2: The analysis unit analyzes the information recorded by the collection unit. This analysis is performed using image analysis algorithms and data mining techniques. For example, it analyzes videos and photos to generate detailed descriptions of each step. Generative AI is used to generate detailed descriptions and analyze the content of videos and photos to extract key points of each step. Step 3: The provision unit provides a training environment based on the information analyzed by the analysis unit. The training environment is provided using a virtual reality (VR) environment or simulation software. For example, an environment is provided in which the successor watches a training video created by the generative AI and actually performs the work. The provision unit may also be equipped with a feedback unit that provides feedback in real time. Step 4: The matching unit matches a successor based on the training environment provided by the provision unit. Matching is based on the successor's skill level, interests, geographical location, etc. For example, the successor inputs their skill level and interests, and the generation AI suggests the optimal training program.

[0148] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0149] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0150] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0151] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0152] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0153] 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.

[0154] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0155] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0156] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0157] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0158] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0159] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0160] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0161] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0162] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0163] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0164] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0165] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0166] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0167] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0168] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0169] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0170] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0171] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0172] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0173] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0174] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0175] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0176] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0177] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0178] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0179] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0180] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0181] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0182] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0183] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0184] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0185] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0186] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0187] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0188] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0189] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0190] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0191] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0192] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0193] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0194] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0195] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0196] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0197] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0198] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0199] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0200] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0201] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0202] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0203] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0204] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0205] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0206] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0207] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0208] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0209] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0210] 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.

[0211] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0212] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0213] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0214] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0215] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0216] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0217] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0218] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0219] [Explanation of symbols]

[0220] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a collection department that records the work or procedures of the craftsmen through video and photographs; an analysis unit that analyzes the information recorded by the collection unit; a providing unit that provides a training environment based on the information analyzed by the analyzing unit; a matching unit that matches a successor based on the training environment provided by the providing unit; Equipped with A system characterized by:

2. The providing unit Equipped with a feedback unit that provides feedback in real time using generation AI 2. The system of claim 1.

3. The matching unit Equipping an evaluation department to evaluate the skill level of successors 2. The system of claim 1.

4. The collecting unit Record details of the craftsman's hand movements or the tools he uses 2. The system of claim 1.

5. The analysis unit Analyzes videos or photos and generates detailed instructions for each step 2. The system of claim 1.

6. The providing unit Provide an environment where successors can watch training videos created by generative AI and actually perform the work.

2. The system of claim 1.

7. The collecting unit Estimate the emotions of the craftsman and adjust the timing of recording based on the estimated emotions of the craftsman 2. The system of claim 1.

8. The collecting unit Analyzing the craftsman's past work history and selecting the optimal recording method 2. The system of claim 1.

9. The collecting unit When recording, filtering is performed based on the craftsman's working environment and the materials used.

2. The system of claim 1.

Images