system

Abstract

The system according to this embodiment aims to automatically generate and provide optimal training programs tailored to the skill levels and goals of employees. [Solution] The system according to the embodiment comprises an analysis unit, a generation unit, and a monitoring unit. The analysis unit analyzes employees' historical data, current skill levels, and individual goals. The generation unit automatically generates and provides an optimal training program based on the analysis results obtained by the analysis unit. The monitoring unit monitors training progress in real time based on the training program generated by the generation unit and provides feedback and support.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that it takes a great deal of labor time to create and maintain an in-house training program, and it is difficult to provide training that meets the individual needs of employees.

[0005] The system according to the embodiment aims to automatically generate and provide an optimal training program according to the skill level and goals of employees.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an analysis unit, a generation unit, and a monitoring unit. The analysis unit analyzes employees' historical data, current skill levels, and individual goals. The generation unit automatically generates and provides an optimal training program based on the analysis results obtained by the analysis unit. The monitoring unit monitors training progress in real time based on the training program generated by the generation unit and provides feedback and support. [Effects of the Invention]

[0007] The system according to this embodiment can automatically generate and provide optimal training programs tailored to the skill levels and goals of employees. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The training program generation system according to an embodiment of the present invention is a system that utilizes multimodal AI to automatically generate and provide in-house training programs that combine videos and text, with an AI agent. This training program generation system addresses the challenges of traditional in-house training programs, which require significant labor time to create and maintain, and the limited resources available to provide uniform training to all employees, as well as the difficulty in providing training that meets the individual needs of employees. To solve these problems, the system consists of the following steps. First, the training program generation system uses an AI agent to analyze employees' historical data, current skill levels, and individual goals, and automatically generates and provides an optimal training program. Specifically, it provides customized training materials that combine videos, text, and practical exercises, which employees can access from home or the office. The training program generation system monitors training progress in real time and provides personalized feedback and support. For example, the training program generation system automatically generates text materials such as explanatory materials, manuals, and case studies according to the employee's skill level. It also generates visual content such as charts and graphs to deepen understanding of topics. Furthermore, it enables the creation of training videos, real-time generation of video subtitles, and multilingual support. It also generates text summaries of lecture content and key points. As an interactive learning experience, the training program generation system features an AI chatbot that answers questions in real time during learning, allowing learners to resolve doubts immediately. It also generates simulations that mimic actual work scenarios, enabling employees to develop practical skills. For progress management and personalized feedback, the training program generation system monitors learners' progress in real time and suggests the next steps based on their learning curve. It automatically generates feedback that provides specific areas for improvement and next learning points based on learning progress. For evaluation and assessment, it automatically generates and evaluates quizzes and tests, and automatically generates explanations for mistakes. Based on learning history, it creates individual competency diagnostic reports and suggests future learning strategies.In this way, the training program generation system can propose and manage optimal training content tailored to each employee's skill level and role, and provide individually customized training materials, thereby streamlining in-house training programs and providing effective learning opportunities.

[0029] The training program generation system according to the embodiment comprises an analysis unit, a generation unit, and a monitoring unit. The analysis unit analyzes employee historical data, current skill levels, and individual goals. Employee historical data includes, but is not limited to, past projects, work history, and evaluation history. Skill levels are evaluated based on evaluation criteria and specific measurement methods, such as skill matrices and certification status. Goals are set based on specific content and setting methods, such as short-term goals, long-term goals, and quantitative goals. The generation unit automatically generates and provides an optimal training program based on the analysis results obtained by the analysis unit. An optimal training program includes, but is not limited to, the type, duration, and content of the training. The generation unit generates customized training materials, such as videos, text, and practical exercises. The generation unit can also adjust the content of the training program according to the employee's skill level and role. The monitoring unit monitors training progress in real time based on the training program generated by the generation unit and provides feedback and support. Specific definitions and criteria of real time include, but are not limited to, seconds, minutes, and instantaneous. The monitoring unit, for example, monitors employees' learning progress and suggests the next steps based on their learning curve. The monitoring unit can also automatically generate feedback that provides specific areas for improvement and next learning points based on learning progress. As a result, the training program generation system according to this embodiment provides an optimal training program based on employees' historical data, skill levels, and goals, and enables efficient training by monitoring progress in real time.

[0030] The analytics department analyzes employee history data, current skill levels, and individual goals. Employee history data includes, but is not limited to, past projects, work history, and performance evaluations. This data is used to gain a detailed understanding of employees' past work experience and achievements. For example, past project data shows what projects employees have participated in and what roles they have played, while work history shows the types of jobs they have held. Performance evaluations include past performance evaluations and feedback, revealing employees' strengths and areas for improvement. Skill levels are assessed based on evaluation criteria and specific measurement methods, such as skill matrices and certifications. Skill matrices list the skills employees possess and assess their proficiency in each skill, while certifications show the qualifications and certifications employees have obtained. This allows for an accurate understanding of employees' current skill levels. Goals are set based on specific content and setting methods, such as short-term goals, long-term goals, and quantitative goals. Short-term goals indicate objectives to be achieved within a few weeks to a few months, while long-term goals indicate objectives to be achieved over several years. Quantitative goals are targets set based on specific numbers and indicators, and are used to measure employee growth and performance. The analytics department comprehensively analyzes this data to identify employees' strengths, weaknesses, and growth opportunities. For example, they use AI to analyze data, identify employee skill gaps, and determine which skills need strengthening. They also determine what kind of training is optimal based on employee goals. This allows the analytics department to provide the foundational data needed to deliver the most suitable training program for each individual employee.

[0031] The generation unit automatically generates and provides an optimal training program based on the analysis results obtained by the analysis unit. An optimal training program includes, but is not limited to, the type, duration, and content of the training. The generation unit generates customized training materials, such as a combination of videos, text, and practical exercises. Video materials are used to make learning content easier to understand visually, while text materials are used to provide detailed explanations and theoretical background. Practical exercises are used to allow employees to experience the learning content firsthand and acquire skills. The generation unit combines these materials to generate customized training programs tailored to the skill level and role of each employee. For example, it provides a program focusing on basic content for beginners and a program including advanced content and practical exercises for advanced learners. The generation unit can also adjust the content of the training program according to the employee's skill level and role. For example, it can focus training on strengthening specific skills for employees lacking those skills, and provide advanced training to further enhance the skills of employees who already possess high skill levels. Furthermore, the generation unit can monitor the progress and effectiveness of the training program in real time and adjust the program content as needed. This allows the generation unit to provide each employee with an optimal training program, supporting efficient and effective learning.

[0032] The monitoring unit monitors training progress in real time based on the training program generated by the generation unit and provides feedback and support. Specific definitions and criteria of "real time" include, but are not limited to, seconds, minutes, or instantaneous. For example, the monitoring unit monitors employee learning progress and suggests the next steps based on the learning curve. The learning curve indicates the employee's learning speed and comprehension, and is used to determine what to learn next and when. The monitoring unit can also automatically generate feedback that provides specific areas for improvement and next learning points based on learning progress. For example, it can use AI to analyze learning data, identify areas where employees are struggling, and provide specific advice to strengthen those areas. Furthermore, the monitoring unit can provide additional support and resources depending on the employee's learning situation. For example, it can provide additional learning materials on specific topics or individual coaching from experts. The monitoring unit can also collect employee feedback to improve the training program. For example, it can collect employee opinions and requests regarding the training program and use that to improve the program's content and format. This allows the monitoring department to effectively support employee learning and continuously improve the quality of training programs.

[0033] The text generation unit can automatically generate text materials. For example, it can automatically generate explanatory materials, manuals, and case studies tailored to the skill levels of employees. For instance, the text generation unit can use a generation AI to generate explanatory materials tailored to the skill levels of employees. It can also use a generation AI to generate manuals tailored to the skill levels of employees. Furthermore, it can use a generation AI to generate case studies tailored to the skill levels of employees. This allows the text generation unit to efficiently provide training content to employees by automatically generating text materials. Text materials include, but are not limited to, manuals, guidebooks, and tutorials.

[0034] The visual generation unit can generate visual content. For example, it can generate visual content such as charts and graphs to deepen understanding of a topic. For instance, the visual generation unit can generate charts using a generation AI. It can also generate graphs using a generation AI. Furthermore, it can generate infographics using a generation AI. This allows the visual generation unit to provide visually easy-to-understand training content by generating visual content. Visual content includes, but is not limited to, charts, illustrations, and infographics.

[0035] The video generation unit can create training videos. For example, the video generation unit can create training videos, generate video subtitles in real time, and support multiple languages. For instance, the video generation unit can create training videos using a generation AI. Furthermore, the video generation unit can generate video subtitles in real time using a generation AI. In addition, the video generation unit can create multilingual training videos using a generation AI. This allows the video generation unit to provide visually and dynamically engaging training content by creating training videos. Training videos include, but are not limited to, lecture videos, demonstration videos, and simulation videos.

[0036] The chatbot unit can provide an AI chatbot that answers questions in real time during learning. For example, the chatbot unit can answer questions that arise during learning in real time. For example, the chatbot unit can provide an AI chatbot that answers questions in real time using generative AI. The chatbot unit can also use generative AI to provide responses that include detailed explanations to questions during learning. Furthermore, the chatbot unit can use generative AI to provide concise and to-the-point responses to questions during learning. As a result, the chatbot unit can instantly resolve learners' doubts by answering questions in real time during learning. AI chatbots include, but are not limited to, natural language processing technology and response patterns.

[0037] The simulation generation unit can generate simulations that mimic actual business scenarios. For example, the simulation generation unit can generate simulations that mimic actual business scenarios, enabling employees to develop practical skills. For instance, the simulation generation unit can use generation AI to generate simulations that mimic actual business scenarios. Furthermore, the simulation generation unit can use generation AI to generate simulated exercises based on business scenarios. In addition, the simulation generation unit can use generation AI to generate virtual environments. This allows the simulation generation unit to cultivate practical skills by generating simulations that mimic actual business scenarios. Simulations include, but are not limited to, business scenarios, simulated exercises, and virtual environments.

[0038] The evaluation unit can automatically generate and evaluate quizzes and tests. For example, the evaluation unit can automatically generate and evaluate quizzes and tests, and also automatically generate explanations for incorrect answers. For instance, the evaluation unit can use a generation AI to automatically generate quizzes and tests. Furthermore, the evaluation unit can use the generation AI to evaluate quizzes and tests. In addition, the evaluation unit can use the generation AI to automatically generate explanations for incorrect answers. This allows the evaluation unit to efficiently assess learners' understanding by automatically generating and evaluating quizzes and tests. Quizzes and tests include, but are not limited to, multiple-choice questions, written answers, and practical skills tests.

[0039] The report generation unit can create individual competency assessment reports. For example, the report generation unit can create individual competency assessment reports based on learning history and propose future learning strategies. For instance, the report generation unit can use a generation AI to create competency assessment reports based on learning history. Furthermore, the report generation unit can use a generation AI to create reports that propose future learning strategies. In addition, the report generation unit can use a generation AI to create reports that include learner skill assessments and performance reviews. This allows the report generation unit to gain a detailed understanding of learners' abilities and propose future learning strategies by creating individual competency assessment reports. Competency assessment reports may include, but are not limited to, skill assessments, performance reviews, and feedback.

[0040] The analytics department can analyze an employee's past training history and select the most suitable analysis method. For example, the analytics department can evaluate an employee's current skill level based on the content of training they have received in the past. For example, the analytics department can use generative AI to analyze an employee's past training history. The analytics department can also focus its analysis on topics that an employee has struggled with in the past. Furthermore, the analytics department can prioritize selecting training methods in which an employee has received high marks in the past. In this way, the analytics department can select the most suitable analysis method by analyzing an employee's past training history. Past training history includes, but is not limited to, training programs attended, performance, and feedback.

[0041] The analytics department can filter data based on an employee's current projects and roles during analysis. For example, the analytics department can focus its analysis on skills related to the projects an employee is currently working on. For instance, the analytics department can use generative AI to filter data based on an employee's current projects and roles. The analytics department can also filter the necessary skill sets according to the employee's role. Furthermore, the analytics department can prioritize analysis based on the progress of an employee's projects. This allows the analytics department to perform highly relevant analysis by filtering data based on an employee's current projects and roles. Current projects and roles include, but are not limited to, assigned tasks, project progress, and job title.

[0042] The generation unit can adjust the level of detail of the generated training based on its importance. For example, the generation unit can generate programs with detailed explanations and exercises for high-importance training. For instance, the generation unit can use generation AI to generate high-importance training programs. The generation unit can also generate programs with simplified explanations and exercises for low-importance training. Furthermore, the generation unit can progressively refine the training content according to its importance. This allows the generation unit to provide efficient training programs by adjusting the level of detail of the generated training based on its importance. The importance of training includes, but is not limited to, factors such as impact on business operations, urgency, and priority.

[0043] The generation unit can apply different generation algorithms depending on the training category during generation. For example, for technical training, the generation unit can apply a generation algorithm specialized in technical content. For instance, the generation unit can generate technical training programs using generational AI. Furthermore, for management training, the generation unit can apply a generation algorithm specialized in management skills. Additionally, for communication training, the generation unit can apply a generation algorithm specialized in communication skills. This allows the generation unit to provide more appropriate training programs by applying different generation algorithms depending on the training category. Generation algorithms include, but are not limited to, machine learning algorithms and rule-based generation.

[0044] The monitoring unit can improve the accuracy of its monitoring by considering the interrelationships of training. For example, the monitoring unit can analyze the interrelationships of training and monitor the progress of related training all at once. For example, the monitoring unit can use generative AI to analyze the interrelationships of training. The monitoring unit can also detect delays in progress early by considering the interrelationships of training. Furthermore, the monitoring unit can monitor for biases in progress based on the interrelationships of training. As a result, the monitoring unit can improve the accuracy of its monitoring by considering the interrelationships of training, enabling more accurate progress management. Interrelationships of training include, but are not limited to, related skills, prerequisites, and dependencies.

[0045] The monitoring department can perform monitoring while considering employee attribute information. For example, the monitoring department can adjust monitoring criteria according to the employee's position. For example, the monitoring department can use generative AI to perform monitoring while considering employee attribute information. The monitoring department can also adjust monitoring criteria according to the employee's years of experience. Furthermore, the monitoring department can adjust monitoring criteria according to the employee's skill level. As a result, the monitoring department can perform monitoring while considering employee attribute information, enabling more individualized progress management. Employee attribute information includes, but is not limited to, age, gender, work history, and skill set.

[0046] The text generation unit can adjust the level of detail in the text based on the importance of the training during text generation. For example, the text generation unit can generate text with detailed explanations for high-importance training. For example, the text generation unit can use a generation AI to generate high-importance training text. The text generation unit can also generate text with concise explanations for low-importance training. Furthermore, the text generation unit can adjust the level of detail in the text in stages according to importance. This allows the text generation unit to provide efficient text materials by adjusting the level of detail in the text based on the importance of the training. The level of detail in the text includes, but is not limited to, the depth of information, the number of specific examples, and the thoroughness of the explanations.

[0047] The text generation unit can apply different generation algorithms depending on the training category when generating text. For example, for technical training, the text generation unit can apply a generation algorithm specialized in technical content. For instance, the text generation unit can use a generation AI to generate technical training text. Furthermore, for management training, the text generation unit can apply a generation algorithm specialized in management skills. In addition, for communication training, the text generation unit can apply a generation algorithm specialized in communication skills. This allows the text generation unit to provide more appropriate text materials by applying different generation algorithms depending on the training category. Generation algorithms include, but are not limited to, machine learning algorithms and rule-based generation.

[0048] The text generation unit can prioritize texts based on the training submission deadlines during text generation. For example, the text generation unit can prioritize generating texts for training with approaching submission deadlines. For instance, the text generation unit can use a generation AI to generate training texts with approaching deadlines. The text generation unit can also postpone generating texts for training with distant submission deadlines. Furthermore, the text generation unit can adjust the text generation order according to the submission deadlines. This enables the text generation unit to provide efficient text materials by prioritizing texts based on the training submission deadlines. Text prioritization includes, but is not limited to, submission deadlines, importance, and urgency.

[0049] The visual generation unit can adjust the level of detail of visuals based on the importance of the training during the visual generation process. For example, the visual generation unit can generate detailed visuals for high-importance training. For instance, the visual generation unit can use a generation AI to generate high-importance training visuals. The visual generation unit can also generate concise visuals for low-importance training. Furthermore, the visual generation unit can adjust the level of detail of visuals in stages according to importance. This allows the visual generation unit to provide efficient visual learning materials by adjusting the level of detail of visuals based on the importance of the training. Visual detail includes, but is not limited to, resolution, amount of information, and number of specific examples.

[0050] The visual generation unit can apply different generation algorithms depending on the training category when generating visuals. For example, for technical training, the visual generation unit generates visuals that are specialized in technical content. For example, the visual generation unit can use generation AI to generate technical training visuals. Furthermore, for management training, the visual generation unit can generate visuals that are specialized in management skills. In addition, for communication training, the visual generation unit can generate visuals that are specialized in communication skills. In this way, the visual generation unit can provide more appropriate visual materials by applying different generation algorithms depending on the training category. Generation algorithms include, but are not limited to, machine learning algorithms and rule-based generation.

[0051] The visual generation unit can prioritize visuals based on the training submission deadlines during the visual generation process. For example, the visual generation unit can prioritize generating visuals for training with approaching submission deadlines. For instance, it can use a generation AI to generate visuals for training with approaching deadlines. The visual generation unit can also postpone generating visuals for training with distant submission deadlines. Furthermore, the visual generation unit can adjust the order of visual generation according to the submission deadlines. This enables the visual generation unit to efficiently provide visual learning materials by prioritizing visuals based on the training submission deadlines. Visual priority may include, but is not limited to, submission deadlines, importance, and urgency.

[0052] The video generation unit can adjust the level of detail in videos based on the importance of the training during video generation. For example, the video generation unit can generate videos with detailed explanations for high-importance training. For instance, the video generation unit can use a generation AI to generate high-importance training videos. It can also generate videos with concise explanations for low-importance training. Furthermore, the video generation unit can adjust the level of detail in videos in stages according to importance. This allows the video generation unit to provide efficient video learning materials by adjusting the level of detail in videos based on the importance of the training. The level of detail in videos includes, but is not limited to, resolution, amount of information, and number of specific examples.

[0053] The video generation unit can apply different generation algorithms depending on the training category when generating videos. For example, for technical training, the video generation unit can generate videos specializing in technical content. For example, the video generation unit can use generation AI to generate technical training videos. Furthermore, for management training, the video generation unit can generate videos specializing in management skills. In addition, for communication training, the video generation unit can generate videos specializing in communication skills. In this way, the video generation unit can provide more appropriate video materials by applying different generation algorithms depending on the training category. Generation algorithms include, but are not limited to, machine learning algorithms and rule-based generation.

[0054] The video generation unit can prioritize videos based on the submission deadlines for training materials. For example, it can prioritize generating videos for training materials with approaching submission deadlines. For instance, it can use a generation AI to generate training videos with approaching deadlines. It can also postpone generating videos for training materials with later submission deadlines. Furthermore, the video generation unit can adjust the video generation order according to the submission deadlines. This allows the video generation unit to efficiently provide video learning materials by prioritizing videos based on the submission deadlines for training materials. Video prioritization may include, but is not limited to, submission deadlines, importance, and urgency.

[0055] The chatbot can adjust the level of detail in its responses based on the importance of the training. For example, the chatbot can provide detailed explanations in responses to high-importance training. For instance, it can use generative AI to respond to high-importance training. It can also provide concise explanations in responses to low-importance training. Furthermore, the chatbot can adjust the level of detail in its responses in stages according to importance. This allows the chatbot to provide efficient responses by adjusting the level of detail in its responses based on the importance of the training. The level of detail in a response includes, but is not limited to, the depth of information, the number of specific examples, and the thoroughness of the explanation.

[0056] The chatbot can apply different response algorithms depending on the training category when responding. For example, the chatbot can provide responses tailored to technical content in technical training. For instance, it can use generative AI to respond to technical training. Furthermore, the chatbot can provide responses tailored to management skills in management training. It can also provide responses tailored to communication skills in communication training. This allows the chatbot to provide more appropriate responses by applying different response algorithms depending on the training category. Response algorithms include, but are not limited to, machine learning algorithms and rule-based responses.

[0057] The chatbot can prioritize responses based on the training submission deadline. For example, it might prioritize responses to training with approaching deadlines. It can use generative AI to respond to training with approaching deadlines. It can also postpone responses to training with distant deadlines. Furthermore, it can adjust the order of responses according to the submission deadlines. This allows the chatbot to respond efficiently by prioritizing responses based on the training submission deadlines. Response priorities may include, but are not limited to, submission deadlines, importance, and urgency.

[0058] The simulation generation unit can adjust the level of detail of the simulation based on the importance of the training during simulation generation. For example, the simulation generation unit can generate detailed simulations for high-importance training. For instance, the simulation generation unit can use a generation AI to generate simulations for high-importance training. The simulation generation unit can also generate concise simulations for low-importance training. Furthermore, the simulation generation unit can adjust the level of detail of the simulation in stages according to its importance. This allows the simulation generation unit to provide efficient simulations by adjusting the level of detail of the simulation based on the importance of the training. The level of detail of the simulation includes, but is not limited to, the depth of information, the number of specific examples, and the thoroughness of the explanation.

[0059] The simulation generation unit can apply different generation algorithms depending on the training category when generating simulations. For example, for technical training, the simulation generation unit generates simulations specialized in technical content. For instance, the simulation generation unit can generate technical training simulations using a generation AI. Furthermore, for management training, the simulation generation unit can generate simulations specialized in management skills. In addition, for communication training, the simulation generation unit can generate simulations specialized in communication skills. This allows the simulation generation unit to provide more appropriate simulations by applying different generation algorithms depending on the training category. Generation algorithms include, but are not limited to, machine learning algorithms and rule-based generation.

[0060] The simulation generation unit generates detailed simulations for high-level training. 2. It generates concise simulations for low-importance training. 3. It adjusts the level of detail of the simulation in stages according to importance. The level of detail of the simulation includes, but is not limited to, the depth of information, the number of specific examples, and the thoroughness of the explanation.

[0061] The evaluation unit can adjust the level of detail of the evaluation based on the importance of the training during the evaluation process. For example, the evaluation unit can perform a detailed evaluation for high-importance training. For example, the evaluation unit can use generative AI to evaluate high-importance training. The evaluation unit can also perform a simplified evaluation for low-importance training. Furthermore, the evaluation unit can adjust the level of detail of the evaluation in stages according to importance. This allows the evaluation unit to perform efficient evaluations by adjusting the level of detail of the evaluation based on the importance of the training. The level of detail of the evaluation includes, but is not limited to, the depth of information, the number of specific examples, and the thoroughness of the explanation.

[0062] The evaluation unit can apply different evaluation algorithms depending on the training category during the evaluation process. For example, the evaluation unit can apply an evaluation algorithm specialized in technical content to technical training. For example, the evaluation unit can use generative AI to evaluate technical training. The evaluation unit can also apply an evaluation algorithm specialized in management skills to management training. Furthermore, the evaluation unit can apply an evaluation algorithm specialized in communication skills to communication training. This allows the evaluation unit to perform more appropriate evaluations by applying different evaluation algorithms depending on the training category. Evaluation algorithms include, but are not limited to, machine learning algorithms and rule-based evaluations.

[0063] The evaluation unit can adjust the order of evaluations based on the submission timing of the training during the evaluation process. For example, the evaluation unit may prioritize the evaluation of training with an approaching submission deadline. For instance, the evaluation unit can use generative AI to evaluate training with an approaching submission deadline. The evaluation unit can also postpone the evaluation of training with a distant submission deadline. Furthermore, the evaluation unit can adjust the order of evaluations according to the submission deadline. This allows the evaluation unit to perform efficient evaluations by adjusting the order of evaluations based on the submission timing of the training. The order of evaluations may include, but is not limited to, submission deadline, importance, and urgency.

[0064] The report generation unit can adjust the level of detail in a report based on the importance of the training. For example, it can generate detailed reports for high-importance training. For instance, it can use a generation AI to generate reports for high-importance training. It can also generate concise reports for low-importance training. Furthermore, the report generation unit can adjust the level of detail in a stepwise manner according to importance. This allows the report generation unit to provide efficient reports by adjusting the level of detail based on the importance of the training. The level of detail in a report includes, but is not limited to, the depth of information, the number of specific examples, and the thoroughness of the explanation.

[0065] The report generation unit can apply different generation algorithms depending on the training category when generating reports. For example, the report generation unit can generate reports focused on technical content for technical training. For example, the report generation unit can use generation AI to generate reports for technical training. The report generation unit can also generate reports focused on management skills for management training. Furthermore, the report generation unit can generate reports focused on communication skills for communication training. In this way, the report generation unit can provide more appropriate reports by applying different generation algorithms depending on the training category. Generation algorithms include, but are not limited to, machine learning algorithms and rule-based generation.

[0066] The report generation unit can prioritize reports based on the training submission deadlines when generating reports. For example, the report generation unit can prioritize generating reports for training with approaching submission deadlines. For instance, the report generation unit can use a generation AI to generate training reports with approaching deadlines. The report generation unit can also postpone generating reports for training with distant submission deadlines. Furthermore, the report generation unit can adjust the order of report generation according to the submission deadlines. This allows the report generation unit to provide efficient reports by prioritizing reports based on the training submission deadlines. Report prioritization includes, but is not limited to, submission deadlines, importance, and urgency.

[0067] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0068] The training program generation system can also include a gamification component. This component can enhance employee motivation by incorporating game elements into the training program. For example, it can award badges or points based on training progress. It can also provide leaderboards to encourage competition among employees. Furthermore, it can reward employees who achieve specific goals. This allows the gamification component to increase employee motivation and improve the effectiveness of the training program.

[0069] The training program generation system can also include a social interaction section. This section can enhance learning effectiveness by facilitating communication among employees. For example, it can provide a forum where employees can discuss training content. It can also offer a chat function where employees can share questions and opinions. Furthermore, it can provide collaboration tools for employees to work on projects together. In this way, the social interaction section can promote communication among employees and enhance learning effectiveness.

[0070] The training program generation system can also be equipped with a virtual reality (VR) section. The VR section allows employees to learn practical skills in a virtual environment. For example, the VR section allows employees to simulate work in a virtual office environment. It also allows employees to give presentations in a virtual conference room. Furthermore, the VR section allows employees to learn how to operate machinery in a virtual factory. This allows the VR section to enhance the effectiveness of training by enabling employees to learn practical skills in a virtual environment.

[0071] The training program generation system can also be equipped with a speech recognition unit. This unit can transcribe employee speech in real time and incorporate it into the training content. For example, it can automatically record what employees say during training for later review. It can also transcribe employee questions and share them with other employees. Furthermore, it can analyze employee speech and suggest improvements to the training program. In this way, the speech recognition unit can enhance learning effectiveness by transcribing employee speech in real time and incorporating it into the training content.

[0072] The training program generation system can also include a feedback collection unit. This unit can collect feedback from employees and use it to improve the training program. For example, it can send out questionnaires after training to gather employee opinions. It can also receive real-time feedback during training. Furthermore, it can analyze employee feedback and suggest improvements to the training program. In this way, the feedback collection unit can collect feedback from employees and use it to improve the training program.

[0073] The training program generation system can also include a mobile-enabled component. This component allows employees to access training programs from their smartphones and tablets. For example, it can provide a mobile app for the training program. It can also optimize the training program content for mobile devices. Furthermore, it can provide offline functionality to allow employees to continue training while on the go. This enables employees to access training programs from their smartphones and tablets, increasing learning flexibility.

[0074] The training program generation system can also be equipped with a data visualization unit. This unit can deepen understanding by visually displaying employee learning progress and training effectiveness. For example, the data visualization unit can display employee learning progress using graphs and charts. It can also visualize training effectiveness and provide this information to employees and managers. Furthermore, the data visualization unit can visually indicate areas for improvement in the training program. In this way, the data visualization unit can visually display employee learning progress and training effectiveness, leading to a deeper understanding.

[0075] The following briefly describes the processing flow for example form 1.

[0076] Step 1: The analysis department analyzes employees' historical data, current skill levels, and individual goals. Employee historical data includes past projects, work history, and performance evaluations. Skill levels are assessed based on evaluation criteria such as skill matrices and certifications. Goals are set based on specific content and setting methods, including short-term goals, long-term goals, and quantitative goals. Step 2: The generation unit automatically generates and provides the optimal training program based on the analysis results obtained by the analysis unit. The optimal training program includes the type of training, duration, and content. The generation unit generates customized training materials that combine videos, text, and practical exercises, and can adjust the content of the training program according to the skill level and role of the employees. Step 3: The monitoring unit monitors training progress in real time based on the training program generated by the generation unit and provides feedback and support. The monitoring unit monitors employees' learning progress and suggests the next steps based on the learning curve. It can also automatically generate feedback that provides specific areas for improvement and next learning points based on learning progress.

[0077] (Example of form 2) The training program generation system according to an embodiment of the present invention is a system that utilizes multimodal AI to automatically generate and provide in-house training programs that combine videos and text, with an AI agent. This training program generation system addresses the challenges of traditional in-house training programs, which require significant labor time to create and maintain, and the limited resources available to provide uniform training to all employees, as well as the difficulty in providing training that meets the individual needs of employees. To solve these problems, the system consists of the following steps. First, the training program generation system uses an AI agent to analyze employees' historical data, current skill levels, and individual goals, and automatically generates and provides an optimal training program. Specifically, it provides customized training materials that combine videos, text, and practical exercises, which employees can access from home or the office. The training program generation system monitors training progress in real time and provides personalized feedback and support. For example, the training program generation system automatically generates text materials such as explanatory materials, manuals, and case studies according to the employee's skill level. It also generates visual content such as charts and graphs to deepen understanding of topics. Furthermore, it enables the creation of training videos, real-time generation of video subtitles, and multilingual support. It also generates text summaries of lecture content and key points. As an interactive learning experience, the training program generation system features an AI chatbot that answers questions in real time during learning, allowing learners to resolve doubts immediately. It also generates simulations that mimic actual work scenarios, enabling employees to develop practical skills. For progress management and personalized feedback, the training program generation system monitors learners' progress in real time and suggests the next steps based on their learning curve. It automatically generates feedback that provides specific areas for improvement and next learning points based on learning progress. For evaluation and assessment, it automatically generates and evaluates quizzes and tests, and automatically generates explanations for mistakes. Based on learning history, it creates individual competency diagnostic reports and suggests future learning strategies.In this way, the training program generation system can propose and manage optimal training content tailored to each employee's skill level and role, and provide individually customized training materials, thereby streamlining in-house training programs and providing effective learning opportunities.

[0078] The training program generation system according to the embodiment comprises an analysis unit, a generation unit, and a monitoring unit. The analysis unit analyzes employee historical data, current skill levels, and individual goals. Employee historical data includes, but is not limited to, past projects, work history, and evaluation history. Skill levels are evaluated based on evaluation criteria and specific measurement methods, such as skill matrices and certification status. Goals are set based on specific content and setting methods, such as short-term goals, long-term goals, and quantitative goals. The generation unit automatically generates and provides an optimal training program based on the analysis results obtained by the analysis unit. An optimal training program includes, but is not limited to, the type, duration, and content of the training. The generation unit generates customized training materials, such as videos, text, and practical exercises. The generation unit can also adjust the content of the training program according to the employee's skill level and role. The monitoring unit monitors training progress in real time based on the training program generated by the generation unit and provides feedback and support. Specific definitions and criteria of real time include, but are not limited to, seconds, minutes, and instantaneous. The monitoring unit, for example, monitors employees' learning progress and suggests the next steps based on their learning curve. The monitoring unit can also automatically generate feedback that provides specific areas for improvement and next learning points based on learning progress. As a result, the training program generation system according to this embodiment provides an optimal training program based on employees' historical data, skill levels, and goals, and enables efficient training by monitoring progress in real time.

[0079] The analytics department analyzes employee history data, current skill levels, and individual goals. Employee history data includes, but is not limited to, past projects, work history, and performance evaluations. This data is used to gain a detailed understanding of employees' past work experience and achievements. For example, past project data shows what projects employees have participated in and what roles they have played, while work history shows the types of jobs they have held. Performance evaluations include past performance evaluations and feedback, revealing employees' strengths and areas for improvement. Skill levels are assessed based on evaluation criteria and specific measurement methods, such as skill matrices and certifications. Skill matrices list the skills employees possess and assess their proficiency in each skill, while certifications show the qualifications and certifications employees have obtained. This allows for an accurate understanding of employees' current skill levels. Goals are set based on specific content and setting methods, such as short-term goals, long-term goals, and quantitative goals. Short-term goals indicate objectives to be achieved within a few weeks to a few months, while long-term goals indicate objectives to be achieved over several years. Quantitative goals are targets set based on specific numbers and indicators, and are used to measure employee growth and performance. The analytics department comprehensively analyzes this data to identify employees' strengths, weaknesses, and growth opportunities. For example, they use AI to analyze data, identify employee skill gaps, and determine which skills need strengthening. They also determine what kind of training is optimal based on employee goals. This allows the analytics department to provide the foundational data needed to deliver the most suitable training program for each individual employee.

[0080] The generation unit automatically generates and provides an optimal training program based on the analysis results obtained by the analysis unit. An optimal training program includes, but is not limited to, the type, duration, and content of the training. The generation unit generates customized training materials, such as a combination of videos, text, and practical exercises. Video materials are used to make learning content easier to understand visually, while text materials are used to provide detailed explanations and theoretical background. Practical exercises are used to allow employees to experience the learning content firsthand and acquire skills. The generation unit combines these materials to generate customized training programs tailored to the skill level and role of each employee. For example, it provides a program focusing on basic content for beginners and a program including advanced content and practical exercises for advanced learners. The generation unit can also adjust the content of the training program according to the employee's skill level and role. For example, it can focus training on strengthening specific skills for employees lacking those skills, and provide advanced training to further enhance the skills of employees who already possess high skill levels. Furthermore, the generation unit can monitor the progress and effectiveness of the training program in real time and adjust the program content as needed. This allows the generation unit to provide each employee with an optimal training program, supporting efficient and effective learning.

[0081] The monitoring unit monitors training progress in real time based on the training program generated by the generation unit and provides feedback and support. Specific definitions and criteria of "real time" include, but are not limited to, seconds, minutes, or instantaneous. For example, the monitoring unit monitors employee learning progress and suggests the next steps based on the learning curve. The learning curve indicates the employee's learning speed and comprehension, and is used to determine what to learn next and when. The monitoring unit can also automatically generate feedback that provides specific areas for improvement and next learning points based on learning progress. For example, it can use AI to analyze learning data, identify areas where employees are struggling, and provide specific advice to strengthen those areas. Furthermore, the monitoring unit can provide additional support and resources depending on the employee's learning situation. For example, it can provide additional learning materials on specific topics or individual coaching from experts. The monitoring unit can also collect employee feedback to improve the training program. For example, it can collect employee opinions and requests regarding the training program and use that to improve the program's content and format. This allows the monitoring department to effectively support employee learning and continuously improve the quality of training programs.

[0082] The text generation unit can automatically generate text materials. For example, it can automatically generate explanatory materials, manuals, and case studies tailored to the skill levels of employees. For instance, the text generation unit can use a generation AI to generate explanatory materials tailored to the skill levels of employees. It can also use a generation AI to generate manuals tailored to the skill levels of employees. Furthermore, it can use a generation AI to generate case studies tailored to the skill levels of employees. This allows the text generation unit to efficiently provide training content to employees by automatically generating text materials. Text materials include, but are not limited to, manuals, guidebooks, and tutorials.

[0083] The visual generation unit can generate visual content. For example, it can generate visual content such as charts and graphs to deepen understanding of a topic. For instance, the visual generation unit can generate charts using a generation AI. It can also generate graphs using a generation AI. Furthermore, it can generate infographics using a generation AI. This allows the visual generation unit to provide visually easy-to-understand training content by generating visual content. Visual content includes, but is not limited to, charts, illustrations, and infographics.

[0084] The video generation unit can create training videos. For example, the video generation unit can create training videos, generate video subtitles in real time, and support multiple languages. For instance, the video generation unit can create training videos using a generation AI. Furthermore, the video generation unit can generate video subtitles in real time using a generation AI. In addition, the video generation unit can create multilingual training videos using a generation AI. This allows the video generation unit to provide visually and dynamically engaging training content by creating training videos. Training videos include, but are not limited to, lecture videos, demonstration videos, and simulation videos.

[0085] The chatbot unit can provide an AI chatbot that answers questions in real time during learning. For example, the chatbot unit can answer questions that arise during learning in real time. For example, the chatbot unit can provide an AI chatbot that answers questions in real time using generative AI. The chatbot unit can also use generative AI to provide responses that include detailed explanations to questions during learning. Furthermore, the chatbot unit can use generative AI to provide concise and to-the-point responses to questions during learning. As a result, the chatbot unit can instantly resolve learners' doubts by answering questions in real time during learning. AI chatbots include, but are not limited to, natural language processing technology and response patterns.

[0086] The simulation generation unit can generate simulations that mimic actual business scenarios. For example, the simulation generation unit can generate simulations that mimic actual business scenarios, enabling employees to develop practical skills. For instance, the simulation generation unit can use generation AI to generate simulations that mimic actual business scenarios. Furthermore, the simulation generation unit can use generation AI to generate simulated exercises based on business scenarios. In addition, the simulation generation unit can use generation AI to generate virtual environments. This allows the simulation generation unit to cultivate practical skills by generating simulations that mimic actual business scenarios. Simulations include, but are not limited to, business scenarios, simulated exercises, and virtual environments.

[0087] The evaluation unit can automatically generate and evaluate quizzes and tests. For example, the evaluation unit can automatically generate and evaluate quizzes and tests, and also automatically generate explanations for incorrect answers. For instance, the evaluation unit can use a generation AI to automatically generate quizzes and tests. Furthermore, the evaluation unit can use the generation AI to evaluate quizzes and tests. In addition, the evaluation unit can use the generation AI to automatically generate explanations for incorrect answers. This allows the evaluation unit to efficiently assess learners' understanding by automatically generating and evaluating quizzes and tests. Quizzes and tests include, but are not limited to, multiple-choice questions, written answers, and practical skills tests.

[0088] The report generation unit can create individual competency assessment reports. For example, the report generation unit can create individual competency assessment reports based on learning history and propose future learning strategies. For instance, the report generation unit can use a generation AI to create competency assessment reports based on learning history. Furthermore, the report generation unit can use a generation AI to create reports that propose future learning strategies. In addition, the report generation unit can use a generation AI to create reports that include learner skill assessments and performance reviews. This allows the report generation unit to gain a detailed understanding of learners' abilities and propose future learning strategies by creating individual competency assessment reports. Competency assessment reports may include, but are not limited to, skill assessments, performance reviews, and feedback.

[0089] The analysis department can estimate employees' emotions and adjust the timing of the analysis based on the estimated emotions. For example, if an employee is feeling stressed, the analysis department can perform the analysis during a time when the employee is relaxed. For example, the analysis department can estimate employees' emotions using an emotion engine or generative AI. The analysis department can also perform a detailed analysis when an employee is focused. Furthermore, if an employee is tired, the analysis department can perform a simplified analysis and then a detailed analysis later. This allows the analysis department to perform more effective analysis by adjusting the timing of the analysis according to the employee's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0090] The analytics department can analyze an employee's past training history and select the most suitable analysis method. For example, the analytics department can evaluate an employee's current skill level based on the content of training they have received in the past. For example, the analytics department can use generative AI to analyze an employee's past training history. The analytics department can also focus its analysis on topics that an employee has struggled with in the past. Furthermore, the analytics department can prioritize selecting training methods in which an employee has received high marks in the past. In this way, the analytics department can select the most suitable analysis method by analyzing an employee's past training history. Past training history includes, but is not limited to, training programs attended, performance, and feedback.

[0091] The analytics department can filter data based on an employee's current projects and roles during analysis. For example, the analytics department can focus its analysis on skills related to the projects an employee is currently working on. For instance, the analytics department can use generative AI to filter data based on an employee's current projects and roles. The analytics department can also filter the necessary skill sets according to the employee's role. Furthermore, the analytics department can prioritize analysis based on the progress of an employee's projects. This allows the analytics department to perform highly relevant analysis by filtering data based on an employee's current projects and roles. Current projects and roles include, but are not limited to, assigned tasks, project progress, and job title.

[0092] The generation unit can estimate an employee's emotions and adjust the content of the training program it generates based on the estimated emotions. For example, if an employee is feeling stressed, the generation unit will generate a training program that includes relaxing content. For example, the generation unit can estimate an employee's emotions using an emotion engine or a generation AI. The generation unit can also generate a training program that includes challenging content if an employee is focused. Furthermore, if an employee is tired, the generation unit can generate a training program that includes simpler content. In this way, the generation unit can provide more effective training by adjusting the content of the training program according to the employee's emotions. The content of the training program includes, but is not limited to, the training theme, difficulty level, and pace. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0093] The generation unit can adjust the level of detail of the generated training based on its importance. For example, the generation unit can generate programs with detailed explanations and exercises for high-importance training. For instance, the generation unit can use generation AI to generate high-importance training programs. The generation unit can also generate programs with simplified explanations and exercises for low-importance training. Furthermore, the generation unit can progressively refine the training content according to its importance. This allows the generation unit to provide efficient training programs by adjusting the level of detail of the generated training based on its importance. The importance of training includes, but is not limited to, factors such as impact on business operations, urgency, and priority.

[0094] The generation unit can apply different generation algorithms depending on the training category during generation. For example, for technical training, the generation unit can apply a generation algorithm specialized in technical content. For instance, the generation unit can generate technical training programs using generational AI. Furthermore, for management training, the generation unit can apply a generation algorithm specialized in management skills. Additionally, for communication training, the generation unit can apply a generation algorithm specialized in communication skills. This allows the generation unit to provide more appropriate training programs by applying different generation algorithms depending on the training category. Generation algorithms include, but are not limited to, machine learning algorithms and rule-based generation.

[0095] The monitoring department can estimate employees' emotions and adjust monitoring criteria based on those estimated emotions. For example, if an employee is stressed, the monitoring department can reduce the frequency of monitoring. For example, the monitoring department can estimate employees' emotions using an emotion engine or generative AI. The monitoring department can also increase the frequency of monitoring if an employee is focused. Furthermore, the monitoring department can reduce the frequency of monitoring if an employee is tired. This allows the monitoring department to perform more effective monitoring by adjusting monitoring criteria according to employees' emotions. Monitoring criteria include, but are not limited to, progress, performance indicators, and feedback frequency. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0096] The monitoring unit can improve the accuracy of its monitoring by considering the interrelationships of training. For example, the monitoring unit can analyze the interrelationships of training and monitor the progress of related training all at once. For example, the monitoring unit can use generative AI to analyze the interrelationships of training. The monitoring unit can also detect delays in progress early by considering the interrelationships of training. Furthermore, the monitoring unit can monitor for biases in progress based on the interrelationships of training. As a result, the monitoring unit can improve the accuracy of its monitoring by considering the interrelationships of training, enabling more accurate progress management. Interrelationships of training include, but are not limited to, related skills, prerequisites, and dependencies.

[0097] The monitoring department can perform monitoring while considering employee attribute information. For example, the monitoring department can adjust monitoring criteria according to the employee's position. For example, the monitoring department can use generative AI to perform monitoring while considering employee attribute information. The monitoring department can also adjust monitoring criteria according to the employee's years of experience. Furthermore, the monitoring department can adjust monitoring criteria according to the employee's skill level. As a result, the monitoring department can perform monitoring while considering employee attribute information, enabling more individualized progress management. Employee attribute information includes, but is not limited to, age, gender, work history, and skill set.

[0098] The text generation unit can estimate employees' emotions and adjust the expression of the generated text based on the estimated emotions. For example, if an employee is stressed, the text generation unit will use a simple and easy-to-understand expression. For example, the text generation unit can estimate an employee's emotions using an emotion engine or generative AI. The text generation unit can also use an expression that includes detailed explanations if an employee is focused. Furthermore, if an employee is tired, the text generation unit can use a concise and to-the-point expression. In this way, the text generation unit can provide more effective text materials by adjusting the expression of the text according to the employee's emotions. The expression of the text includes, but is not limited to, word choice, writing style, and formatting. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0099] The text generation unit can adjust the level of detail in the text based on the importance of the training during text generation. For example, the text generation unit can generate text with detailed explanations for high-importance training. For example, the text generation unit can use a generation AI to generate high-importance training text. The text generation unit can also generate text with concise explanations for low-importance training. Furthermore, the text generation unit can adjust the level of detail in the text in stages according to importance. This allows the text generation unit to provide efficient text materials by adjusting the level of detail in the text based on the importance of the training. The level of detail in the text includes, but is not limited to, the depth of information, the number of specific examples, and the thoroughness of the explanations.

[0100] The text generation unit can apply different generation algorithms depending on the training category when generating text. For example, for technical training, the text generation unit can apply a generation algorithm specialized in technical content. For instance, the text generation unit can use a generation AI to generate technical training text. Furthermore, for management training, the text generation unit can apply a generation algorithm specialized in management skills. In addition, for communication training, the text generation unit can apply a generation algorithm specialized in communication skills. This allows the text generation unit to provide more appropriate text materials by applying different generation algorithms depending on the training category. Generation algorithms include, but are not limited to, machine learning algorithms and rule-based generation.

[0101] The text generation unit can estimate employees' emotions and adjust the length of the generated text based on the estimated emotions. For example, if an employee is stressed, the text generation unit will generate short, concise text. For example, the text generation unit can estimate employees' emotions using an emotion engine or generative AI. The text generation unit can also generate longer text with detailed explanations if an employee is focused. Furthermore, if an employee is tired, the text generation unit can generate concise and short text. In this way, the text generation unit can provide more effective text materials by adjusting the length of the text according to the employee's emotions. Text length includes, but is not limited to, the number of characters, paragraphs, and pages. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0102] The text generation unit can prioritize texts based on the training submission deadlines during text generation. For example, the text generation unit can prioritize generating texts for training with approaching submission deadlines. For instance, the text generation unit can use a generation AI to generate training texts with approaching deadlines. The text generation unit can also postpone generating texts for training with distant submission deadlines. Furthermore, the text generation unit can adjust the text generation order according to the submission deadlines. This enables the text generation unit to provide efficient text materials by prioritizing texts based on the training submission deadlines. Text prioritization includes, but is not limited to, submission deadlines, importance, and urgency.

[0103] The visual generation unit can estimate employees' emotions and adjust the way it generates visuals based on those estimated emotions. For example, if an employee is stressed, the visual generation unit will generate simple, visually calming visuals. For example, the visual generation unit can estimate an employee's emotions using an emotion engine or a generation AI. The visual generation unit can also generate visuals containing detailed information if an employee is focused. Furthermore, if an employee is tired, the visual generation unit can generate concise, highly visible visuals. In this way, the visual generation unit can provide more effective visual training materials by adjusting the way it expresses visuals according to the employee's emotions. The way it expresses visuals includes, but is not limited to, design style, color scheme, and layout. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0104] The visual generation unit can adjust the level of detail of visuals based on the importance of the training during the visual generation process. For example, the visual generation unit can generate detailed visuals for high-importance training. For instance, the visual generation unit can use a generation AI to generate high-importance training visuals. The visual generation unit can also generate concise visuals for low-importance training. Furthermore, the visual generation unit can adjust the level of detail of visuals in stages according to importance. This allows the visual generation unit to provide efficient visual learning materials by adjusting the level of detail of visuals based on the importance of the training. Visual detail includes, but is not limited to, resolution, amount of information, and number of specific examples.

[0105] The visual generation unit can apply different generation algorithms depending on the training category when generating visuals. For example, for technical training, the visual generation unit generates visuals that are specialized in technical content. For example, the visual generation unit can use generation AI to generate technical training visuals. Furthermore, for management training, the visual generation unit can generate visuals that are specialized in management skills. In addition, for communication training, the visual generation unit can generate visuals that are specialized in communication skills. In this way, the visual generation unit can provide more appropriate visual materials by applying different generation algorithms depending on the training category. Generation algorithms include, but are not limited to, machine learning algorithms and rule-based generation.

[0106] The visual generation unit can estimate employees' emotions and adjust the length of the generated visuals based on the estimated emotions. For example, if an employee is stressed, the visual generation unit will generate short, concise visuals. For example, the visual generation unit can estimate employees' emotions using an emotion engine or a generation AI. The visual generation unit can also generate longer visuals containing detailed information if an employee is focused. Furthermore, if an employee is tired, the visual generation unit can generate concise and short visuals. In this way, the visual generation unit can provide more effective visual training materials by adjusting the length of visuals according to employees' emotions. Visual length includes, but is not limited to, display time, number of pages, and number of frames. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0107] The visual generation unit can prioritize visuals based on the training submission deadlines during the visual generation process. For example, the visual generation unit can prioritize generating visuals for training with approaching submission deadlines. For instance, it can use a generation AI to generate visuals for training with approaching deadlines. The visual generation unit can also postpone generating visuals for training with distant submission deadlines. Furthermore, the visual generation unit can adjust the order of visual generation according to the submission deadlines. This enables the visual generation unit to efficiently provide visual learning materials by prioritizing visuals based on the training submission deadlines. Visual priority may include, but is not limited to, submission deadlines, importance, and urgency.

[0108] The video generation unit can estimate employees' emotions and adjust the presentation of the generated video based on the estimated emotions. For example, if an employee is feeling stressed, the video generation unit can generate a video with relaxing content. For example, the video generation unit can estimate employees' emotions using an emotion engine or generative AI. The video generation unit can also generate a video with detailed explanations if an employee is concentrating. Furthermore, if an employee is tired, the video generation unit can generate a concise and to-the-point video. In this way, the video generation unit can provide more effective video training materials by adjusting the presentation of the video according to the employee's emotions. Presentation methods in the video include, but are not limited to, narration, subtitles, and visual effects. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0109] The video generation unit can adjust the level of detail in videos based on the importance of the training during video generation. For example, the video generation unit can generate videos with detailed explanations for high-importance training. For instance, the video generation unit can use a generation AI to generate high-importance training videos. It can also generate videos with concise explanations for low-importance training. Furthermore, the video generation unit can adjust the level of detail in videos in stages according to importance. This allows the video generation unit to provide efficient video learning materials by adjusting the level of detail in videos based on the importance of the training. The level of detail in videos includes, but is not limited to, resolution, amount of information, and number of specific examples.

[0110] The video generation unit can apply different generation algorithms depending on the training category when generating videos. For example, for technical training, the video generation unit can generate videos specializing in technical content. For example, the video generation unit can use generation AI to generate technical training videos. Furthermore, for management training, the video generation unit can generate videos specializing in management skills. In addition, for communication training, the video generation unit can generate videos specializing in communication skills. In this way, the video generation unit can provide more appropriate video materials by applying different generation algorithms depending on the training category. Generation algorithms include, but are not limited to, machine learning algorithms and rule-based generation.

[0111] The video generation unit can estimate employees' emotions and adjust the length of the generated video based on the estimated emotions. For example, if an employee is stressed, the video generation unit will generate a short, concise video. For example, the video generation unit can estimate employees' emotions using an emotion engine or a generative AI. The video generation unit can also generate a longer video with detailed explanations if an employee is focused. Furthermore, if an employee is tired, the video generation unit can generate a concise and short video. In this way, the video generation unit can provide more effective video training by adjusting the length of the video according to the employee's emotions. Video length includes, but is not limited to, playback time, number of scenes, and number of frames. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0112] The video generation unit can prioritize videos based on the submission deadlines for training materials. For example, it can prioritize generating videos for training materials with approaching submission deadlines. For instance, it can use a generation AI to generate training videos with approaching deadlines. It can also postpone generating videos for training materials with later submission deadlines. Furthermore, the video generation unit can adjust the video generation order according to the submission deadlines. This allows the video generation unit to efficiently provide video learning materials by prioritizing videos based on the submission deadlines for training materials. Video prioritization may include, but is not limited to, submission deadlines, importance, and urgency.

[0113] The chatbot can estimate an employee's emotions and adjust its response method based on the estimated emotions. For example, if an employee is stressed, the chatbot will respond in a calm tone. For example, the chatbot can estimate an employee's emotions using an emotion engine or generative AI. The chatbot can also provide detailed explanations in its responses if the employee is focused. Furthermore, if the employee is tired, the chatbot can provide concise and to-the-point responses. This allows the chatbot to provide more effective responses by adjusting its response method according to the employee's emotions. The chatbot's response method includes, but is not limited to, the tone of response, response speed, and response content. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0114] The chatbot can adjust the level of detail in its responses based on the importance of the training. For example, the chatbot can provide detailed explanations in responses to high-importance training. For instance, it can use generative AI to respond to high-importance training. It can also provide concise explanations in responses to low-importance training. Furthermore, the chatbot can adjust the level of detail in its responses in stages according to importance. This allows the chatbot to provide efficient responses by adjusting the level of detail in its responses based on the importance of the training. The level of detail in a response includes, but is not limited to, the depth of information, the number of specific examples, and the thoroughness of the explanation.

[0115] The chatbot can apply different response algorithms depending on the training category when responding. For example, the chatbot can provide responses tailored to technical content in technical training. For instance, it can use generative AI to respond to technical training. Furthermore, the chatbot can provide responses tailored to management skills in management training. It can also provide responses tailored to communication skills in communication training. This allows the chatbot to provide more appropriate responses by applying different response algorithms depending on the training category. Response algorithms include, but are not limited to, machine learning algorithms and rule-based responses.

[0116] The chatbot can estimate an employee's emotions and adjust the length of its responses based on the estimated emotions. For example, if an employee is stressed, the chatbot will provide a short, to-the-point response. For example, the chatbot can estimate an employee's emotions using an emotion engine or generative AI. The chatbot can also provide a longer response with more detailed explanations if the employee is focused. Furthermore, if the employee is tired, the chatbot can provide a concise and short response. This allows the chatbot to provide more effective responses by adjusting the length of its responses according to the employee's emotions. Response length includes, but is not limited to, the number of characters, paragraphs, or pages. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0117] The chatbot can prioritize responses based on the training submission deadline. For example, it might prioritize responses to training with approaching deadlines. It can use generative AI to respond to training with approaching deadlines. It can also postpone responses to training with distant deadlines. Furthermore, it can adjust the order of responses according to the submission deadlines. This allows the chatbot to respond efficiently by prioritizing responses based on the training submission deadlines. Response priorities may include, but are not limited to, submission deadlines, importance, and urgency.

[0118] The simulation generation unit can estimate an employee's emotions and adjust the content of the simulation it generates based on the estimated emotions. For example, if an employee is stressed, the simulation generation unit will generate a simulation with relaxing content. For example, the simulation generation unit can estimate an employee's emotions using an emotion engine or a generation AI. The simulation generation unit can also generate a simulation with detailed explanations if the employee is focused. Furthermore, if the employee is tired, the simulation generation unit can generate a concise and to-the-point simulation. In this way, the simulation generation unit can provide more effective simulations by adjusting the content of the simulation according to the employee's emotions. The content of the simulation includes, but is not limited to, scenarios, tasks, and conditions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0119] The simulation generation unit can adjust the level of detail of the simulation based on the importance of the training during simulation generation. For example, the simulation generation unit can generate detailed simulations for high-importance training. For instance, the simulation generation unit can use a generation AI to generate simulations for high-importance training. The simulation generation unit can also generate concise simulations for low-importance training. Furthermore, the simulation generation unit can adjust the level of detail of the simulation in stages according to its importance. This allows the simulation generation unit to provide efficient simulations by adjusting the level of detail of the simulation based on the importance of the training. The level of detail of the simulation includes, but is not limited to, the depth of information, the number of specific examples, and the thoroughness of the explanation.

[0120] The simulation generation unit can apply different generation algorithms depending on the training category when generating simulations. For example, for technical training, the simulation generation unit generates simulations specialized in technical content. For instance, the simulation generation unit can generate technical training simulations using a generation AI. Furthermore, for management training, the simulation generation unit can generate simulations specialized in management skills. In addition, for communication training, the simulation generation unit can generate simulations specialized in communication skills. This allows the simulation generation unit to provide more appropriate simulations by applying different generation algorithms depending on the training category. Generation algorithms include, but are not limited to, machine learning algorithms and rule-based generation.

[0121] The simulation generation unit can estimate an employee's emotions and adjust the length of the simulation it generates based on the estimated emotions. For example, if an employee is stressed, the simulation generation unit will generate a short, concise simulation. For example, the simulation generation unit can estimate an employee's emotions using an emotion engine or a generative AI. The simulation generation unit can also generate a longer simulation with detailed explanations if the employee is focused. Furthermore, if the employee is tired, the simulation generation unit can generate a concise and short simulation. In this way, the simulation generation unit can provide more effective simulations by adjusting the length of the simulation according to the employee's emotions. The length of the simulation includes, but is not limited to, execution time, number of steps, and number of tasks. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0122] The simulation generation unit generates detailed simulations for high-level training. 2. It generates concise simulations for low-importance training. 3. It adjusts the level of detail of the simulation in stages according to importance. The level of detail of the simulation includes, but is not limited to, the depth of information, the number of specific examples, and the thoroughness of the explanation.

[0123] The evaluation department can estimate employees' emotions and adjust evaluation methods based on those estimated emotions. For example, if an employee is stressed, the evaluation department may use a simplified evaluation method. For example, the evaluation department can estimate an employee's emotions using an emotion engine or generative AI. The evaluation department can also use a detailed evaluation method if an employee is focused. Furthermore, the evaluation department can use a concise evaluation method if an employee is tired. This allows the evaluation department to perform more effective evaluations by adjusting evaluation methods according to employees' emotions. Evaluation methods include, but are not limited to, evaluation criteria, evaluation methods, and evaluation frequency. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0124] The evaluation unit can adjust the level of detail of the evaluation based on the importance of the training during the evaluation process. For example, the evaluation unit can perform a detailed evaluation for high-importance training. For example, the evaluation unit can use generative AI to evaluate high-importance training. The evaluation unit can also perform a simplified evaluation for low-importance training. Furthermore, the evaluation unit can adjust the level of detail of the evaluation in stages according to importance. This allows the evaluation unit to perform efficient evaluations by adjusting the level of detail of the evaluation based on the importance of the training. The level of detail of the evaluation includes, but is not limited to, the depth of information, the number of specific examples, and the thoroughness of the explanation.

[0125] The evaluation unit can apply different evaluation algorithms depending on the training category during the evaluation process. For example, the evaluation unit can apply an evaluation algorithm specialized in technical content to technical training. For example, the evaluation unit can use generative AI to evaluate technical training. The evaluation unit can also apply an evaluation algorithm specialized in management skills to management training. Furthermore, the evaluation unit can apply an evaluation algorithm specialized in communication skills to communication training. This allows the evaluation unit to perform more appropriate evaluations by applying different evaluation algorithms depending on the training category. Evaluation algorithms include, but are not limited to, machine learning algorithms and rule-based evaluations.

[0126] The evaluation department can estimate employees' emotions and determine evaluation priorities based on those estimated emotions. For example, if an employee is stressed, the evaluation department may prioritize a simpler evaluation. For example, the evaluation department can estimate an employee's emotions using an emotion engine or generative AI. The evaluation department can also prioritize a detailed evaluation if an employee is focused. Furthermore, if an employee is tired, the evaluation department may prioritize a concise evaluation. This allows the evaluation department to conduct more effective evaluations by determining evaluation priorities according to the employee's emotions. Evaluation priorities include, but are not limited to, deadlines, importance, and urgency. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0127] The evaluation unit can adjust the order of evaluations based on the submission timing of the training during the evaluation process. For example, the evaluation unit may prioritize the evaluation of training with an approaching submission deadline. For instance, the evaluation unit can use generative AI to evaluate training with an approaching submission deadline. The evaluation unit can also postpone the evaluation of training with a distant submission deadline. Furthermore, the evaluation unit can adjust the order of evaluations according to the submission deadline. This allows the evaluation unit to perform efficient evaluations by adjusting the order of evaluations based on the submission timing of the training. The order of evaluations may include, but is not limited to, submission deadline, importance, and urgency.

[0128] The report generation unit can estimate employees' emotions and adjust the content of the reports it generates based on those estimated emotions. For example, if an employee is stressed, the report generation unit can generate a concise and to-the-point report. For example, the report generation unit can estimate an employee's emotions using an emotion engine or generative AI. The report generation unit can also generate a report with detailed explanations if an employee is focused. Furthermore, if an employee is tired, the report generation unit can generate a concise and short report. In this way, the report generation unit can provide more effective reports by adjusting the content of the reports according to the employee's emotions. The content of the reports may include, but are not limited to, skill assessments, performance reviews, and feedback. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0129] The report generation unit can adjust the level of detail in a report based on the importance of the training. For example, it can generate detailed reports for high-importance training. For instance, it can use a generation AI to generate reports for high-importance training. It can also generate concise reports for low-importance training. Furthermore, the report generation unit can adjust the level of detail in a stepwise manner according to importance. This allows the report generation unit to provide efficient reports by adjusting the level of detail based on the importance of the training. The level of detail in a report includes, but is not limited to, the depth of information, the number of specific examples, and the thoroughness of the explanation.

[0130] The report generation unit can apply different generation algorithms depending on the training category when generating reports. For example, the report generation unit can generate reports focused on technical content for technical training. For example, the report generation unit can use generation AI to generate reports for technical training. The report generation unit can also generate reports focused on management skills for management training. Furthermore, the report generation unit can generate reports focused on communication skills for communication training. In this way, the report generation unit can provide more appropriate reports by applying different generation algorithms depending on the training category. Generation algorithms include, but are not limited to, machine learning algorithms and rule-based generation.

[0131] The report generation unit can estimate employees' emotions and adjust the length of the generated report based on the estimated emotions. For example, if an employee is stressed, the report generation unit will generate a short, concise report. For example, the report generation unit can estimate employees' emotions using an emotion engine or generative AI. The report generation unit can also generate a longer report with detailed explanations if an employee is focused. Furthermore, if an employee is tired, the report generation unit can generate a concise and short report. In this way, the report generation unit can provide more effective reports by adjusting the length of the report according to the employee's emotions. Report length includes, but is not limited to, the number of characters, paragraphs, or pages. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0132] The report generation unit can prioritize reports based on the training submission deadlines when generating reports. For example, the report generation unit can prioritize generating reports for training with approaching submission deadlines. For instance, the report generation unit can use a generation AI to generate training reports with approaching deadlines. The report generation unit can also postpone generating reports for training with distant submission deadlines. Furthermore, the report generation unit can adjust the order of report generation according to the submission deadlines. This allows the report generation unit to provide efficient reports by prioritizing reports based on the training submission deadlines. Report prioritization includes, but is not limited to, submission deadlines, importance, and urgency.

[0133] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0134] The training program generation system can also include a gamification component. This component can enhance employee motivation by incorporating game elements into the training program. For example, it can award badges or points based on training progress. It can also provide leaderboards to encourage competition among employees. Furthermore, it can reward employees who achieve specific goals. This allows the gamification component to increase employee motivation and improve the effectiveness of the training program.

[0135] The training program generation system can also include a social interaction section. This section can enhance learning effectiveness by facilitating communication among employees. For example, it can provide a forum where employees can discuss training content. It can also offer a chat function where employees can share questions and opinions. Furthermore, it can provide collaboration tools for employees to work on projects together. In this way, the social interaction section can promote communication among employees and enhance learning effectiveness.

[0136] The training program generation system can also be equipped with a virtual reality (VR) section. The VR section allows employees to learn practical skills in a virtual environment. For example, the VR section allows employees to simulate work in a virtual office environment. It also allows employees to give presentations in a virtual conference room. Furthermore, the VR section allows employees to learn how to operate machinery in a virtual factory. This allows the VR section to enhance the effectiveness of training by enabling employees to learn practical skills in a virtual environment.

[0137] The training program generation system can also be equipped with a speech recognition unit. This unit can transcribe employee speech in real time and incorporate it into the training content. For example, it can automatically record what employees say during training for later review. It can also transcribe employee questions and share them with other employees. Furthermore, it can analyze employee speech and suggest improvements to the training program. In this way, the speech recognition unit can enhance learning effectiveness by transcribing employee speech in real time and incorporating it into the training content.

[0138] The training program generation system can also be equipped with a biometrics unit. This unit can acquire employees' biometric information and adjust the training program accordingly. For example, it can monitor employees' heart rate and stress levels and suggest breaks at appropriate times. It can also measure employees' concentration levels and provide more challenging training when their concentration is high. Furthermore, it can assess employees' fatigue levels and provide easier training if fatigue is accumulating. This allows the biometrics unit to adjust the training program based on employees' biometric information, providing more effective training.

[0139] The training program generation system can also be equipped with an emotion analysis unit. This unit can analyze employees' emotions in real time and adjust the training program accordingly. For example, if an employee is feeling stressed, the emotion analysis unit can provide a training program that includes relaxing content. Conversely, if an employee is focused, it can provide a training program with more challenging content. Furthermore, if an employee is tired, it can provide a training program with simpler content. This allows the emotion analysis unit to adjust the training program content according to the employee's emotions, thereby providing more effective training.

[0140] The training program generation system can also include a personalized reminder function. This function can send reminders based on an employee's learning progress to encourage continued training. For example, if an employee has interrupted their training, the personalized reminder function can send a reminder to encourage them to resume. It can also send a congratulatory message when an employee is approaching their goal. Furthermore, if an employee is falling behind in their training progress, the personalized reminder function can send a supportive reminder. In this way, the personalized reminder function can send reminders based on an employee's learning progress to encourage continued training.

[0141] The training program generation system can also include a feedback collection unit. This unit can collect feedback from employees and use it to improve the training program. For example, it can send out questionnaires after training to gather employee opinions. It can also receive real-time feedback during training. Furthermore, it can analyze employee feedback and suggest improvements to the training program. In this way, the feedback collection unit can collect feedback from employees and use it to improve the training program.

[0142] The training program generation system can also include a mobile-enabled component. This component allows employees to access training programs from their smartphones and tablets. For example, it can provide a mobile app for the training program. It can also optimize the training program content for mobile devices. Furthermore, it can provide offline functionality to allow employees to continue training while on the go. This enables employees to access training programs from their smartphones and tablets, increasing learning flexibility.

[0143] The training program generation system can also be equipped with a data visualization unit. This unit can deepen understanding by visually displaying employee learning progress and training effectiveness. For example, the data visualization unit can display employee learning progress using graphs and charts. It can also visualize training effectiveness and provide this information to employees and managers. Furthermore, the data visualization unit can visually indicate areas for improvement in the training program. In this way, the data visualization unit can visually display employee learning progress and training effectiveness, leading to a deeper understanding.

[0144] The following briefly describes the processing flow for example form 2.

[0145] Step 1: The analysis department analyzes employees' historical data, current skill levels, and individual goals. Employee historical data includes past projects, work history, and performance evaluations. Skill levels are assessed based on evaluation criteria such as skill matrices and certifications. Goals are set based on specific content and setting methods, including short-term goals, long-term goals, and quantitative goals. Step 2: The generation unit automatically generates and provides the optimal training program based on the analysis results obtained by the analysis unit. The optimal training program includes the type of training, duration, and content. The generation unit generates customized training materials that combine videos, text, and practical exercises, and can adjust the content of the training program according to the skill level and role of the employees. Step 3: The monitoring unit monitors training progress in real time based on the training program generated by the generation unit and provides feedback and support. The monitoring unit monitors employees' learning progress and suggests the next steps based on the learning curve. It can also automatically generate feedback that provides specific areas for improvement and next learning points based on learning progress.

[0146] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0147] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0148] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0149] Each of the multiple elements described above, including the analysis unit, generation unit, monitoring unit, text generation unit, visual generation unit, video generation unit, chatbot unit, simulation generation unit, evaluation unit, and report generation unit, is implemented by, for example, at least one of the smart device 14 and the data processing device 12. For example, the analysis unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The generation unit is implemented by, for example, the specific processing unit 290 of the data processing device 12. The monitoring unit is implemented by, for example, the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The text generation unit is implemented by, for example, the specific processing unit 290 of the data processing device 12. The visual generation unit is implemented by, for example, the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The video generation unit is implemented by, for example, the specific processing unit 290 of the data processing device 12. The chatbot unit is implemented, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The simulation generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12. The evaluation unit is implemented, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The report generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be changed in various ways.

[0150] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0151] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0152] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0153] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0154] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0155] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0156] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0157] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0158] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0159] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0160] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0161] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0162] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0163] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0164] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0165] Each of the multiple elements described above, including the analysis unit, generation unit, monitoring unit, text generation unit, visual generation unit, video generation unit, chatbot unit, simulation generation unit, evaluation unit, and report generation unit, is implemented, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12. The monitoring unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The text generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12. The visual generation unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The video generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12. The chatbot unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The simulation generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12. The evaluation unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The report generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be changed in various ways.

[0166] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0167] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0168] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0169] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0170] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0171] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0172] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0173] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0174] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0175] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0176] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0177] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0178] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0179] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0180] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0181] Each of the multiple elements described above, including the analysis unit, generation unit, monitoring unit, text generation unit, visual generation unit, video generation unit, chatbot unit, simulation generation unit, evaluation unit, and report generation unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the analysis unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The generation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12. The monitoring unit is implemented by, for example, the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The text generation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12. The visual generation unit is implemented by, for example, the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The video generation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12. The chatbot unit is implemented, for example, by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12. The simulation generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12. The evaluation unit is implemented, for example, by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12. The report generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be changed in various ways.

[0182] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0183] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0184] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0185] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0186] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0187] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0188] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0189] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0190] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0191] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0192] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0193] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0194] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0195] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0196] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0197] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0198] Each of the multiple elements described above, including the analysis unit, generation unit, monitoring unit, text generation unit, visual generation unit, video generation unit, chatbot unit, simulation generation unit, evaluation unit, and report generation unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the analysis unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The generation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12. The monitoring unit is implemented by, for example, the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The text generation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12. The visual generation unit is implemented by, for example, the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The video generation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12. The chatbot unit is implemented, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The simulation generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12. The evaluation unit is implemented, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The report generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be changed in various ways.

[0199] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0200] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0201] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0202] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0203] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0204] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0205] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0206] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0207] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0208] 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.

[0209] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0210] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0211] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0212] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0213] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0214] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0215] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0216] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0217] (Note 1) The analytics department analyzes employee history data, current skill levels, and individual goals. A generation unit that automatically generates and provides an optimal training program based on the analysis results obtained by the aforementioned analysis unit, The system includes a monitoring unit that monitors training progress in real time based on the training program generated by the generation unit and provides feedback and support. A system characterized by the following features. (Note 2) It includes a text generation unit that automatically generates text learning materials. The system described in Appendix 1, characterized by the features described herein. (Note 3) It includes a visual generation unit that generates visual content. The system described in Appendix 1, characterized by the features described herein. (Note 4) It includes a video generation unit for creating training videos. The system described in Appendix 1, characterized by the features described herein. (Note 5) It includes a chatbot section that provides an AI chatbot that answers questions in real time during the learning process. The system described in Appendix 1, characterized by the features described herein. (Note 6) It includes a simulation generation unit that generates simulations that mimic actual business scenarios. The system described in Appendix 1, characterized by the features described herein. (Note 7) It includes an evaluation unit that automatically generates and evaluates quizzes and tests. The system described in Appendix 1, characterized by the features described herein. (Note 8) It includes a report generation unit that creates individual ability assessment reports. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit is We estimate the emotions of our employees and adjust the timing of the analysis based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit is Analyze employees' past training history and select the most suitable analysis method. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit is During the analysis, filtering is performed based on the employee's current project and role. The system described in Appendix 1, characterized by the features described herein. (Note 12) The generating unit is We estimate employees' emotions and adjust the content of training programs generated based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The generating unit is During generation, adjust the level of detail based on the importance of the training. The system described in Appendix 1, characterized by the features described herein. (Note 14) The generating unit is During generation, different generation algorithms are applied depending on the training category. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned monitoring unit, We estimate employees' emotions and adjust monitoring standards based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned monitoring unit, During monitoring, consider the interrelationships of training to improve monitoring accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned monitoring unit, During monitoring, employee attribute information should be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 18) The text generation unit, We estimate employees' emotions and adjust the way text is expressed based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 19) The text generation unit, When generating text, adjust the level of detail in the text based on the importance of the training. The system described in Appendix 2, characterized by the features described herein. (Note 20) The text generation unit, When generating text, different generation algorithms are applied depending on the training category. The system described in Appendix 2, characterized by the features described herein. (Note 21) The text generation unit, It estimates the emotions of employees and adjusts the length of the generated text based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 22) The text generation unit, When generating text, prioritize the text based on when the training was submitted. The system described in Appendix 2, characterized by the features described herein. (Note 23) The aforementioned visual generation unit, We estimate employees' emotions and adjust the way visuals are generated based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 24) The aforementioned visual generation unit, When generating visuals, adjust the level of detail in the visuals based on the importance of the training. The system described in Appendix 3, characterized by the features described herein. (Note 25) The aforementioned visual generation unit, When generating visuals, different generation algorithms are applied depending on the training category. The system described in Appendix 3, characterized by the features described herein. (Note 26) The aforementioned visual generation unit, It estimates the emotions of employees and adjusts the length of the visuals generated based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 27) The aforementioned visual generation unit, When generating visuals, prioritize visuals based on the training submission deadline. The system described in Appendix 3, characterized by the features described herein. (Note 28) The aforementioned video generation unit, We estimate the emotions of our employees and adjust the way videos are expressed based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 29) The aforementioned video generation unit, When generating videos, adjust the level of detail in the videos based on the importance of the training. The system described in Appendix 4, characterized by the features described herein. (Note 30) The aforementioned video generation unit, When generating videos, different generation algorithms are applied depending on the training category. The system described in Appendix 4, characterized by the features described herein. (Note 31) The aforementioned video generation unit, It estimates the emotions of employees and adjusts the length of the generated videos based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 32) The aforementioned video generation unit, When generating videos, prioritize them based on when the training was submitted. The system described in Appendix 4, characterized by the features described herein. (Note 33) The aforementioned chatbot unit is The system estimates the employee's emotions and adjusts the chatbot's response based on those emotions. The system described in Appendix 5, characterized by the features described herein. (Note 34) The aforementioned chatbot unit is When the chatbot responds, adjust the level of detail in the response based on the importance of the training. The system described in Appendix 5, characterized by the features described herein. (Note 35) The aforementioned chatbot unit is When the chatbot responds, it applies different response algorithms depending on the training category. The system described in Appendix 5, characterized by the features described herein. (Note 36) The aforementioned chatbot unit is The system estimates the employee's emotions and adjusts the length of the chatbot's response based on those emotions. The system described in Appendix 5, characterized by the features described herein. (Note 37) The aforementioned chatbot unit is When the chatbot responds, it prioritizes responses based on when the training was submitted. The system described in Appendix 5, characterized by the features described herein. (Note 38) The simulation generation unit, We estimate the emotions of our employees and adjust the content of the simulations generated based on those estimated emotions. The system described in Appendix 6, characterized by the features described herein. (Note 39) The simulation generation unit, When generating simulations, adjust the level of detail of the simulation based on the importance of the training. The system described in Appendix 6, characterized by the features described herein. (Note 40) The simulation generation unit, When generating simulations, different generation algorithms are applied depending on the training category. The system described in Appendix 6, characterized by the features described herein. (Note 41) The simulation generation unit, It estimates the emotions of employees and adjusts the length of the simulation generated based on those estimated emotions. The system described in Appendix 6, characterized by the features described herein. (Note 42) The simulation generation unit, When generating simulations, the simulation prioritization is determined based on when the training was submitted. The system described in Appendix 6, characterized by the features described herein. (Note 43) The evaluation unit, We estimate employees' emotions and adjust evaluation methods based on those estimated emotions. The system described in Appendix 7, characterized by the features described herein. (Note 44) The evaluation unit, During evaluation, adjust the level of detail based on the importance of the training. The system described in Appendix 7, characterized by the features described herein. (Note 45) The evaluation unit, During evaluation, different evaluation algorithms are applied depending on the training category. The system described in Appendix 7, characterized by the features described herein. (Note 46) The evaluation unit, The system estimates employees' emotions and determines evaluation priorities based on those estimated emotions. The system described in Appendix 7, characterized by the features described herein. (Note 47) The evaluation unit, During evaluation, the order of evaluations will be adjusted based on when the training was submitted. The system described in Appendix 7, characterized by the features described herein. (Note 48) The report generation unit, We estimate employees' emotions and adjust the content of reports generated based on those estimated emotions. The system described in Appendix 8, characterized by the features described herein. (Note 49) The report generation unit, When generating reports, adjust the level of detail in the report based on the importance of the training. The system according to appended note 8, characterized in that... (Appended note 50) The report generation unit Applies different generation algorithms according to the category of training when generating a report The system according to appended note 8, characterized in that... (Appended note 51) The report generation unit Estimates the feelings of employees and adjusts the length of the report generated based on the estimated feelings of the employees The system according to appended note 8, characterized in that... (Appended note 52) The report generation unit Determines the priority of the report based on the submission time of the training when generating the report The system according to appended note 8, characterized in that...

Explanation of reference signs

[0218] 10, 210, 310, 410 Data processing system 12 Data processing device 14 Smart device 214 Smart glasses 314 Headset-type terminal 414 Robot

Claims

1. The analytics department analyzes employee history data, current skill levels, and individual goals. A generation unit that automatically generates and provides an optimal training program based on the analysis results obtained by the aforementioned analysis unit, The system includes a monitoring unit that monitors training progress in real time based on the training program generated by the generation unit and provides feedback and support. A system characterized by the following features.

2. It includes a text generation unit that automatically generates text learning materials. The system according to feature 1.

3. It includes a visual generation unit that generates visual content. The system according to feature 1.

4. It includes a video generation unit for creating training videos. The system according to feature 1.

5. It includes a chatbot section that provides an AI chatbot that answers questions in real time during the learning process. The system according to feature 1.

6. It includes a simulation generation unit that generates simulations that mimic actual business scenarios. The system according to feature 1.

7. It includes an evaluation unit that automatically generates and evaluates quizzes and tests. The system according to feature 1.

8. It includes a report generation unit that creates individual ability assessment reports. The system according to feature 1.

9. The aforementioned analysis unit is We estimate the emotions of our employees and adjust the timing of the analysis based on those estimated emotions. The system according to feature 1.

10. The aforementioned analysis unit is Analyze employees' past training history and select the most suitable analysis method. The system according to feature 1.

Images